Received 4 March 2023, accepted 20 March 2023, date of publication 22 March 2023, date of current version 28 March 2023.

Digital Object Identifier 10.1109/ACCESS.2023.3260763

Big Data ML-Based Fake News Detection Using

Distributed Learning
ALAA ALTHENEYAN AND ASEEL ALHADLAQ
Department of Computer Science and Engineering, College of Applied Studies and Community Services, King Saud University, Riyadh 11495, Saudi Arabia
Corresponding author: Alaa Altheneyan ([email protected])
This work was supported by Researchers Supporting Project number (RSPD2023R532), King Saud University, Riyadh, Saudi Arabia.

ABSTRACT Users rely heavily on social media to consume and share news, facilitating the mass dis-
semination of genuine and fake stories. The proliferation of misinformation on various social media
platforms has serious consequences for society. The inability to differentiate between the several forms of
false news on Twitter is a major obstacle to effective detection of fake news. Researchers have made
progress toward a solution by emphasizing methods for identifying fake news. The dataset FNC-1, which
includes four categories for identifying false news, will be used in this study. The state-of-the-art methods
for spotting fake news are evaluated and compared using big data technology (Spark) and machine learning.
The methodology of this study employed a decentralized Spark cluster to create a stacked ensemble
model. Following feature extraction using N-grams, Hashing TF-IDF, and count vectorizer, we used the
proposed stacked ensemble classification model. The results show that the suggested model has a superior
classification performance of 92.45% in the F1 score compared to the 83.10 % F1 score of the baseline
approach. The proposed model achieved an additional 9.35% F1 score compared to the state-of-the-art
techniques.

INDEX TERMS Big data, machine learning, fake news, ensemble learning, social media.

I. INTRODUCTION
Many automatically assume that the news is either bogus
The use of social media platforms to disseminate and digest
or legitimate based on the article’s content. Techniques
media has increased in recent years. Social networking sites
based on news content use methods for collecting data and
like Facebook and Twitter generate daily data [1]. It is
tone from fake news stories. The goal of style-based
no secret that the internet is a goldmine of information,
methods for de-detecting false news is to utilize the
especially recent news [2]. The proliferation of fake news
manipulators’ writing styles for detection. By examining
is directly attributable to the internet’s user-friendly nature.
certain language features, we can distinguish fake news
Since fake news is often presented as factual, it is often
from the real thing [3]. However, false news is created with
shared on social media. Often, this data is spread for profit
the intent of fooling readers. Thus, improving the detection
or influencing politics. The effects of fake news on society
of false news using news content style is a difficult problem.
as a whole are profound. In the light of its profound
To assist in avoiding the difficult and time-consuming
impacts, fixing this issue is crucial [3]. Multiple instances
human work of fact- checking, the Natural Language
of false news were reported to have spread on social media
Processing (NLP) industry has shown considerable
during the 2016 US elections, including the presidential
interest in automatic recognition of fake news [6], [7].
election and the nomination of a new Air Marshal in India
Determining the integrity of news is a difficult task, even
[4]. The dissemination of false information has negatively
for automated approaches [8]. Familiarizing with what
affected people’s mental health and society as a whole [5].
other news outlets say on the same issue might be a useful
starting point for recognizing false news. Identifying a
The associate editor coordinating the review of this manuscript and
person’s position is the purpose of this phase. Multiple
approving it for publication was Chong Leong Gan .
tasks, such as evaluating online arguments [9], [10],
verifying the integrity of Twitter rumors [11], [12],
 This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
VOLUME 11, 2023 29447
 A. Altheneyan, A. Alhadlaq: Big Data ML-Based Fake News Detection Using Distributed Learning

FIGURE 1. Overview of the headline and text bodies with their respective stances.

or understanding the argumentation structure of seminal Fools’ jokes, rumors, clickbait, or stated opinions posted
works [13], [14], have traditionally relied on position online with incorrect facts.
identification. In this research work, ‘‘fake news’’ is defined as a
In the first example of evaluating the first False News written article that is manifestly untrue and falsely
Challenge (FNC-1), a media news source discusses a topic disseminated without being authentic mostly accompanird
to create automated fake news detection systems using by malicious intents. This definition includes three
AI technology and machine learning. Almost fifty groups important textual, visual, and audio bases. Other elements
from industry and academics worked on this problem. One such as video-based fake news and audio, are typically
of the objectives of the FNC-1 challenge is to track out ignored when referring to textual fake news; additionally,
a media production dealing with a certain title. It might each element has its linguistic complexities that necessitate
support, challenge, or have nothing to do with the title. Four different machine learning and deep learning algorithms to
potential vantage points from which an essay is to be detect and solve problems such as ‘Deep Fake,’ etc. The
written. The guidelines, dataset, and grading criteria for notion also implies that fake news might be fact-checked, an
the FNC- 1 challenge are all available on their site. These important characteristic. Therefore, the claims may be
topics are further shown in Figure 1, which depicts the checked to see if they are true or false. Because rumors are
results of four distinct research. usually hard to verify, they are deleted from the
Multiple deep learning and Recurrent Neural Networks definition because of this inclusion. Conspiracy theories are
(RNN), as well as their modifications, including Convolution classed as rumors because they are persistent rumors that
Neural Networks (CNN) [15], are often employed for NLP are difficult to refute. False information concerning the
tasks and have shown to perform magnificently on NLP- entertainment sector, including hoaxes and April Fools’
related tasks [16], [17], [18]. gags, is not permitted because the objective must be
harmful. Furthermore, the goal is infamous as it seeks to
A. OVERVIEW OF FAKE NEWS DETECTION affect public opinion in favor of a specific message. It
In 2017, Facebook released a white paper that explored also removes text bits that were mistakenly published
the risks of online communication and the management of improperly, such as transposed numbers.
being one of the most prominent social media platforms A model of the connection between headlines and news
today. Weedon, Nuland, and Stamos also noticed the content is necessary for identifying clickbait. It is also
growing challenge of using the enigmatic phrase ‘‘fake crucial to tell the difference between false news and
news,’’ and proclaimed that ‘‘the overuse and clickbait. The term ‘‘clickbait’’ refers to articles with
misapplication of the term ‘‘fake news’’ might be enticing headlines written to attract online audience or
challenging since we cannot understand or adequately traffic; when people click on such a headline, they end up at
address these concerns without shared definitions’’ [19]. a different website with poorly written articles that have
The word can apply to anything from virtually incorrect nothing to do with the subject line. So, clickbait is written
news articles to deceptions, April with one goal: getting more people to visit a website that
29448 VOLUME 11, 2023
 A. Altheneyan, A. Alhadlaq: Big Data ML-Based Fake News Detection Using Distributed Learning

relies on advertising to make

VOLUME 11, 2023 29449

 A. Altheneyan, A. Alhadlaq: Big Data ML-Based Fake News Detection Using Distributed Learning

money. The motive is monetary gain rather than furthering and quantity with which it is distributed have changed:
a political agenda via disseminating false information. social media platforms
A great example is the deliberately spread of false news
about Hillary Clinton by Russian trolls in the 2016
presiden- tial election campaign, which was designed to
affect people’s voting choices away from Hillary and toward
Donald Trump. This instance demonstrates how dangerous
it can be when false information spreads on critical issues.
Of course, there’s another problem with false news, toxic
information is spread for no reason to sow doubt, stir up
chaos, and make it difficult for readers to tell fact from
fiction.

1) SOCIAL MEDIA AND FAKE NEWS

Global knowledge dissemination has been democratized
because of technological advancements and the emergence
of social media. Important news organizations have
invested heavily in digital journalism, generating content
for media platforms, and growing their reach via social
media and online tools. Furthermore, online social media
platforms are becoming most important sites for
information spreading. Dissemination of information
allows for the exchange of ideas and the connectivity of
previously inaccessible locations. It enables users to
generate opinions about the information platforms offer
from many perspectives.
In the past, media companies have invested heavily in
creating their presence online, with online media
networking sites playing a significant role. They use social
media platforms such as Facebook and Twitter to promote
their material, spread information/news, and develop a
network of individuals they may engage with. On the other
hand, users benefit from social media’s technical
developments since people now have access to a wide range
of information sources.
The current digital landscape for information dissemina-
tion and the challenges that media organizations face in an
ever-present media environment have resulted in substantial
changes in how news organizations are founded. Economic,
technical, and social pressures have combined with the
desire to be always noticeable, race of reporting with
similar speed and excitement, getting followers, creating an
atmosphere where fake news is prevalent.
The latest technological advancements in social media
have undoubtedly provided a hostile environment for
spread- ing online lies in a primarily deregulated media
financed and driven by advertising. The motivation for
good is usually overshadowed by the desire for profit,
which significantly influences how the medium changes
over time. According to the above, fake news exists on
social media alongside real news, and the difficulty appears
to be distinguishing them. While fake news is not new, the
speed it travels and the worldwide reach of the instruments
that can distribute it are unprecedented. Consequently, fake
news emerges on social media in the same context as actual
news, and the problem appears to be discerning between the
two. While fake news is not a new phenomenon, the pace
29450 VOLUME 11, 2023
 A. Altheneyan, A. Alhadlaq: Big Data ML-Based Fake News Detection Using Distributed Learning

such as Twitter, Facebook, and Instagram provide an ideal

ground for quickly transmitting fake news. Furthermore, bots
are increasingly being utilized to distort information, disrupt
social media conversations, and draw users’ attention,
according to the same author.

