TABLE OF CONTENTS

Contents
1 INTRODUCTION 3
1.1 Introduction to Project Domain . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
1.2 Problem Definition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
1.3 Available Similar Systems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
1.4 Objectives of Proposed System . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
1.5 Proposed Methodology . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4
1.6 Applicability . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4

2 LITERATURE SURVEY 5

3 ANALYSIS 7
3.1 Hardware Requirements . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
3.2 Software Requirements . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
3.3 Functional Requirements . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8
3.4 Non-Functional Requirements . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8
3.5 Functional Modelling: Data Flow Diagram . . . . . . . . . . . . . . . . . . . . . . . . 8
3.5.1 Data Flow Diagram (DFD): Level 0 . . . . . . . . . . . . . . . . . . . . . . . 8
3.5.2 Data Flow Diagram (DFD): Level 1 . . . . . . . . . . . . . . . . . . . . . . . 9
3.5.3 Data Flow Diagram (DFD): Level 2 . . . . . . . . . . . . . . . . . . . . . . . 10

4 PLANNING 11
4.1 Software Process Model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11
4.2 Model Description . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11
4.2.1 Historical Data . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12
4.3 Team Structure . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12
4.4 Project Scheduling . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13

5 DESIGN 14
5.1 UML Modeling . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14
5.1.1 Use Case Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14
5.1.2 Activity Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
5.1.3 Class Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16
5.1.4 Component Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16

1
 5.1.5 Deployment Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18

6 Implementation Language: Python 19

6.1 Features . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19
6.2 Implementation Details . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19
6.3 Advantages of Using Python . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19
6.4 Comparison between Python and Java . . . . . . . . . . . . . . . . . . . . . . . . . . 19

REFERENCES 20

7 Conclusion 21
7.1 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21

REFERENCES 22

List of Figures
1 System Architecture . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4
2 Data Flow Diagram (DFD): Level 0 . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
3 Data Flow Diagram (DFD): Level 1 . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
4 Data Flow Diagram (DFD): Level 2 . . . . . . . . . . . . . . . . . . . . . . . . . . . 10
5 Software Process Model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11
6 Team Structure . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12
7 Project Scheduling . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13
8 Use Case Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14
9 Activity Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
10 Class Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16
11 Component Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
12 Deployment Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18

List of Tables
1 Hardware Requirements . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
2 Software Requirements . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
3 Comparison between Python and Java . . . . . . . . . . . . . . . . . . . . . . . . . . 20

2
 1. INTRODUCTION

1 INTRODUCTION
1.1 Introduction to Project Domain
Online Social Media portals play an influential role in information propagation which is considered
as an important source for producers in their advertising campaigns as well as for customers in
selecting products and services. In the past years, people rely a lot on the written reviews in their
decision-making processes, and positive/negative reviews encouraging/discouraging them in their se-
lection of products and services. In addition, written reviews also help service providers to enhance
the quality of their products and services. These reviews thus have become an important factor in
success of a business while positive reviews can bring benefits for a company, negative reviews can
potentially impact credibility and cause economic losses. The fact that anyone with any identity
can leave comments as review provides a tempting opportunity for fakemers to write fake reviews
designed to mislead users’ opinion. These misleading reviews are then multiplied by the sharing
function of social media and propagation over the web.

1.2 Problem Definition

• To develop and identify the fake and real content using reviews and performs four categories
of features including review-behavioral, user-behavioral, review-linguistic and user-linguistic
features for showing only trusted reviews to the user’s side.
• People believe on the written reviews in their decision-making processes, and positive/negative
reviews encouraging/discouraging them in their selection of products and services.
• Anyone can access application through registration and gives feedbacks as reviews for spam-
mers to guide other user’s opinion.

1.3 Available Similar Systems

• Online Social Media portals play an influential role in information propagation which is con-
sidered as an important source for producers in their advertising campaigns as well as for
customers in selecting products and services. In the past years, people rely a lot on the
written reviews in their decision-making processes, and positive/negative reviews encourag-
ing/discouraging them in their selection of products and services. In addition, written reviews
also help service providers to enhance the quality of their products and services. These reviews
thus have become an important factor in success of a business while positive reviews can bring
benefits for a company, negative reviews can potentially impact credibility and cause economic
losses. The fact that anyone with any identity can leave comments as review provides a tempt-
ing opportunity for spammers to write fake reviews designed to mislead users’ opinion. These
misleading reviews are then multiplied by the sharing function of social media and propagation
over the web.

