See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/340099721

A Survey of Semantic Analysis Approaches

Chapter in Advances in Intelligent Systems and Computing · March 2020

DOI: 10.1007/978-3-030-44289-7_6

CITATIONS READS

70 4,585

3 authors, including:

Said A. Salloum Khaled Shaalan

305 PUBLICATIONS 14,590 CITATIONS

British University in Dubai
426 PUBLICATIONS 14,688 CITATIONS
SEE PROFILE
SEE PROFILE

All content following this page was uploaded by Khaled Shaalan on 29 October 2023.

The user has requested enhancement of the downloaded file.

 A Survey of Semantic Analysis Approaches

Said A. Salloum1,2(&) , Rehan Khan1, and Khaled Shaalan1

1
Faculty of Engineering and IT, The British University in Dubai, Dubai, UAE
2
Research Institute of Sciences and Engineering, University of Sharjah,
Sharjah, UAE
[email protected]

Abstract. Semantics is a branch of linguistics, which aims to investigate the

meaning of language. Semantics deals with the meaning of sentences and words
as fundamentals in the world. Semantic analysis within the framework of natural
language processing evaluates and represents human language and analyzes
texts written in the English language and other natural languages with the
interpretation similar to those of human beings. This study aimed to critically
review semantic analysis and revealed that explicit semantic analysis, latent
semantic analysis, and sentiment analysis contribute to the leaning of natural
languages and texts, enable computers to process natural languages, and reveal
opinion attitudes in texts. The future prospect is in the domain of sentiment
lexes. The overall results of the study were that semantics is paramount in
processing natural languages and aid in machine learning. This study has cov-
ered various aspects including the Natural Language Processing (NLP), Latent
Semantic Analysis (LSA), Explicit Semantic Analysis (ESA), and Sentiment
Analysis (SA) in different sections of this study. However, LSA has been
covered in detail with specific inputs from various sources. This study also
highlights the future prospects of semantic analysis domain and finally the study
is concluded with the result section where areas of improvement are highlighted
and the recommendations are made for the future research. This study also
highlights the weakness and the limitations of the study in the discussion
(Sect. 4) and results (Sect. 5).

Keywords: Natural language processing
Sentiment analysis
Explicit

semantic analysis
Latent semantic analysis
Wikipedia linked based measures

1 Introduction

Documented data occurs in an ever-increasing number of researches, [1–4], and

business situations, and is encountered in different contexts by different scientists and
scholars [5–12]. [13] indicate that factoring rapid increase in data gathering, language
processing, and information retrieval attract investigators pursuing high system per-
formance [14–16] argue that researchers from a variety of disciplines have interests in
evaluating abstracts, titles, and publication full-text bodies to categorize attributes
including research topics, methods, and theories associated with the research nature.
According to [17], many multidisciplinary fields including biochemistry, engineering,
data mining, neuroscience, and bioinformatics [18] have emerged in the past numerous

© Springer Nature Switzerland AG 2020

A.-E. Hassanien et al. (Eds.): AICV 2020, AISC 1153, pp. 61–70, 2020.
https://doi.org/10.1007/978-3-030-44289-7_6
62 S. A. Salloum et al.

decades. Because multidisciplinary environments involve theories, techniques, and

methods from several areas, it is not easy to understand all the research processes in
these fields [17]. Hence, there should be a method of organizing documents and texts
into groups based on their pertinent structures. The method, which researchers and
scholars utilize to group texts based on the underlying structures is semantic analysis.
[19] state that semantic analysis accords the exact meaning and interpretation of the
dictionary meaning emanating from structures developed by syntactic assessment [20].
Semantics is a branch of linguistics, which aims to investigate the meaning of language
and language exhibits a meaningful message due to semantic interaction with diverse
linguistic categories, syntax, phonology, and lexicon [19]. In this regard, semantic
analysis is concerned with the meaning of words and sentences as elements in the
world. This assignment reviews critically – offers descriptive, analytical, and inter-
pretative evaluations of semantics. To accomplish this, the assignment factors semantic
classification for practical natural language processing [21], latent semantic analysis,
explicit semantic analysis, and sentiment analysis. The analyses contribute to the
facilitation of free communication and the understanding of the textual data, which can
be applied in information systems. The main challenges of Machine learning and
Artificial intelligence is learning from natural language and text. Any significant
advancement in this area has solid effect on numerous applications varying from speech
recognition, information and data retrieval, natural language processing and machine
interpretation.
It is important to emphasize that this study has also deliberately considered some
research papers published before 2006 because of some interesting findings by the
authors. Nonetheless, the latest research papers have been specifically focused. Liter-
ature Review.