2) USERS’ RE-SHARING BEHAVIOR AND FAKE NEWS

From the perspectives discussed so far, it can be deduced that
social media sites play an essential role in disseminating false
information. Furthermore, internet users are to blame for
spreading false information. There are two main types of data
sharing on online sharing sites: self-disclosure, in which a user
voluntarily discloses private information, and re- sharing, in
which a user distributes material already created by another
user of the site or a third party. Distributing low-quality,
erroneous, or purposefully misleading material may have
negative implications, such as spreading false news, but
spreading high-quality information can assist in development
of a more informed community. One of the most common
ways information is disseminated online is by re-sharing,
which includes retweeting, re-posting, re- vining, and re-
blogging. In social media, for instance, it is common practice
for users to write articles, distribute them among their
networks, and engage in related online discourse. Social media
users may engage in this practice with various apps. Sharing
information rapidly is essential in many situations, including
political campaigns and times of crisis, and therefore sites like
Twitter, YouTube, and Facebook have become more important.
Individuals are also using social media accounts for news
production and dissemination.
In the case of social media, for instance, someone may
spread false information (or even create a fake tale and post it).
Resharing is a feature of many social media sites, so if one
person shares a story, it increases the likelihood that others will
do the same. Several proposed remedies are present, but there
is still much disagreement over what constitutes ‘‘fake news’’,
how it spreads, and how it affects social and political
outcomes. Multiple major actors—including social media
platforms, users, and groups against the spread of fake news—
may be able to control the spread of false information on the
internet. This brief theoretical overview of the Uses and
gratifications theory (UGT), the filter bubble phenomenon, and
social media re-sharing behavior provides important context
for the current investigation. According to UGT’s research, the
Ellinika-Hoaxes-Facebook demographic represents an engaged
audience searching for high-quality news and information from
sources outside their echo chamber via media consumption.
Know that this demographic is engaged, actively looking for
information and trying to confirm the integrity of rumours they
may have seen on social media. Users’ familiarity with the
Internet, social media, and other media is crucial for
identifying the prevalence of false news on these platforms and
stopping its spread. To properly answer the Formulation of
research question (RQ) and draw conclusions on how members
of the Ellinika-Hoaxes-Facebook group use particular media
to

VOLUME 11, 2023 29451

 A. Altheneyan, A. Alhadlaq: Big Data ML-Based Fake News Detection Using Distributed Learning

FIGURE 2. Category of fake news on social media.

detect and prevent the spread of false news, it is necessary informa- tion has grown and evolved throughout time,
to conduct research into their online behavior. including print,

B. FAKE NEWS CHARACTERIZATION

The principle of fake news has two components:
authenticity and purpose. The word ‘‘authenticity’’ refers to
the fact that misleading news often contains false
information that may be demonstrated to be untrue.
Conspiracy theories, for example, are not included in the
definition of fake news since it is nearly hard to tell whether
they are real or false in most situations. According to the
second component, the erroneous material’s objective was to
deceive the reader. Figure 2 represents the category of fake
news on social media. The characterization module
represents fake news belonging to traditional media and
social media. The second module shows the fake news
detection techniques used for both traditional and social
media.
First, to identify fake news, understand the text context
and the procedure to categorize it. It is vital to begin by
characterization when developing detection models, and it
is also necessary to grasp what fake news is before
attempting to identify it. It is also not easy to develop a
universally agreed definition for ‘‘fake news: Stories that
are purposely and verifiably misleading and mislead
readers’’. As per Wikipedia, deliberate misinformation or
hoaxes spread via multiple online platforms and news
channels or digital social media constitute a sort of fake
journalism or propaganda [20]. Today’s fake news is
manipulative and diversified in topics, techniques, and
platforms. It consists of two components: authenticity and
intent. Fake news material that contains inaccuracies that
may be verified falls under authenticity. However, it
excludes conspiracy theories because they are difficult to
prove actual or wrong in most circumstances. The second
part refers to the misleading material written to deceive the
reader.

C. TRADITIONAL MEDIA FAKE NEWS

The media ecosystem supporting the spread of false
29452 VOLUME 11, 2023
 A. Altheneyan, A. Alhadlaq: Big Data ML-Based Fake News Detection Using Distributed Learning

broadcast, social media, and digital platforms. Before the rise

of social media, this was seen as a concern because of its role
in disseminating false information. Multiple psychological and
social scientific foundations are used to characterize the effects
of false news on individuals and the social knowledge
environment. Humans aren’t great at spotting believable
stories from those who aren’t. Several psychological and
perceptual theories explain this phenomenon and the impact of
misleading information. Traditional false news exploits
readers’ emotional vulnerabilities. Incorrect information is
more likely to irritate clients due to the following two major
factors:
• Customers with naive realism believe that their view of
the world is valid and that others who disagree with them
are irrational or dishonest [21].
• People are more likely to be presented with data that
backs with their existing worldview. The cognitive biases
that are part of the human condition led con- sumers to
regularly confuse fake news with the genuine thing [22].
By analysing the news ecosystem as a whole, we may be
able to pinpoint some of the societal factors that fuel the spread
of disinformation. Theories of Social Identity [23] and
Normative Influence [5] argue that the need for others’
approval is central to a person’s sense of self and identity,
which increases the likelihood that users will prefer the
anonymity and security of online platforms when obtaining
and sharing news content, even if it is false.

D. THE EXTRACTION OF FEATURES

Unlike social media, where additional social data may help
identify false news, conventional news organizations rely on
content like text and photographs to spot and identify fake
news. Some representative features of false news were shown
in Figure 3. We will next examine how to extract and
disseminate relevant data from the media.

1) TEXTUAL CONTEXT BASED

Three important methods to make up news content:

VOLUME 11, 2023 29453

 A. Altheneyan, A. Alhadlaq: Big Data ML-Based Fake News Detection Using Distributed Learning

FIGURE 3. Feature representation of fake news.

• Source-Where it takes the news or a piece of news one is lexicon, the second is semantics, then discourse
getting source, who published it, and source is and syntax. Structure-related features are also technique-
authentic or not.
oriented features because most quantification depends on
• Headline-A detailed summary of the news’s quality to
NLP-based methods. The critical challenge at the lexical
entice readers. level is identifying the frequency statistics of a word(s),
• Body Text-It shows the actual story/content of the
news. The most common method for detecting false letter(s), or other entity, which may be done correctly
information is by applying n-gram models. Part-of-Speech (POS)-taggers
to look at the content of the news piece. The substance of a execute shallow syntax tasks at the syntax level, making
news report is generally separated into two types: textual tagging and assessment of POS easier. Probabilistic
and visual. Much of the news material is presented in the Context- Free Grammars (PCFG) analyses Context-Free
textual mode, one of these modalities. As previously said, Grammars (CFG) by performing deep syntax level
fake news consists of manipulating the audience, and it operations with parse trees. On the semantic level, word
does so via the use of specific terminology. Non-fake count (WC) and linguistic inquiry are also utilized to create
news, however, is usually transferred to a separate semantic classes for semantic features.
language list since it is more legitimate. Attribute-based
language characteristics and structure-related language E. PROBLEM FORMULATION
features are two common categories. Developing a Spark distributed cluster-based environment
for efficiently detecting fake news articles via a supervised
2) ATTRIBUTE-BASED LANGUAGE FEATURES learning paradigm necessitated solving two sub-problems.
They involve the ten parallel aspects of content style’s First, our model needed to learn how to recognize and seize
linguistic elements. These aspects involve volume, uncer- necessary information in lengthy and textual news articles
tainty, objectivity, emotions, diversity, and readability [24]. for categorizing the association between news item titles
Although attribute-based language characteristics are gener- and related meta descriptions.
ally extremely important, explainable, and predictable, they
are often useless in assessing deception style compared F. RESEARCH OBJECTIVES
to structure-based features. Furthermore, attributed features In the first section of this research, we examine the effec-
require extra resources for deception detection, which may tiveness of Recurrent Neural Networks (RNN) in modeling
take longer and significantly focus on correct feature news articles to identify the link between an article’s body
evaluation and filtering. content and its title. As part of our research, we use the
3) STRUCTURE-BASED LANGUAGE FEATURES dataset made available for the FNC-1 competition to train
Content style is defined by structure-based linguistic prop- and assess a classifier. We want the classifier to be able to
erties and must have four levels of language: the first do the following.