1.4 Objectives of Proposed System

• To identify the fake user using positive and negative reviews in E-commerce platforms.
• To identify the fake user using content similarity of reviews in E-commerce platforms.
• To display only trusted reviews to the users.

3
1.5 Proposed Methodology

Figure 1: System Architecture

A new proposed framework consists in representing a set of reviews data provided as HIN (Heteroge-
neous Information Network) and solving the issue of fake detection in a problem of HIN classification.
In particular, to show their views dataset as a HIN where the reviews are linked through different
types of nodes (such as functionality and users). Then a weighting algorithm is used to calculate
the importance (or weight) of each function. These weights are used to calculate the latest review
labels using supervised and unsupervised procedures. Based on our observations, defining two views
for features (review-user and behavioral-linguistic), the classified features as review behavioral have
more weights and yield better performance on spotting fake reviews in both semi-supervised and
unsupervised approaches. The feature weights can be added or removed for labeling and hence time
complexity can be scaled for a specific level of accuracy. Categorizing features in four major cate-
gories (review-behavioral, user-behavioral, review-linguistic, user-linguistic), helps us to understand
how much each category of features is contributed to fake detection.

1.6 Applicability
• Social Media Application

• E commerce Application

4
 2. LITERATURE SURVEY

2 LITERATURE SURVEY
Detailed The pair wise features are first explicitly utilized to detect group colluders in online prod-
uct review fake campaigns, which can reveal collusions in fake campaigns from a more fine-grained
perspective.

In [1] paper, Fake campaigns spotted in popular product review websites (e.g., amazon. com) have
attracted mounting attention from both industry and academia, where a group of online posters are
hired to collaboratively craft deceptive reviews for some target products. The goal is to manipulate
perceived reputations of the targets for their best interests.

In [2] paper, Online product reviews have become an important source of user opinions. Due to
profit or fame, imposters have been writing deceptive or fake reviews to promote and/or to demote
some target products or services. Such imposters are called review spammers. In the past few years,
several approaches have been proposed to deal with the problem. In this work, take a different
approach, which exploits the burrstones nature of reviews to identify review spammers.

In [3] paper, Online reviews on products and services can be very useful for customers, but they need
to be protected from manipulation. So far, most studies have focused on analyzing online reviews
from a single hosting site. How could one leverage information from multiple review hosting sites?
This is the key question in our work. In response, develop a systematic methodology to merge,
compare, and evaluate reviews from multiple hosting sites. focus on hotel reviews and use more
than 15million reviews from more than 3.5 million users spanning three prominent travel sites.

In [4] paper, Users increasingly rely on crowd sourced information, such as reviews on Yelp and
Amazon, and liked post sand ads on Facebook. This has lento market for black hat promotion tech-
niques via fake (e.g., Sybil) and compromised accounts, and collusion networks. Existing approaches
to detect such behavior relies mostly on supervised (or semi-supervised) learning over known (or
hypothesized) attacks. They are unable to detect attacks missed by the operator while labeling, or
when the attacker changes strategy.

In [5] paper, Online reviews have become an increasingly important resource for decision making
and product designing. But reviews systems are often targeted by opinion fakeming. Although fake
review detection has been studied by researchers for years using supervised learning, ground truth
of large scale datasets is still unavailable and most of existing approaches of supervised learning are
based on pseudo fake reviews rather than real fake reviews. Working with Dianping1, the largest
Chinese review hosting site, present the first reported work on fake review detection in Chinese with
filtered reviews from Damping’s fake review detection system.

In [6] paper, Online reviews are quickly becoming one of the most important sources of information
for consumers on various products and services. With their increased importance, there exists an
increased opportunity for fakemers or unethical business owners to create false reviews in order to
artificially promote their goods and services or smear those of their competitors. In response to
this growing problem, there have been many studies on the most effective ways of detecting review
fake using various machine learning algorithms. One common thread in most of these studies is
the conversion of reviews to word vectors, which can potentially result in hundreds of thousands of
features.