2 Literature Review

2.1 Technical Part

2.1.1 Natural Language Processing
Semantic analysis interprets language structures through natural language analysis.
Natural language processing (NLP) is a theory-motivated scope of computational
techniques for the automatic evaluation of representation of human language [22]. [23]
indicate that the field of NLP is concerned with the building of computer software
systems that process and analyze texts written in the English language and other
languages with interpretation and generation capacities similar to those of human
beings. [24] adds that NLP is a field of research and application that examines how
computers can be utilized to comprehend and manipulate natural language speeches
and texts to accomplish useful endeavors. The aim of NLP researchers is to learn how
people understand and use language in order to develop effective tools and methods to
make computers understand and affect natural languages and to perform the required
tasks [24]. The extracted meanings can be utilized for various tasks including under-
taking robotic actions, production of equivalent translation in a dissimilar natural
language in the context of machine translation systems, and retrieving information from
 A Survey of Semantic Analysis Approaches 63

databases. Natural language processing system inventions are associated with the
semantic analysis of linguistic structures. For instance, [25] present a semantic dis-
course presentation structure (SemDRS), which is a model that interprets linguistic
structures outputs based on the natural language linguistic analysis framework.
SemDRS performs the transformation by contrasting the input linguistic construction to
an automatic program in such a way that SemDRS correctly capture the area-specific
interpretation of the linguistic expression [25]. For the undefined words in the natural
languages, [26] indicate that there is an invention that requires users to input synonyms
existing in the dictionary so that they can process natural languages and understand
their meanings. NLP is applicable in diverse fields of research including machine
translation, user interfaces, multi-language information retrieval, expert systems,
speech recognition, natural language text processing, and summarization, and artificial
intelligence.

2.1.2 Latent Semantic Analysis

The intelligence and machine learning face challenges such as difficulties learning from
the natural language and text, but latent semantic analysis can address the challenges
[27]. The fundamental issue is to understand the denotation and utilization of words in
an information driven manner, for e.g. from some given content without any prior
knowledge of linguistics.
[17] argue that latent semantic analysis (LSA) is a theoretical framework of
acquiring knowledge, induction, and representation. LSA is a systematic machine
learning methodology for evaluating the associations and similarities of structures
among terms and documents without depending on human experience, knowledge
bases, past theoretical models, and semantic dictionaries [17]. [16] indicate that LSA
was introduced in the late 1980s as an information retrieval approach developed to
better the indexing of library and search engine performances. Later, LSA became a
method and a theory for retrieving and representing word meaning including sorting
words and category judgments. [28] opine that LSA is utilized because of its unpar-
alleled capacity to reveal the conceptual content of the unstructured data based on
different mathematical dimension reduction approaches that approximate the linear
combinations of the interpretation of words and concepts. LSA utilizes the categorized
words and concepts to permit subsequent in-depth analyses. Latent semantic analysis is
important in the whole semantic analysis discourse. Latent Semantic Analysis (LSA) is
a natural language processing method, which extracts ideas and concepts from the
collection of terms to generate an arrangement of terminologies connected by the
underlying assumption that words similar in interpretation occur in the analogous
segments of the text [28]. LSA identified a model called “Probabilistic Latent Semantic
Analysis (PLSA)” where the variable has a sound computable foundation and identified
an applicable propagative model of the data [29]. Therefore, LSA addresses challenges
of learning from the natural language and text since its goal is to locate data mapping
that offers information beyond the level of lexical interpretation and reveals a semantic
association between the parties of interest [29]. Because of its generality, it is a suitable
and valuable analytical tool with a diverse range of applications in business and
information systems to analyze textual data. Some of the areas LSA can be applied
include quantitative literature reviews, evaluation of textual data in computer-mediated
64 S. A. Salloum et al.