29454 VOLUME 11, 2023

A. Altheneyan, A. Alhadlaq: Big Data ML-Based Fake News Detection Using Distributed Learning

FIGURE 4. Graphical representation of proposed approach.

• Use the Spark framework to research, assess, and efficient stacked ensemble classifier for fake news
compare several machine learning classification techniques detection.
on four classes from the FNC-1 dataset.
In an experiment, we demonstrate that the recommended
• Given a title and an article, determine if the article method can accurately identify fake news and beats current
agrees with, disagrees with, discusses, or is irrelevant to the state of the art algorithms.
assertion made in the headline.
• To propose an efficient, systematic, and functional G. PAPER LAYOUT
approach based on machine learning algorithms for The remaining paper contains the following sections. Related
detecting fake news using Spark and to design an
work is reviewed in section II. The dataset used for
VOLUME 11, 2023 29455
 A. Altheneyan, A. Alhadlaq: Big Data ML-Based Fake News Detection Using Distributed Learning

experimentation and preliminaries is discussed in section view concerning a specified target, such as a single topic,
III. The experimental results and discussion are articulated headline, or even a person [15], [29]. Consequently, there
in section IV. Finally, section V presents a conclusion, and are three factors and a machine learning based
future work. categorization technique to determine how the comparison
occurs. The group’s titles (for example: help, against, for,
II. LITERATURE REVIEW
or neutral) are determined by the issue. Political arguments
This section provides an overview of the previous
[30], [31], articles [32], [33], and even internal company
research’s difficulties in identifying fake news. To identify
dialogues [25], [34], which stretches a wide range of fields
fabricated news stories, it is necessary to do rumor
may be referred to as categories. Detecting the stretch of
detection and identification. It is important to distinguish
Tweets or short texts such as hearsays [35] or
between Real and fake news since both are based on
microblogging accounts has gotten much attention in
deliberate fab- rication. Fake news identification is
opinion mining. ‘‘Hillary Clinton’’ as a celebrity,
particularly difficult when detecting news based on
‘‘Atheism’’ as a specific issue, or the profess that ‘‘E-
characteristics. Tweets and social context can be used to
cigarettes are safer than regular cigarettes’’ are examples of
generate features. As a result, we assess prior work based
objectives presented in the available datasets. Shared tasks
on single-modality and stance identification.
for providing such datasets and promoting research have
emerged in several languages.
A. TEXTUAL CONTENT BASED
The sub-task for exposing stance in Tweets [26] was
Most earlier news identification studies relied mainly on
presented at SemEval-2016, with roughly 5,000 tweets
textual elements and user metadata. Text based features are
in English, including five familiar subjects. The task has
statistically extracted from message text content and have
initiated a variety of approaches, including conventional
been extensively discussed in the literature on fake news
techniques (for example, KNN [36], SVM [22], or essen-
identification. The textual component extracts unique writing
tial attributes given by methods [34]) and deep learning
styles [15], [19], [20] and emotional sensations [18] that are
approaches (e.g., BiLSTM [37], Bidirectional Conditional
prominent in fake news.
Encoding [27], [34]). Furthermore, public datasets, for
Network connections, style analysis, and individual emo-
instance, the Multi-Perspective Consumer Health Query
tions have all been proven to contribute to detecting fake
dataset [38] dedicated to exposing the stance of sentences
news [19]. After reading these posts, [20] explored the
taken from high-quality articles on five separate assertions.
writing style and its effects on readers’ viewpoints and
Like ‘‘Sun exposure causes skin cancer,’’ the dataset is
attitudes. Emotion is a significant predictor in many fake
avail- able to work on the development of new and exciting
news detection studies, and most rely on user positions or
work. It contains an in-depth examination of various
simple statistical emotional features to convey emotion. In
approaches to the two goals listed above. The need for well-
[15] authors introduced a novel dual emotion-based method
interpreted data in languages other than English has rapidly
for identifying fake news that can learn from publishers’
increased notation efforts and collaborative tasks aimed at
and users’ content, user comments, and emotional
furthering research. There are efforts like Stance-Cat, an
representation. Reference [25] employed an ML model for
aim for identifying attitudes in Spanish and Catalan tweets
identifying fake news that employs convolution filters to
[39], a proposal and database of brief statements in Russian
distinguish between different granularities of text
online forums [40], and even projects that integrate several
information. They investigated the issue of posture
languages [41].
categorization in an innovative approach to consumer
A group of volunteers from industry and academia
health information inquiries and achieved 84% accuracy
launched the Fake News Challenge in December 2016 [10].
using the SVM model.
Using Machine Learning, Natural Language Processing
B. SOCIAL CONTEXT BASED
(NLP), and Artificial Intelligence (AI), this competition
aimed to encourage the development of technologies that
User generated social media interactions with news stories
could assist human fact-checkers in detecting deliberate
may give additional information, in addition to aspects
deception in news reporting as a first step, the organizers
directly relevant to the substance of the stories. In [26]
decided to research what other media outlets have to say
authors proposed a novel approach employing a knowledge
about the topic. Consequently, they decided to introduce the
graph to identify fake news based on actual content. A event with a stance detection challenge in the first round
graph-kernel- based approach used be [27] to discover of competition. The organizers collected data on headlines
propagation patterns and attitudes. On the other hand, social and body text before the event. In the competition, they
context features are difficult to gather because they are asked participants to create classifiers that could reliably
loud, unstructured, and time-consuming [28]. classify a body text’s viewpoint on a given headline into
one of four categories: ‘‘disagree’’, ‘‘agree’’, ‘‘discuss’’ or
C. STANCE DETECTION OVERVIEW
‘‘unrelated’’. On this task’s test set, the top three teams
From a broad viewpoint, stance detection can be elaborated achieved accuracy rates greater than or equal to 80%. The
as the problem of determining an author’s or text’s point of top team’s model combined Gradient Boosted Decision
29456 VOLUME 11, 2023
 A. Altheneyan, A. Alhadlaq: Big Data ML-Based Fake News Detection Using Distributed Learning

Trees and Deep Convolutional Neural Networks.

VOLUME 11, 2023 29457

 A. Altheneyan, A. Alhadlaq: Big Data ML-Based Fake News Detection Using Distributed Learning

D. MISLEADING HEADLINES done on posture identification problems, such as

Identifying misleading headlines in this research required linking a
classifying each article’s treatment of the assertion made in
the title into one of four categories: (a) agrees, (b) discusses,
(c) disagrees, and (d) irrelevant (headline and different
topic discussed in body text). As a result of the proliferation
of annotated corpora and the increased use of new
technologies to combat the fake news pandemic, a new
obstacle has recently presented itself to the field of fake
news analysis [8]. In this setting, several research
challenges and competitions are presented. The most recent
and important ones are then dissected in great detail. The
evolving dataset [18] was used to create the fake news
Challenge6 (FNC-1) [42]. The goal of FNC-1 is to serve as
a benchmark for research into AI- based technologies,
machine learning, and natural language processing as they
apply to the detection of false news. The planners decided
to begin with stance disclosure to finish this macro-
challenge. The FNC-1 dataset, which included over 75,000
instances labelled as either ‘‘agreeing,’’ ‘‘discussing,’’
‘‘disagreeing,’’ or ‘‘unrelated,’’ was made publicly
available. Given the headline ‘‘Robert Plant Ripped up
$800M Led Zeppelin Reunion Contract,’’ the following
excerpts illustrate the categories mentioned, as annotated by
the barometer in the FNC-1 dataset.
Body content that conforms to the headline is an instance
of agree class. These topics might be discussed in a
discussion class: The article’s main body addresses the
same issue as the title, but does not take a position on the
matter. For instance, when comparing the headline and
body content, one might say they belong to different
classes. The FNC-1 competition had 200 entries, the top
10% of which averaged 82% relative points. The group
developed a basic criterion using just hand-coded features
and a Gradient Boosting Classifier, both freely accessible
on GitHub. Top systems were UCLMR [43], Talos [44],
and the Athene system [23]. The CNNs utilised by Talos
[44] were one-dimensional, active at the word level, and
trained using Google News topic vectors for the article’s
main body and title. The data from the CNN is then fed into
a multi-layer perceptron (MLP) model that generates one of
four possible classes of results. Next, it undergoes a
comprehensive, start-to-finish training process. The system
won the FNC-1 competition with its superior performance
using the CNN-MLP combo. In recent trials, several
research have employed FNC-1 with encouraging
outcomes. For instance, [45] suggested a tree- like structure
for the linked classes by combining the existing disagree,
agree, and discuss ones. This approach uses a two- layer
neural network to learn a hierarchical representation of
classes, achieving a weighted accuracy of 88.0%.
Additionally, scholars built a stance detection model
using accomplishment transfer learning on a Roberta Deep
Bidirectional Transformer Language Model. They achieved
a weighted accuracy of 90.01% by employing Bidirectional
Cross Attention between claim article pairings via pair
encoding with self-attention [46]. Further work should be
29458 VOLUME 11, 2023
 A. Altheneyan, A. Alhadlaq: Big Data ML-Based Fake News Detection Using Distributed Learning