5
In [7] paper, it providing an efficient and effective method to identify review fakemers by incor-
porating social relations based on two assumptions that people are more likely to consider reviews
from those connected with them as trustworthy, and review fakemers are less likely to maintain
a large relationship network with normal users. The contributions of this paper are two-fold: (1)
elaborate how social relationships can be incorporated into review rating prediction and propose a
trust based rating prediction model using proximity as trust weight; and (2) design a trust-aware
detection model based on rating variance which iteratively calculates user-specific overall trustwor-
thiness scores as the indicator for fake city.

In [8] paper, to detect fake reviews for a product by using the text and rating property from a
review. In short, the proposed system (ICF++) will measure the honesty value of a review, the
trustiness value of the reviewers and the reliability value of a product. The honesty value of a review
will be measured by utilizing the text mining and opinion mining techniques. The result from the
experiment shows that the proposed system has a better accuracy compared with the result from
iterative computation framework (ICF) method.

In [9] paper, Online Social Networks (OSNs), which captures the structure and dynamics of person-
to-person and person-to-technology interaction, is being used for various purposes such as business,
education, telemarketing, medical, entertainment. This technology also opens the door for unlawful
activities. Detecting anomalies, in this new perspective of social life that articulates and reflects
the off-line relationships, is an important factor as they could be a sign of a significant problem or
carrying useful information for the analyzer.

In [10] paper, they propose a new holistic approach called SpEagle that utilizes clues from all
metadata (text, timestamp, and rating) as well as relational data (network), and harness them col-
lectively under a unified system to spot suspicious users and reviews, as well as products targeted
by fake. SpEagle employs a review-network-based classification task which accepts prior knowledge
on the class distribution of the nodes, estimated from metadata. Positive points are: It enables
seamless integration of labeled data when available. It is extremely efficient.

6
 3. ANALYSIS

3 ANALYSIS
Analysis is concerned with understanding and modeling the application and domain within which it
operates. The initial input to the analysis phase is problem statement, which describes the problem
to be solved, and provides a conceptual view of the proposed system. Subsequent dialog with the
customer and real-world background knowledge are additional inputs to analysis. The output from
analysis is a formal model that captures the three essential aspects of the system: the objects and
their relationships, the dynamic flow of control, and the functional transformation of data subject
to constraints.

Requirement analysis bridges the gap between system engineering and software analysis design.
Software requirement analysis involves requirement collection, classification, structuring, prioritiz-
ing and validation. Requirement analysis consists of user requirements Analysis is concerned with
understanding and modeling the application and domain within which it operates. The initial input
to the analysis phase is problem statement, which describes the problem to be solved, and provides
a conceptual view of the proposed system.

3.1 Hardware Requirements

Hardware Type Minimum Requirement

Processor Intel i3 core
Speed 1.1 GHz
RAM 4 GB
Hard Disk 50 GB
Keyboard Standard Windows Keyboard
Monitor SVG

Table 1: Hardware Requirements

3.2 Software Requirements

Software Type Minimum Requirement

Operating System Windows
Front End Python
Back End SQLite
Design Tool RSA (Rational Software Architect), Edraw 6.1
Development Tool (IDE) Visual Studio Code
Testing Tool Manual
Documentation Tool Latex Overleaf

Table 2: Software Requirements

7
3.3 Functional Requirements
System Features:
Here we propose fake review detection using machine learning.
External Interface Requirements:
3.3.1 User Interface
Home page
Input Page
Processing Page
Result Page
3.3.2 Hardware Interfaces:
The entire software requires a completely equipped computer system including monitor, keyboard,
and other input output devices.
3.3.3 Software Interfaces :
The system can use Microsoft as the operating system platform. System also makes use of certain
GUI tools. To run this application we need python and above as windows platform and Apache
tomcat as server. To store data we need MySQL database.

3.4 Non-Functional Requirements

3.4.1 Accuracy :
Proposed Framework will give proper result to user if data available on database.
3.4.2 Failure handling :
System components may fail independently of others. Therefore, system components must be built
so they can handle failure of other components they depend on.
3.4.3 Openness :
It supports Online Data Streaming.
Security requirements
Private links can send on users mail id.
Software quality attributes
3.4.4 Usability :
The software will be embedded in a website. It should be scalable designed to be easily adopted by
a system. Any user can handle system user friendly.
3.4.5 Reliability :
The system should have accurate results and fast responses to user’s changing habits.