communication, evaluation of client feedback interviews, and management of knowl-

edge repositories.
The statistical understanding of LSA leads to the emergence of probabilistic latent
semantic analysis (PLSA), which is a new model of LSA. The probabilistic variant of
LSA presents a formidable statistical foundation that explains a solid generative
framework of the data [29]. The goal of PLSA is to identify and distinguish between
contrasting contexts of word utilization without relying on a dictionary. Semantic
relatedness interventions seek to encourage computers to reason for written text. PLSA
has two applications such as permitting the disambiguation of polysems – words with
more than one meaning and projecting the topical similarities by aggregating together
words that form a common context [13, 29]. The research paper claimed substantial
performance could be obtained by using this technique. Latent semantic analysis can
complement unsupervised learning for a different range of applications in information
retrieval and text Learning. LSA and its new model, PLSA are critical in the evaluation
of text and natural language to comprehend the meaning and utilization of words in
different machine learning, artificial intelligence, and other applications.

2.1.3 Explicit Semantic Analysis

To process natural language, computers need access to domain-specific world
knowledge and a huge volume of common sense, which can be provided by explicit
semantic analysis. Unlike LSA that utilizes statistical co-occurrence information,
explicit semantic analysis utilizes knowledge humans gather and organize [30]. Explicit
semantic analysis assists text representation with huge amounts of world knowledge
such as those of Wikipedia to enable computers to process natural language and reason
about the semantic associations of natural language utterances [31]. Explicit semantic
analysis is critical in the computation of words and text relatedness and is applicable in
artificial intelligence and natural language processing.
The motivation behind semantic relatedness measures is to enable Wikipedia Link-
based Measure (WLM) approach have been developed to extract the semantic relat-
edness measures from Wikipedia. The main difference between the WLM and the
conventional method is that relatedness is defined by using hyperlink structures [31]. In
this technique, links between articles were used instead of textual content to provide
precise measures cost-effectively. This approach is similar to Explicit Semantic
Analysis (ESA) as it uses the online encyclopedia for this purpose. ESA is still con-
sidered as the best measures in terms of accuracy and effectiveness; the authors were
successful in matching the accuracy when the individual articles in Wikipedia is
defined as a term. Future work may include applying WLM to different tasks to explore
its effectiveness further.

2.1.4 Sentiment Analysis

It is not a new job for advertising researchers to derive the opinions and feelings of
customers from a pool of qualitative data. Conventionally, the coding of manual
content can perform such a task. Researchers thoroughly and comprehensively examine
the data and independently develop their own categories of sentiments. The growing
popularity of sentiment analysis can be due to its unique benefits: firstly, computer-
 A Survey of Semantic Analysis Approaches 65

aided feelings sentiment analysis is not only more effective than manual coding but also
yield comparable results.
Opinion and attitudes in a language are fundamental aspects of semantic analysis,
which sentiment analysis reveals [32]. Sentiment analysis encompasses a sequence of
methodologies, tools and techniques, related to the detection and extraction of indi-
vidual data including opinion and attitudes from languages [33]. The objective of
sentiment analysis is to identify in what way sentiments are presented in scripts and if
the expressions exhibit positive (favorable) and negative (unfavorable) views on a
subject [34]. The analysis identifies sentiments expressions, polarity, and power of the
expressions, and the association to the topic. The identified elements contribute to the
subjective comprehension of texts, which is critical in revealing the meaning of lan-
guage. Twitter is a social networking and microblogging site for users to post real-time
tweets [35–38]. Tweets are brief posts, just 140 characters long. Given the nature of
this micro-blogging platform, people use acronyms, make mistakes with spelling, use
hashtags, and other expressions that convey their particular meaning. [39] used the
twitter data in their research to analyze the sentiment analysis, POS features and kernel
tree usage. Twitter data was preprocessed by using an acronym dictionary and
emoticons. A glossary of emoticons was prepared by labeling 170 emoticons available
on Wikipedia. Different types of labels were assigned to emoticons, such as positive,
negative, neutral, etc. Unigram model was used as a baseline and reported an overall
increase of 4% for two activities: binary versus negative and neutral versus negative
versus positive.
In summation, the Sect. 2 of the assignment critically analyzed NLP in general and
narrowed down to latent semantic, explicit semantic, and sentiment analyses.
Whereas NLP analyzes texts written in the English language and other natural lan-
guages, LSA provides a framework for machine learning to learn from natural lan-
guages. The explicit semantic analysis presents domain-specific world knowledge for
computers to process natural language, while sentiment analysis investigates opinions
and attitudes in the text.