news title and article content, outside the FNC-1 Challenge

and dataset. Several writers have compiled claims and
criticisms [21], [47] to help with identification. Some analytic
effort is devoted to ‘‘argument mining,’’ in which the headline
presents an argument not supported by the content. While
argument mining is effective in solving the problem of posture
identification, other tasks that discover semantic relationships
within the text, such as inconsistency detection [48], contrast
detection [49], and synthesis detection [50], may also be
useful. Mishra et al. provided a comprehensive taxonomy for
spotting false news, outlining the many forms of
disinformation and what sets them apart. Multiple mechanisms
exist to track down those who propagate false information.
Multiple liar, false news, and corpus datasets have been used
to compare traditional machine and deep learning techniques.
This study demonstrated that deep learning methods
outperformed more conventional machine learning strategies.
Bi-LSTM outperforms the competition in detecting bogus
news with an F1 score of 96.
In [43] authors introduced the Multi-integrated Domain
Adaptive Supervision (MIDAS) system to automatically
choose the model that best fits a particular collection of data
drawn from random distributions. By using local smoothness
as a proxy for accuracy and the relevance of training data,
MIDAS can increase generalization accuracy across nine
distinct fake news datasets. MIDAS has a larger than 10%
success rate in recognizing bogus news linked to COVID-19,
compared to other labelling methods [43]. The results of the
literature review were summarized in Table 1.

III. PROPOSED METHODOLOGY

This section describes a comprehensive detail about the pro-
posed approach. The proposed approach comprises multiple
steps of data analysis, feature extraction, single classifier, and
the ensemble classifier classification, as shown in Figures 4.
The challenge of fake news in stage 1, a particular purpose and
dataset is presented to handle the difficulty of identifying fake
news. The challenge’s primary motivation is to build a semi-
automated pipeline that examines the attitude of several news
items on a specific topic. Thus, the dataset comprises
occurrences with a title, article body, and one of the four
labels ‘‘Disagree’’, ‘‘Agree’’, ‘‘Unrelated’’, and ‘‘Discuss’’.
Figure 4 summarizes our proposed approach, which consists of
the steps to achieve fake news classification by solving multi-
class labels. The first part explains the corpus creation
technique by combining stances and bodies based on news
article ids. The second phase describes the preprocessing
processes done on news article text. The third phase
demonstrates techniques to feature selection or dimensionality
reduction. The fourth stage describes each ML and ensemble
model used in this study. Finally, the last phase outlines this
study’s various ensemble learning models. We divide the
dataset into two parts for experiments: training and testing. The
training dataset comprises 75% of the data, whereas the testing
dataset contains 25%.

VOLUME 11, 2023 29459

 A. Altheneyan, A. Alhadlaq: Big Data ML-Based Fake News Detection Using Distributed Learning

TABLE 1. Literature review summary.

A. DATASET
Challenge Stage 1 (FNC-1) to investigate the potential of
Carnegie Mellon University adjunct professor dean Pomer- machine learning and natural language processing in the
leau, Joostware, and the AI Research Corporation founder fight against fake news [27]. This issue was the driving force
Delip Rao hosted a competition called the Fake News for the competition, which focused on stance detection. This
29460 VOLUME 11, 2023
 A. Altheneyan, A. Alhadlaq: Big Data ML-Based Fake News Detection Using Distributed Learning

section

VOLUME 11, 2023 29461

 A. Altheneyan, A. Alhadlaq: Big Data ML-Based Fake News Detection Using Distributed Learning

TABLE 1. (Continued.) Literature review summary.

provides an overview of the competition dataset, the stories written in English. Collecting news
baseline used by the FNC-1 organisers, and the winning stories from
strategies used throughout the competition.
It ensued by turning a news story into a headline,
then annotated the title and using the story to show
where they stood on the assertion they introduced. For
this attitude categorization exercise, we have three possible
sets of labels: ‘‘for,’’ ‘‘against,’’ and ‘‘observing.’’ The
developing dataset [27] is the basis for the FNC-1
competition dataset. To create the FNC-1 dataset, we
randomly match headlines and articles from the emerging
dataset depending on their attitude toward the linked
allegation. In addition, the headlines and articles are
separated into related and unrelated groups. Second, and
more difficult, the collection of connected headline-article
pairings is further split into the three classes disagree,
agree, and discuss, allowing for supervision of the job of
evaluating the attitude of an article relative to the assertion
presented in the associated headline. There are 49,972
headline-article pairs in the training set of the FNC-1
dataset, and another set of pairs in the test set. There are
1,689 distinct headlines and 1,648 unique articles used to
build the headline-article pairings that make up the training
set. The test set includes 904 distinct articles and 894
unique headlines. Seventy-three percent are classified as
unrelated, 7.4 percent as agreeing, 1.7 percent as
disagreeing, and 17.8 percent as debating. About 72.2
percent of the test data is irrelevant; 7.4 percent is in
agreement; 2.7 percent is in disagreement; and 17.6 percent
is up for discussion. The training set has 40,350 headline-
article sets, the hold-out set has 9,622, and the claim set has
25,413 sets.

B. CORPUS DESIGN
The dataset FCN-1 has four distinct classes (agree,
disagree, discuss, unrelated). In pre-processing, labels are
encoded into numeric target values and perform some pre-
processing steps. Preprocessed data is split into 75% data
for training and 25% for testing.
This study used the FNC-1 dataset, consisting of two
CSV files, including stances and body corpora of text news
29462 VOLUME 11, 2023
 A. Altheneyan, A. Alhadlaq: Big Data ML-Based Fake News Detection Using Distributed Learning

multiple sources is difficult due to a lack of linguistic resources.

Furthermore, annotating these news pieces based on their contents
necessitates specialist expertise, a signif- icant amount of time, and
substantial money. As a result, augmented corpus design is the
only way to conduct fake news detection research. Our augmented
corpus is created by combining 49972 stances with 1683 bodies
based on ids. The corpus has four distinct classes (agree, disagree,
discuss, unrelated). It contains 8909 discuss stances, 36545
unrelated stances, 3678 stances, and 840 disagree stances. After
gathering headlines and articles in one column, the final corpus
contains text and stances.

C. PRE-PROCESSING
Data mining relies heavily on pre-processing. It converts
inconsistent and incomplete raw data into a machine-readable
representation. Various text preprocessing activities were
conducted on the FNC-1 dataset. To complete these tasks, NLP
approaches such as character conversion to lowercase letters, stop
word elimination, stemming, and tokenization, as well as
algorithms from keras library were used. Stop words, which
comprise words like ‘‘the, of, there,’’ etc., are the most commonly
used words in our daily language and typically have relatively
limited significance in terms of the entire context of the phrase.
By removing the stop words, we save time and space that would
otherwise be consumed by the useless phrases mentioned before.
Words with comparable meanings may appear in the text many
times. For example, ‘‘eating’’ in any sentence will become ‘‘eats’’.
Reducing the language to its most basic form can help if that’s the
case. This operation, known as stemming [51], uses an open-source
version of the NLTK’s Porter stemmer method. Few preprocessing
steps are as follows:
1) Stop Word Removal: Languages commonly use a group of
terms collectively known as ‘‘stop words.’’ The words ‘‘a,’’
‘‘the,’’ ‘‘is,’’ and ‘‘are’’ are all examples of stop words in
English. Stop words are common in text mining and natural
language processing (NLP) to weed out overused words and
thus contain little useful information. NLTK provides the
stop word dictionary

VOLUME 11, 2023 29463

 A. Altheneyan, A. Alhadlaq: Big Data ML-Based Fake News Detection Using Distributed Learning

in this instance. To begin, the text is cleaned up by used to calculate the phrase frequency. When working
removing all stop words. It is possible to remove stop with large datasets,
words from the text because they are more common
and carry less useful information. Some common stop
words include the conjunctions ‘and’ ’or’ and ‘but’.
Pre-processing data is essential in natural language
processing because processing these less frequently
used full words consumes a significant amount of
time.
2) Punctuation Removal: The grammatical context of a
sentence is provided by natural language punctuation.
A comma, for example, may not add anything to the
understanding of the statement.
3) Link Removal: This step removes hypertext links
from social media posts. Regular expressions are used
to do this.
4) Lemmatization or stemming: Either lemmatization
or stemming is done during this step. The NLTK’s
WordNet Lemmatizer is used for lemmatization,
while the NLTK’s Snowball Stemmer
implementation is used for stemming, based on the
Porter2 stemming algorithm [52].
5) Apart from the above-mentioned pre-processing
stages, every social media post must go through.
Reply removal: Words beginning with @ (primarily
used for Twitter replies) are eliminated in this phase.
Regular expressions are also used to do this.
6) Lowercase transformation: Every word is
converted to lowercase in this phase to account for
variances in capitalization.