3.5 Functional Modelling: Data Flow Diagram

Data flow diagram (DFD), also called as Bubble chart is a hierarchical (or leveled) set of diagrams,
used to represent the flow of data elements into and out of the functional units of the program, data
stores, environmental sources and sinks.

The Data Flow Diagram (DFD) Serves Two Purposes:

1. To provide an indication of how data are transformed as they move through the system.
2. To depict the functions (and sub-functions) that transform the data flow.

3.5.1 Data Flow Diagram (DFD): Level 0

A level 0 DFD, also called a fundamental system model or a context model, represents the entire
software element as a single bubble with input and output data indicated by incoming and outgoing
arrows, respectively. Additional processes (bubbles) and information flow paths are represented as
the level 0 DFD is partitioned to reveal more detail. DFD Level 0 is also called a Context Diagram.
It’s a basic overview of the whole system or process being analyzed or modeled. It’s designed to

8
be an at-a-glance view, showing the system as a single high-level process, with its relationship to
external entities. It should be easily understood by a wide audience, including stakeholders, business
analysts, data analysts and developers.

Figure 2: Data Flow Diagram (DFD): Level 0

3.5.2 Data Flow Diagram (DFD): Level 1

A Data Flow Diagram (DFD) at Level 1 is a more detailed breakdown of the processes depicted in
the higher-level DFD0 (context-level diagram). DFD Level 1 provides a deeper understanding of
the system by expanding on the processes identified in the context-level diagram and showing their
sub- processes, inputs, outputs, and data stores.

Figure 3: Data Flow Diagram (DFD): Level 1

9
3.5.3 Data Flow Diagram (DFD): Level 2
Level provides an even more detailed view of the system by breaking down the sub-processes iden-
tified in the level 1 Data Flow Diagram (DFD) into further sub-processes. Each sub-process is
depicted as a separate process on the level 2 DFD. The data flows and data stores associated with
each sub-process are also shown.

Figure 4: Data Flow Diagram (DFD): Level 2

10
 4. PLANNING

4 PLANNING
4.1 Software Process Model
Every system developed is different and requires a suitable SDLC approach to be followed based on
internal and external factors. We choose waterfall model as software process model.

4.2 Model Description

The Waterfall Model is sequential design process, often used in Software development processes,
where progress is seen as flowing steadily download through the phase of Requirement gathering,
Analysis, System Design, Implementation(Coding), Testing, Deployment and Maintenance. This
Model is also called as the classic Life cycle model as it suggests a systematic sequential approach to
software developments. This one of the oldest model followed in software engineering. The process
begins with the requirement phase where the customer specifies the requirements and then progress
through other phases like requirement gathering, analysis, system design, implementation (coding),
testing, deployment and maintenance of the software.
There are 7 Phase of water fall model:

Figure 5: Software Process Model

• REQUIREMENTS
The first phase involves gathering requirements from stakeholders and analyzing them to un-
derstand the scope and objectives of the project.
• DESIGN
Once the requirements are understood, the design phase begins. This involves creating a

11
 detailed design document that outlines the software architecture, user interface, and system
components
• DESIGN
Once the requirements are understood, the design phase begins. This involves creating a
detailed design document that outlines the software architecture, user interface, and system
components
• IMPLEMENTATION
This phase include implementation involves coding the software based on the design specifica-
tions. This phase also includes unit testing to ensure that each component of the software is
working as expected.
• TESTING
In the testing phase, the software is tested as a whole to ensure that it meets the requirements
and is free from defects.
• DEPLOYMENT
Once the software has been tested and approved, it is deployed to the production environment.
A feedback is taken from the customer to ensure the quality of the product.
• MAINTENANCE
The final phase of the Waterfall Model is maintenance, which involves fixing any issues that
arise after the software has been deployed and ensuring that it continues to meet the require-
ments over time.

4.2.1 Historical Data

The model leverages historical product review data from well-known E-commerce platforms. This
dataset includes labeled reviews, both genuine and fake, to train and validate the model. Historical
data is critical for:

• Developing an automated system that can detect fake reviews from a set of genuine reviews
using machine learning techniques.
• Identifying fake reviews by analyzing sentiment, writing patterns, and reviewer behavior.
• Gathering product review data and applying preprocessing techniques like tokenization, stop-
word removal, and feature extraction to prepare data for machine learning models.
• Displaying only authentic reviews to enhance user trust and experience on E-commerce plat-
forms.