D. FEATURE EXTRACTION
Feature extraction transforms raw data into numerical
features that can be further processed while preserving the
original data set’s information. It is more effective than just
using raw data to train a machine.

1) HASHINGTF
The mapped indices are then used to calculate the phrase
frequency. Bypassing the need for a term-to-index map,
which can be time consuming and expensive for large cor-
pora, this method is less susceptible to hash collisions [45],
where multiple raw features are hashed into the same term.
HashingTF maps a series of phrases to their word
frequencies using the hashing method. Using Austin
Appleby’s Murmur Hash 3 algorithm, we can now
compute the term object’s
hash code value (MurmurHash3 × 86 32). Since the hash
function is translated to a column index using a simple
modulo, the features would not be evenly mapped to the
columns if the numb-Features input was less than a power
of two. The HashingTF transforms a set of terms into
feature vectors of fixed length. Regarding text processing, a
‘‘term set’’ could be a collection of words. HashingTF
employs the hashing technique. A hash function transforms
a raw attribute into an index (term). Murmur-Hash-3 is the
hash function in use here. The mapped indices are then
29464 VOLUME 11, 2023
 A. Altheneyan, A. Alhadlaq: Big Data ML-Based Fake News Detection Using Distributed Learning

avoiding creating a global term-to-index map is preferable

because doing so can be time-consuming and expensive.
However, this method is vulnerable to hash collisions, which
occur when different raw features are hashed into the same
term. Increasing the number of buckets in the hash table to
reduce the likelihood of collisions is recommended. A simple
modulo determines the vector index on the hashed value, so
the feature size should be a power of two. If the feature size is
smaller than this, the vector indices will not be evenly
distributed. There is a binary toggle parameter that controls the
frequency of terms. When this value is true, all nonzero
frequency counts are reset to 1. As a result, discrete probability
models are built that do not use integer counts but rather binary
ones.

2) IDF
Inverse Document Frequency (IDF) is a calculation fre-
quently employed in association with term frequency. The
issue with term frequency is that frequent terms are not
necessarily the most significant. For example, ‘‘content’’ will
appear on every web page. IDF is a method for lowering the
weight of frequently occurring words in a corpus (collection of
documents). IDF is determined by dividing the total number of
documents by the number of documents containing the phrase
in the collection. IDF is an Estimator that generates an IDF
Model after being fitted to a dataset. Feature vectors (typically
created by Hashing-TF or count- vectorizer) are used to scale
each IDF model feature [46]. It appears to downplay qualities
that are common in a corpus.

E. CLASSIFICATION MODELS AND PARAMETERS

SETTINGS
We use the following machine learning techniques to detect
irregularities and breakdown of unusual events and investigate
the effectiveness of our advanced method:
Random Forest (RF): a supervised learning technique that
may be used for classification, retrieval, and other tasks. It
generates a few trees to aid in decision-making. It takes a
random sample of data, constructs many decision trees
to forecast each tree, and then votes on the best option. n-
estimators = 200, bootstrap = True, criterion = Gini,
min-samples-split = 2, random-state = 0, and min-
samples-leaf = 1 are the parameters for our RF method.
Logistic Regression (LR): It is a segregated targeted
learning model. A very straightforward ML algorithm
differentiates problems such as noise detection, diabetes
prediction, cancer detection, etc. LR is used to predict
probability of target variability [47]. In our application the
parameters of the LR algorithm are Penalty = l2, C = 1.0,
reduce rating = 1, solver = lbfgs, max iter = 100 and verbose
= 0.
Decision Tree (DT): are extensively used in decision
analysis and machine learning [21]. It’s a decision-making tool
that uses a tree-like graph of decisions and consequences, such
as random event outcomes, resource costs, and utility, to make
judgments. Internal nodes in a DT express a

VOLUME 11, 2023 29465

 A. Altheneyan, A. Alhadlaq: Big Data ML-Based Fake News Detection Using Distributed Learning

condition about an attribute. Each internal node divides classes suggest

into branches depending on the condition’s outcome until
it reaches a point where it no longer splits and leads
to leaf nodes, which indicate the class label that will be
applied [48].
Ensemble Classifier: In addition to the custom
classifiers, an ensemble technique was developed, which
combined the three custom classifiers. The objective is to
develop a voting classifier that calculates the weights to
apply to each classifier’s prediction [53]. The probabilities
computed by the classifiers are first stored in a matrix for
each training instance, resulting in each training case being
linked with a probability vector. The weights are calculated,
and the final label is created using this matrix of vectors,
which is then fed into a Meta classifier model (0, 1, 2, or 3).
In contrast to the ensemble model, a voting classifier was
also constructed to perform simple majority voting among
the models’ predictions. Ensemble categorization is
generally divided into two stages: base-level and ensemble-
level. This base predictors employ the HashingTF with IDF
received from news articles as input. The output predictions
from these base-predictors are fed into ensemble-level
models. The ensemble model’s main purpose is to improve
the overall prediction F1 score by overcoming the
shortcomings of the primary predictors. We have used
stacking ensemble models for ensemble classification [54].

F. EVALUATION METRICS
The main concern is determining the model’s ability to
discern true and false news. We used metrics to properly
examine the model’s efficiency for this difficult challenge.
Model selection and implementation are essential but
should not take precedence over the rest of the project.
Various assessment measures are used to test data to assess
the model’s capacity to detect false news. Multiple
evaluation metrics, such as classification reports (accuracy,
precision, recall, F1-score) and confusion measures, may be
used to assess machine learning models. The sections that
follow go through each of the assessment measures in
detail. Pre- processing and other ways of gathering fake
news data are loaded into a strong algorithm, producing
incredible results [49].
Observations that match the predictions made by the
model are true positives and negatives, respectively, and are
marked in green. Because we would want to cut down on
both types of errors, the ones we are trying to minimize are
marked below. These phrases don’t make a lot of sense. So,
we can check our understanding by dissecting each
statement.
A True Positive (TP) is a correctly anticipated positive
result when the actual and projected class values are yes.
For instance, if the expected and actual class values suggest
that the passenger made it, we know they did. When both
the actual and anticipated class values are negative, we say
the value is a True Negative (TN). For instance, this
passenger did not survive if both the actual and predicted
29466 VOLUME 11, 2023
 A. Altheneyan, A. Alhadlaq: Big Data ML-Based Fake News Detection Using Distributed Learning

that they did not. When the actual class size differs from the
projected class size, false positives and negatives occur.
When the expected class is present, but the real class is not,
this is called a false positive (FP). The actual class will be
utilized if, for example, it shows that the passenger did not
survive but the fore-cast class predicts that the passenger
would. In cases when the true class is yes but the predicted
class is no, a false negative has occurred. If, for example, the
actual class value reveals that the passenger lived whereas the
expected class value predicted that they would die, the actual
class value would be utilized.
To verify the usefulness of the model, the following
assessment criteria are used:
Precision is the proportion of actual test results that were
predicted correctly. This is calculated by dividing the number of
correct predictions by the number of incorrect ones.
TP + TN
Acc = TP + FN + TN + FN
Precision: To calculate a classifier’s precision, divide the
number of positive outcomes by the number of positive
predictions.
TP
Pr = TP
+ FP
Recall: The total number of positive outcomes divided by
the total number of predicted positive outcomes is used to
determine recall.
TP
Re = TP
+ FP
F1-score: It is a great way to test accuracy and recall
simultaneously. This value is used to gauge accuracy and
recall.
2 × (Precision × Recall)
F1= Precision + Recall
The accuracy of a prediction may be measured with the use
of a classification report (CR). Correct and incorrect
classifications for each category are utilized to determine the
totals. False positive (FP), true negative (FN), and false
positive and negative (FP/FN) are widely used in the
classification report’s construction (FP&N). Several metrics
may be used to evaluate a model’s efficacy, but accuracy is
often prioritized. For example, it incorporates a wide range of
assessment tools including as (accuracy, precision, recall, F1
score, and support.) The backing indicates the number of
occurrences for each class [50]. It represents how much
information out of the total possible may be calculated with
high precision. Number of courses where just the best features
were recalled. An equation may be used to depict this. To get
the F1-score, we add the percentage of correct predictions and
the number of correct recalls. The table summarizes the mean
weighted recall and accuracy for a certain sample. The F1-
score for this model is 1, which means it is ideal. ‘‘Support’’
refers to the number of class occurrences in a given dataset.
The word ‘‘accuracy’’ refers to the proportion of correct
predictions relative to the number of potential ones.

VOLUME 11, 2023 29467

 A. Altheneyan, A. Alhadlaq: Big Data ML-Based Fake News Detection Using Distributed Learning

TABLE 2. Proposed approach results.

IV. EXPERIMENTS AND RESULTS

precision, 91.24% recall, and 90.45% F1-score. As
A. CLASSIFICATION RESULTS
compared to LR with count vectorizer, the SVM obtained
The experimental results of Term Frequency-Inverse Docu- high results. We also employed LR and SVM models with
ment Frequency (TF-IDF) and HashingTF feature HashingTF-IDF features. The results of LR with
extraction techniques with ensemble models are presented HashingTF-IDF are better than the SVM model. Compared
in Table 2. The results using HashTF and IDF features to LR, the SVM model with HashingTF-IDF achieved
regarding accuracy, precision, recall, and F1-score are 90.75% accuracy.
93.45%, 92.03%, 92.45%, and 92.25%. The results from The LR model with HashingTF-IDF obtained 93.78%
LR_HashingTF-IDF is 93.45%, and it’s a highest as accuracy, which is higher than the SVM model’s accuracy.
compared to all other experimental. Furthermore, Bigram At the end we utilized Trigram, Unigram + Bigram +
Logistic Regression exhibits 88.45% accuracies, 87.02% Trigram, Unigram + Bigram + Trigram + 16000 limited
precision, 88.01% recall, and 87.06% F1-score. We also
top features and Unigram + Bigram + Trigram + Cv +
performed experiments using glove word embedding. We IDF + Chiseq feature with Logistic Regression to
used the glove embedding technique with logistic efficiently detect fake news. The LR with Trigram obtains
regression. However, the glove with logistic regression significant
model results is not so high but quite well with accuracy results: accuracy is 83.47%, precision is 82.01%, recall
scores of 73.25% and 63.12%, 73.25%, 62.45% as the is 83.45%, and F1-score is 82.64%. While compared to
precision, recall, and F1-score. To make a broader individual Trigram features, the LR model with Uni, Bi,
comparison, we include features of the count vectorizer and Trigram obtained better results with 88.64% accuracy.
technique. The features of the count vectorizer were passed However, when running tests with Uni, Bi, Trigram, and
to logistic regression to detect fake news. Using the count 16000 limited top features, the LR model obtained less
vectorizer technique, the logistic model achieved 88.45% accuracy, which is 83.78%. Ultimately, we tried to merge
accuracy, 82.12% precision, 88.45% recall, and 87.35% F1 all
score. Moreover, we merged the count vectorizer and TF- the features Unigram + Bigram + Trigram + Cv + IDF +
IDF features to obtain better results, but we failed to avail Chiseq, applied LR on these features, and obtained promising
improved results due to the high computational cost. The results with 83.45% accuracy and accuracy and 82.45%
correctness, precision, recall, and F1-score using count F1-score.
vectorizer and TF-IDF features with logistic regression are The Figure 5 (a) shows the classification report of
84.54%, 83.12%, 84.25%, and 83.26%. We also employed ensem- ble model. The support presents the number of
the Support Vector Machine (SVM) model to testify its instances of each class in testing set. 12,403 instances are
abilities using count vectorizer features, and the SVM used for testing data. We used weighted accuracy to
model gets improved results with 91.75% accuracy, 91.25% calculate the precision, recall and F1-score because it deals
29468 VOLUME 11, 2023
 A. Altheneyan, A. Alhadlaq: Big Data ML-Based Fake News Detection Using Distributed Learning

with the class imbalance problem. The mean average

precision, recall, F1-score of all classes is calculated using
macro average, while weighted

VOLUME 11, 2023 29469

 A. Altheneyan, A. Alhadlaq: Big Data ML-Based Fake News Detection Using Distributed Learning

TABLE 3. Comparative analysis of proposed and baseline approaches.

average is the total number of TP divided by the entire features and LR

number of objects in all classes. Macro average stands for
mean average. The weighted average score is higher due to
the class unbalancing in the dataset. We also construct the
ensemble model’s confusion matrix, as shown in Figure
5(b). A confusion matrix, also known as an error matrix, is
a table that visually depicts the performance of a
supervised classification machine learning system. Figure 5
(b) shows that the model made multiple incorrect
classifications. The ensemble model’s ultimate accuracy on
testing data is 93%.

B. PERFORMANCE COMPARISON OF DIFFERENT

APPROACHES
The comparative analysis of proposed approaches with
various baseline approaches is presented in Table 3. The
bold values manifest the highest achieved score of proposed
and baseline approaches. The experimental setting of
proposed approaches resembled the baseline. It is shown in
the table 3 that the proposed approach with TF-IDF
29470 VOLUME 11, 2023
 A. Altheneyan, A. Alhadlaq: Big Data ML-Based Fake News Detection Using Distributed Learning

model outperforms the baseline highest F1 score, which is

83.10%, while the proposed approach obtained the highest F1
score of 93.84%. In addition, dealing with the class- wise
score, the baseline approach of [46] exhibits the best score for
Agree class with 73.76%. The proposed approach with TF-IDF
features and LR model achieved the highest agree with class
score of 80.23%. The proposed approach outperforms the
baseline regarding the F1 score, with the highest F1 score of
92.45% and improved 9.35 %.

C. DISCUSSION
The FNC-1 dataset, which contains 49,972 headline articles
and four distinct categories, was used to achieve the inves-
tigation’s objectives, and obtain the desired results (discuss,
agree, unrelated, and disagree). The proposed system com-
prises numerous components, such as data pre-processing,
visualization, exploratory analysis, feature extraction, and
classification using machine learning strategies. We proposed
classifying data with an ensemble model influenced by

VOLUME 11, 2023 29471

 A. Altheneyan, A. Alhadlaq: Big Data ML-Based Fake News Detection Using Distributed Learning

deciding whether or not to employ PySpark. Compared to

the other approaches utilized during this inquiry and the
previous baseline studies, the suggested ensemble model
had the greatest F1 score. The proposed ensemble model
exhibits the highest F1 score compared to the existing
baseline studies and other approaches used in this study.
This model achieved the highest F1 score of 92.45% due to
the features of HashingTF- IDF that were added during
development. We boosted our F1 score by 9.35%, which is
a sufficient gain to prove the novelty of this research.
In the future, one of our long-term goals is to use Spark
to implement deep learning models in a multi-agent
distributed learning environment. These algorithms will be
used to detect instances of fake news. As a result, we can
assess the effectiveness of a wide range of machine learning
and deep learning algorithms on a diverse set of fabricated
news stories. Furthermore, we intend to create a featured
ensemble of different embedding techniques alongside
different machine learning and deep learning models
capable of accurately recognizing and categorizing various
hoaxes and fake news. This will be done so that we may
better understand how to spot false news, which will not
only aid in understanding the patterns of detecting hoax or
fake news but also in developing a cutting-edge real-time
fake news detection system.
consideration in
FIGURE 5. (a): Classification report of final ensemble model
(b): Confusion matrix of final ensemble model.