4.3 Team Structure

Figure 6: Team Structure

12
4.4 Project Scheduling

Figure 7: Project Scheduling

13
 5. DESIGN

5 DESIGN
Design uses a combination of text and diagrammatic forms to depict the requirements for data,
function and behavior in a way that is relatively easy to understand and more importantly, straight-
forward to review for correctness, completeness, and consistency.
A diagram is the graphical presentation of a set of elements most often rendered as a connected
graph of vertices (things) and arcs (relationship). These diagrams are drawn to visualize a system
from different perspectives so a diagram into a system.

5.1 UML Modeling

The unified modeling language (UML) is a Graphical Language for visualization, Specifying, con-
struction and documenting the artifacts of a software intensive system. The UML gives a standard
was to write system’s blueprints, covering conceptual thing, such as Business Processes and system
functions, as well as concrete things, such as classes written in a specific programming language,
database schemas, and reusable software components.

5.1.1 Use Case Diagram

A use case defines behavioral features of a system. Each use case is named using a verb phase
expresses a goal of the system. A use case diagram shows a set of use cases and actors and their
relationships. Use case diagrams address the static use case view of a system. These diagrams are
especially important in organizing and modeling the behaviors of a system. It shows the graphical
overview of functionality provided by the system intents actor.

Figure 8: Use Case Diagram

14
5.1.2 Activity Diagram
An activity diagram of a special kind of state chart diagram that shows the flow from activity
within a system. An activity addresses the dynamic view of a system. The activity diagram is often
seen as part of the functional view of a system because it describes logical processes, or functions.
Each process describes a sequence of tasks and the decisions that govern when and when they are
performed. The flow in an activity diagram is driven by the completion of an action.

Figure 9: Activity Diagram

15
5.1.3 Class Diagram
The class diagram is a static diagram. It represents the static view of an application. Class diagram
is not only used for visualizing, describing and documenting different aspects of a system but also for
constructing executable code of the software application. The class diagram describes the attributes
and operations of a class and also the constraints imposed on the system. The class diagrams are
widely used in the modeling of object-oriented systems because they are the only UML diagrams
which can be mapped directly with object-oriented languages. The class diagram shows a collection
of classes, interfaces, associations, collaborations and constraints. It is also known as a structural
diagram. The purpose of the class diagram is to model the static view of an application.

Figure 10: Class Diagram

5.1.4 Component Diagram

A component diagram shows the organization and dependencies among a set of components. Com-
ponent diagrams address the static implementation view of a system. Component diagrams are one
of the two kinds of diagrams found in modeling the physical aspects of object-oriented systems. A

16
component diagram shows the organization and dependencies among set of components. You can
use component diagrams to model the static implementation view of a system.

Figure 11: Component Diagram

17
5.1.5 Deployment Diagram
Deployment diagram shows the configuration of run time processing nodes and components that live
on them. Deployment diagram addresses the static deployment view of architecture. A deployment
diagram shows the configuration of run-time processing nodes and the components that live on
them. Deployment diagrams address the static view of architecture. They are related to components
diagram in that a node typically encloses one or more components.

Figure 12: Deployment Diagram

18
 6. IMPLEMENTATION

6 Implementation Language: Python

6.1 Features
• Easy coding: Python is very easy to code compared to other popular languages like Java and
C++. Anyone can learn basic Python syntax in a few hours, making it programmer-friendly.
• Easy to learn and use: Python is easy to learn and use. It is a developer-friendly and
high-level programming language.
• Object-oriented: Python supports both procedural and object-oriented programming, which
is one of the key features of the language. Unlike Java, it also supports multiple inheritance.
• Free and open-source: Python is freely available. We can download it from the official
Python website. Moreover, it is open-source, meaning its source code is open to the public for
download, modification, use, and distribution.

• Portable: Python is portable in the sense that the same code can be used on different
machines. For instance, a Python code written on a Mac can also run on Windows.

6.2 Implementation Details

The implementation process involves designing the system using Python, which includes the following
steps:
1. Setting up the development environment using tools such as Visual Studio Code.
2. Writing modular and reusable Python code to ensure maintainability.