machine learning in real time during the experiment. As a

direct result, a more rapid interpretation of the findings is
now possible. Instead of just one, two, or three different
clas- sification methods, the proposed ensemble model
employs three distinct machine learning approaches
(Random Forest, Logistic Regression, and Decision Tree).
This ensemble model was created as part of our efforts to
improve our previous investigations into identifying and
categorizing fake news.
Several different factors are influencing the current situ-
ation. Several experiments are being carried out using the
Apache Spark framework to handle big data and perform
classification task. These experiments were carried out to
improve our ability to detect fake news. As a result of these
experiments, our ability to recognize hoaxes and other
forms of disinformation should be enhanced. The model’s
was one of the aspects considered during the evaluation
process for this particular piece of research. The model’s
accuracy was also considered part of the evaluation process,
in addition to its performance compared to five other
distinct criteria. Different evaluation metrics include
accuracy, precision, recall, the F1-score, and the confusion
matrix to test the model’s performance.
PySpark was chosen because it uses RDD, significantly
accelerating computation processing. As a result, the
compu- tations were finished significantly faster than they
otherwise would have been. This was the essential
29472 VOLUME 11, 2023
 A. Altheneyan, A. Alhadlaq: Big Data ML-Based Fake News Detection Using Distributed Learning
V. CONCLUSION
Headline stance checker has been indicated to be a helpful
method for exposing falsehood in the news, particularly when a
headline is contrasted to its content body. To demonstrate the
applicability of the headline stance checker, various tests were
conducted in the context of an existing assignment (Fake News
Challenge FNC-1). The stance of a headline had to be
categorized into one of the following classes: disagree, agree,
unrelated, and discuss. The studies included verifying each of
the suggested classification steps separately and the overall
method is evaluated by comparing the state-of-the- art in this
job. In this study, researchers used the dataset FNC-1, which
has categorized fake news into four categories, while using big
data technology (Spark) to perform machine learning analysis
for assessment and comparison with other state-of-the-art
approaches in fake news identification. The suggested
approach created a stacked ensemble model and experimented
with it on a distributed Spark cluster. We used N-grams,
HashingTF-IDF, and count vectorizer for feature extraction,
followed by the suggested stacked ensemble classification
model. Compared to the baseline techniques’ results, the
suggested model has a high classification performance of
92.45% in F1-score. The suggested model outperforms the
previous baseline techniques and improves the F1 score
significantly. The suggested ensemble model improves the F1
score by 9.35%.

A. RECOMMENDATIONS FOR FURTHER WORK

We currently work with a supervised approach, but researchers
can work with unsupervised fake news detection in the future.
This proposed work can also be extended

VOLUME 11, 2023 29473

 A. Altheneyan, A. Alhadlaq: Big Data ML-Based Fake News Detection Using Distributed Learning

using various neural network-based models, which are measure,’’ in Proc. 27th Int. Flairs Conf., May 2014.
more sufficient for unsupervised fake news detection. Spark
takes too much training time due to the standalone cluster.
Due to the solitary cluster, Spark takes twice as long to
train. In future, researchers can perform experiments on
creating a cluster on a different machine. This research
may be further stretched by employing various neural
network-based models better suitable for unsupervised fake
news identification. We will try to build a cluster on a
separate computer.

ACKNOWLEDGMENT
We would like to thank Researchers Supporting Project
number (RSPD2023R532) King Saud University, Riyadh,
Saudi Arabia.

REFERENCES
[1] P. H. A. Faustini and T. F. Covões, ‘‘Fake news detection in multiple
platforms and languages,’’ Expert Syst. Appl., vol. 158, Nov. 2020,
Art. no. 113503.
[2] M. D. Vicario, W. Quattrociocchi, A. Scala, and F. Zollo, ‘‘Polarization
and fake news: Early warning of potential misinformation targets,’’ ACM
Trans. Web, vol. 13, no. 2, pp. 1–22, May 2019.
[3] Y. Liu and Y.-F.-B. Wu, ‘‘FNED: A deep network for fake news early
detection on social media,’’ ACM Trans. Inf. Syst., vol. 38, no. 3, pp. 1–
33, Jul. 2020.
[4] J. C. S. Reis, A. Correia, F. Murai, A. Veloso, and F. Benevenuto,
‘‘Supervised learning for fake news detection,’’ IEEE Intell. Syst., vol.
34, no. 2, pp. 76–81, Mar. 2019.
[5] M. Z. Asghar, A. Habib, A. Habib, A. Khan, R. Ali, and A. Khattak,
‘‘Exploring deep neural networks for rumor detection,’’ J. Ambient Intell.
Hum. Comput., vol. 12, no. 4, pp. 4315–4333, Apr. 2021.
[6] R. K. Kaliyar, A. Goswami, and P. Narang, ‘‘DeepFakE: Improving fake
news detection using tensor decomposition-based deep neural network,’’
J. Supercomput., vol. 77, no. 2, pp. 1015–1037, Feb. 2021.
[7] S. S. Jadhav and S. D. Thepade, ‘‘Fake news identification and classifica-
tion using DSSM and improved recurrent neural network classifier,’’
Appl. Artif. Intell., vol. 33, no. 12, pp. 1058–1068, Oct. 2019.
[8] A. Vereshchaka, S. Cosimini, and W. Dong, ‘‘Analyzing and distinguishing
fake and real news to mitigate the problem of disinformation,’’ Comput.
Math. Org. Theory, vol. 26, no. 3, pp. 350–364, Sep. 2020.
[9] F. Monti, F. Frasca, D. Eynard, D. Mannion, and M. M. Bronstein, ‘‘Fake
news detection on social media using geometric deep learning,’’ 2019,
arXiv:1902.06673.
[10] M. H. Goldani, S. Momtazi, and R. Safabakhsh, ‘‘Detecting fake news
with capsule neural networks,’’ 2020, arXiv:2002.01030.
[11] S. Shellenbarger, ‘‘Most students don’t know when news is fake,
Stanford study finds,’’ Wall Street J., vol. 21, 2016.
[12] D. Pierson, ‘‘Facebook and Google pledged to stop fake news. So why
did they promote Las Vegas-shooting hoaxes?’’ Los Angeles Times, Oct.
2017.
[13] G. Zarrella and A. Marsh, ‘‘MITRE at SemEval-2016 task 6: Transfer
learning for stance detection,’’ 2016, arXiv:1606.03784.
[14] S. Ghosh, P. Singhania, S. Singh, K. Rudra, and S. Ghosh, ‘‘Stance
detection in web and social media: A comparative study,’’ in Proc. Int.
Conf. Cross-Lang. Eval. Forum Eur. Lang. Cham, Switzerland: Springer,
2019, pp. 75–87.
[15] A. I. Al-Ghadir, A. M. Azmi, and A. Hussain, ‘‘A novel approach to
stance detection in social media tweets by fusing ranked lists and
sentiments,’’ Inf. Fusion, vol. 67, pp. 29–40, Mar. 2021.
[16] S. Somasundaran and J. Wiebe, ‘‘Recognizing stances in ideological on-
line debates,’’ in Proc. NAACL HLT Workshop Comput. Approaches
Anal. Gener. Emotion Text, 2010, pp. 116–124.
[17] A. Konjengbam, S. Ghosh, N. Kumar, and M. Singh, ‘‘Debate stance
classification using word embeddings,’’ in Proc. Int. Conf. Big Data
Anal. Knowl. Discovery. Cham, Switzerland: Springer, 2018, pp. 382–
395.
[18] A. Faulkner, ‘‘Automated classification of stance in student essays: An
approach using stance target information and the Wikipedia link-based
29474 VOLUME 11, 2023
 A. Altheneyan, A. Alhadlaq: Big Data ML-Based Fake News Detection Using Distributed Learning
[19] J. Weedon, W. Nuland, and A. Stamos, Information Operations and
Facebook. Menlo Park, CA, USA: Facebook, 2017.
[20] A. Vlachos and S. Riedel, ‘‘Identification and verification of simple claims
about statistical properties,’’ in Proc. Conf. Empirical Methods Natural Lang.
Process., 2015, pp. 2596–2601.
[21] S. N. Shorabeh, N. N. Samany, F. Minaei, H. K. Firozjaei, M. Homaee, and
A. D. Boloorani, ‘‘A decision model based on decision tree and particle
swarm optimization algorithms to identify optimal locations for solar power
plants construction in Iran,’’ Renew. Energy, vol. 187, pp. 56–67, 2022.
[22] E. Zotova, R. Agerri, and G. Rigau, ‘‘Semi-automatic generation of
multilingual datasets for stance detection in Twitter,’’ Expert Syst. Appl., vol.
170, May 2021, Art. no. 114547.
[23] S. Mishra, P. Shukla, and R. Agarwal, ‘‘Analyzing machine learning enabled
fake news detection techniques for diversified datasets,’’ Wireless Commun.
Mobile Comput., vol. 2022, pp. 1–18, Mar. 2022.
[24] A. Spark, ‘‘Apache spark,’’ Retrieved January, vol. 17, no. 1, p. 2018, 2018.
[25] A. Sen, M. Sinha, S. Mannarswamy, and S. Roy, ‘‘Stance classification of
multi-perspective consumer health information,’’ in Proc. ACM India Joint
Int. Conf. Data Sci. Manage. Data, Jan. 2018, pp. 273–281.
[26] S. V. Vychegzhanin and E. V. Kotelnikov, ‘‘Stance detection based on
ensembles of classifiers,’’ Program. Comput. Softw., vol. 45, no. 5,
pp. 228–240, Sep. 2019.
[27] C. Silverman, ‘‘Lies, damn lies and viral content,’’ Tow Center Digit.
Journalism, Columbia Univ., New York, NY, USA, 2015.
[28] S. Harabagiu, A. Hickl, and F. Lacatusu, ‘‘Negation, contrast and
contradiction in text processing,’’ in Proc. AAAI, vol. 6, 2006, pp. 755–762.
[29] S. Mohammad, S. Kiritchenko, P. Sobhani, X. Zhu, and C. Cherry,
‘‘SemEval-2016 task 6: Detecting stance in tweets,’’ in Proc. 10th Int.
Workshop Semantic Eval. (SemEval). San Diego, CA, USA: Association for
Computational Linguistics, 2016, pp. 31–41.
[30] B. G. Patra, D. Das, and S. Bandyopadhyay, ‘‘JU_NLP at SemEval-2016 task
6: Detecting stance in tweets using support vector machines,’’ in Proc. 10th
Int. Workshop Semantic Eval. (SemEval), 2016, pp. 440–444.
[31] H. Elfardy and M. Diab, ‘‘CU-GWU perspective at SemEval-2016 task 6:
Ideological stance detection in informal text,’’ in Proc. 10th Int. Workshop
Semantic Eval. (SemEval), 2016, pp. 434–439.
[32] I. Augenstein, T. Rocktäschel, A. Vlachos, and K. Bontcheva, ‘‘Stance
detection with bidirectional conditional encoding,’’ 2016, arXiv:1606.05464.
[33] P. Wei, W. Mao, and D. Zeng, ‘‘A target-guided neural memory model for
stance detection in Twitter,’’ in Proc. Int. Joint Conf. Neural Netw. (IJCNN),
Jul. 2018, pp. 1–8.
[34] S. Zhou, J. Lin, L. Tan, and X. Liu, ‘‘Condensed convolution neural network
by attention over self-attention for stance detection in Twitter,’’ in Proc. Int.
Joint Conf. Neural Netw. (IJCNN), Jul. 2019, pp. 1–8.
[35] M. Taulé, M. A. Martí, F. M. Rangel, P. Rosso, C. Bosco, and V. Patti,
‘‘Overview of the task on stance and gender detection in tweets on Catalan
independence at IberEval 2017,’’ in Proc. 2nd Workshop Eval. Hum. Lang.
Technol. Iberian Lang. (CEUR-WS), vol. 1881, 2017, pp. 157–177.
[36] M. Lai, A. T. Cignarella, D. I. Hernández Farías, C. Bosco, V. Patti, and
P. Rosso, ‘‘Multilingual stance detection in social media political debates,’’
Comput. Speech Lang., vol. 63, Sep. 2020, Art. no. 101075.
[37] S. Sommariva, C. Vamos, A. Mantzarlis, L. U.-L. Dào, and D. M. Tyson,
‘‘Spreading the (fake) news: Exploring health messages on social media and
the implications for health professionals using a case study,’’ Amer. J. Health
Educ., vol. 49, no. 4, pp. 246–255, Jul. 2018.
[38] B. Riedel, I. Augenstein, G. P. Spithourakis, and S. Riedel, ‘‘A simple but
tough-to-beat baseline for the Fake News Challenge stance detection task,’’
pp. 1–6, May 2018, arXiv:1707.03264.
[39] Q. Zhang, S. Liang, A. Lipani, Z. Ren, and E. Yilmaz, ‘‘From stances’
imbalance to their hierarchical representation and detection,’’ in Proc. World
Wide Web Conf., May 2019, pp. 2323–2332.
[40] C. Dulhanty, J. L. Deglint, I. B. Daya, and A. Wong, ‘‘Taking a stance on
fake news: Towards automatic disinformation assessment via deep
bidirectional transformer language models for stance detection,’’ 2019,
arXiv:1911.11951.
[41] B. Pouliquen, R. Steinberger, and C. Best, ‘‘Automatic detection of
quotations in multilingual news,’’ in Proc. Recent Adv. Natural Lang.
Process., 2007, pp. 487–492.
[42] M.-C. De Marneffe, A. N. Rafferty, and C. D. Manning, ‘‘Finding
contradictions in text,’’ in Proc. Assoc. Comput. Linguistics, 2008,
pp. 1039–1047.

VOLUME 11, 2023 29475

 A. Altheneyan, A. Alhadlaq: Big Data ML-Based Fake News Detection Using Distributed Learning

[43] A. Suprem and C. Pu, ‘‘MiDAS: Multi-integrated domain adaptive

[55] R. Agrawal, S. Rajagopalan, R. Srikant, and Y. Xu, ‘‘Mining newsgroups
supervision for fake news detection,’’ 2022, arXiv:2205.09817.
using networks arising from social behavior,’’ in Proc. 12th Int. Conf.
[44] O. Levy, T. Zesch, I. Dagan, and I. Gurevych, ‘‘Recognizing partial
World Wide Web, 2003, pp. 529–535.
textual entailment,’’ in Proc. 51st Annu. Meeting Assoc. Comput.
[56] A. Murakami and R. Raymond, ‘‘Support or oppose? Classifying
Linguistics, vol. 2, 2013, pp. 451–455.
positions in online debates from reply activities and opinion
[45] C. Cai and D. Lin, ‘‘Find another me across the world - large-scale
expressions,’’ in Proc. 23rd Int. Conf. Comput. Linguistics, 2010, pp.
semantic trajectory analysis using spark,’’ 2022, arXiv:2204.00878.
869–875.
[46] M. D. N. Darji, S. M. Parikh, and H. R. Patel, ‘‘Sentiment analysis
[57] G. Gorrell, E. Kochkina, M. Liakata, A. Aker, A. Zubiaga, K. Bontcheva,
of unstructured data using spark for predicting stock market price
and L. Derczynski, ‘‘SemEval-2019 task 7: RumourEval, determining
movement,’’ in Inventive Computation and Information Technologies.
rumour veracity and support for rumours,’’ in Proc. 13th Int. Workshop
Singapore: Springer, 2022, pp. 521–530.
Semantic Eval., 2019, pp. 845–854.
[47] A. A. H. Ahmadini, ‘‘A novel technique for parameter estimation in
intuitionistic fuzzy logistic regression model,’’ Ain Shams Eng. J., vol.
13, no. 1, Jan. 2022, Art. no. 101518.
[48] S. Choe, A. Ha, J. W. Jeoung, K. H. Park, and Y. K. Kim, ‘‘Macular
sector-wise decision tree model for the prediction of parafoveal scotoma
not detected by 24–2 visual field test,’’ Clin. Exp. Ophthalmol., vol. 50, ALAA ALTHENEYAN received the B.Ed. degree in computer and
no. 5, pp. 510–521, Jul. 2022. education and the M.S. and Ph.D. degrees in computer science from King
[49] S. Visa, B. Ramsay, A. L. Ralescu, and E. Van Der Knaap, ‘‘Confusion Saud University, Riyadh, Saudi Arabia, in 2006, 2012, and 2020,
matrix-based feature selection,’’ MAICS vol. 710, no. 1, pp. 120–127, respectively. From 2011 to 2021, she was a Lecturer with King Saud
2011. University, where she has been an Assistant Professor with the Computer
[50] A. Basarkar, ‘‘Document classification using machine learning,’’ San and Engineering Department, since 2021. Her research interests include
José State Univ., San Jose, CA, USA, 2017. natural language processing and machine learning.
[51] E. Loper and S. Bird, ‘‘NLTK: The natural language toolkit,’’ 2002,
arXiv:cs/0205028.
[52] C. Li, A. Porco, and D. Goldwasser, ‘‘Structured representation learning
for online debate stance prediction,’’ in Proc. 27th Int. Conf. Comput.
Linguistics, 2018, pp. 3728–3739. ASEEL ALHADLAQ received the B.S. and M.S. degrees in computer science
[53] R. Sandrilla and M. S. Devi, ‘‘FNU-BiCNN: Fake news and fake URL from King Saud University, Riyadh, Saudi Arabia, in 2006 and 2013,
detection using bi-CNN,’’ Int. J. Adv. Comput. Sci. Appl., vol. 13, no. 2, respectively, and the Ph.D. degree in computing from Newcastle
p. 477, 2022. University, Newcastle upon Tyne, U.K., in 2021.
[54] A. Abbasi, A. R. Javed, C. Chakraborty, J. Nebhen, W. Zehra, and From 2011 to 2021, she was a Lecturer with King Saud University,
Z. Jalil, ‘‘ElStream: An ensemble learning approach for concept drift
where she has been an Assistant Professor with the Computer and
detection in dynamic social big data stream learning,’’ IEEE Access, vol.
Engineering Department, since 2021. Her research interests include
9,
pp. 66408–66419, 2021. human–computer interaction, social media, and designs.

29476 VOLUME 11, 2023