3. Testing the system manually to validate its functionality and correctness.

4. Documenting the process using tools like Latex Overleaf to ensure comprehensive documenta-
tion.

6.3 Advantages of Using Python

• Python’s simplicity and readability make it suitable for rapid application development.
• The availability of numerous libraries and frameworks accelerates development.
• Python’s extensive community support ensures that developers can find solutions to common
problems quickly.

6.4 Comparison between Python and Java

19
Criteria Python Java
Compilation Interpreted language; code is Compiled language; JVM is used
scrutinized line by line. for execution.
Code Fewer lines of code. More lines of code.
Readability Less code required to read files. More code required to read files.
Speed Interpreted language; simpler Faster due to compiled nature.
syntax, slower due to runtime de-
termination.
Frameworks Fewer frameworks (e.g., Django, Many frameworks (e.g., Spring,
Flask). Blade, Hibernate).
Indentation Does not use braces; relies on Uses braces to define the
proper indentation. start/end of functions or classes.
Portability Requires an interpreter on the lo- Portable with any device capable
cal machine. of running a JVM.

Table 3: Comparison between Python and Java

20
 7. CONCLUSION FUTURE SCOPE

7 Conclusion
7.1 Conclusion
In this proposed system investigation presents a novel fake reviews detection system in particular
NetSpam framework for product reviews based on Sentiment analysis (SA) and latent semantic
analysis (LSA). This paper has used SA and LSA with netfake algorithm for fake reviews detection.
Our perceptions appear that computed weights by utilizing this metapath idea can be exceptionally
successful in distinguishing fake reviews and prompt a superior performance. Additionally, NetSpam
can end furthermore, it yields better execution in the highlights’ expansion process, and performs
superior to anything past works, with just a modest number of highlights. In addition, in the wake
of characterizing four primary classifications for highlights our perceptions demonstrate that the
reviews behavioral classification. LSA is used in the proposed system to reduce similar comments
and try to improve fake reviews detection accuracy. The outcomes about additionally affirm that
utilizing distinctive supervisions, comparative to the semi-supervised technique, have no observable
impact on deciding the vast majority of the weighted highlights, similarly as in various datasets.

21
 REFERENCES

References
[1] h. Xu and J. Zhang,” Combating product review fake campaigns
via multiple heterogeneous pairwise features”, In SIAM International
Conference on Data Mining, 2014.
[2] . Fei, A. Mukherjee, B. Liu, M. Hsu, M. Castellanos, and R. Ghosh,
“Exploiting bustiness in reviews for review fakemer detection”, In
ICWSM, 2013.
[3] . j. Minnich, N. Chavoshi, A. Mueen, S. Luan, and M. Faloutsos,
“True view: Harnessing the power of multiple review sites”,In ACM
WWW, 2015.
[4] . Viswanath, M. Ahmad Bashir, M. Crovella, S. Guah, K. P.
Gummadi, B. Krishnamurthy, and A. Mislove, “Towards detecting
anomalous user behavior in online social networks”, In USENIX,
2014.
[5] . Li, Z. Chen, B. Liu, X. Wei, and J. Shao,” Spotting fake reviews
via collective PU learning”, In ICDM, 2014.
[6] . Crawford, T. M. Khoshgoftaar, and J. D. Prusa,” Reducing Fea-
ture Set Explosion to Faciliate Real-World Review Sapm Detection”,
In Proceeding of 29th International Florida Artificial Intelligence Re-
search Society Conference, 2016.
[7] . Xue, F. Li, H. Seo, and R. Pluretti,” Trust-Aware Review Spam
Detection”,IEEETrustcom/ISPA.,2015.
[8] . D. Wahyuni , A. Djunaidy,” Fake Review Detection From a Prod-
uct Review Using Modified Method of Iterative Computation Frame-
work”, In Proceeding MATEC Web of Conferences, 2016.
[9] . Hassanzadeh,” Anomaly Detection in Online Social Networks: Us-
ing Datamining Techniques and Fuzzy Logic”, Queensland Univer-
sity of Technology, Nov, 2014.

22
[10] . Shebuti, L. Akoglu,” Collective opinion fake detection: bridging
review networks and metadata”, In ACM KDD, 2015.

23