3 Future Prospects

Semantic analysis is primarily concerned with the meaning of language [32, 40].
Language shows a meaningful message since it involves semantic interactions with the
dissimilar language groupings such as lexicon and syntax [41]. The technical part
revealed a deeper technical content of the semantic analysis including aspects such as
latent semantic, explicit semantic, and sentiment semantic within the framework of
practical natural language processing. Because of this, future research within the area
would be sentiment expressions, which sentiment analysis as a technique of semantic
analysis identifies. Sentiment expressions motivate me because the meaning of words
and sentences should not only end at the understanding of the text but also at the
comprehension of how they contain emotionally loaded opinions. [34] provide a
framework for sentiment analysis and define sentiment expressions. In this regard, the
grammatical arrangement of words in a sentence is important since it encompasses the
elements in the world that constitute the meaning. However, the element of sentiment
66 S. A. Salloum et al.

expression must be clearly understood based on the interpretation of words such as

verbs, adjectives, nouns, prepositions, and adverbs. For instance, [34] argue that sen-
timent expressions utilizing adjectives such as good denotes noun modification with
positive polarity. For example, a good product is a sentiment expression, which shows
a positive attribute of a product. Similarly, an adverb such as beautifully in the case of
play beautiful modifies an adverb to project a positive sentiment expression [34].
Hence, sentiment expressions utilizing adverbs, nouns, and adjectives can be explained
based on positive and negative polarity argumentation. Critically, sentiment expression
presents the prospect for research undertaking within the semantic analysis because of
the applicability of the concept. In the field of computer science, opinion mining is
critical when testing the quality of products. Therefore, computer science students have
the opportunity to capitalize on large volumes of data and documents to develop
powerful functionalities for competitive advantage. A research area is a powerful tool
for analyzing and detecting the favorable and unfavorable attributes of innovations and
products for appropriate risk analysis and management. In this regard, the study aims to
achieve the fundamental association between sentiment expressions and practical
natural language processing, especially in the construction of systems that process texts
written in conventional languages, natural languages, their interpretation, and contri-
butions in assigning products and concepts the positive, negative, and neutral polarities.
The methodology applicable to future research is the critical review of the literature
about the topic area. The critical review method of literature offers an opportunity to
assess the strengths and weaknesses of the published literature on the research area,
analyze ideas and content, and relate them to other aspects of natural language pro-
cessing. Fundamentally, the critical review methodology provides the basis for
describing, analyzing, and interpreting the literature and extracts the presentation
associated with the topic area. In conclusion, the future prospect is sentiment expres-
sions. The motivation for the selection is to comprehend how words contain emo-
tionally loaded opinions. The future prospect is critical since it can be applied in
gathering data about product quality.

4 Discussion

Summarily, the report has been a critical review of over 12 published research papers
on semantic analysis [13, 22, 30, 42–50]. Some papers have been scanned quickly to
check the relevance of the topic and the interesting findings revealed by the authors.
The analysis unearthed that natural language processing focuses on the development of
computer software infrastructure that can evaluate texts composed in English and other
natural languages. The computer software should be able to interpret and generate
concepts similar to human beings. However, the ability of the NLP to extract the
meaning from the text depends on representing the meaning in a style suitable for
computer manipulation. Therefore, what I did in the report was to draw a connection
between the NLP, which is a theory-motivated scope of computational methods for
automatic evaluation and representation of human language with semantic analysis.
This study was able to present the ambit of semantic analysis is the meaning of words
and sentences, which NLP can rely on to explore how computers can be utilized to
 A Survey of Semantic Analysis Approaches 67

comprehend and manipulate natural speeches and texts for various applications such as
machine translation, artificial intelligence, user interfaces, and expert systems.
Fundamentally, this study was able to reveal how SemDRS is a model, which
performs semantic analysis based on the natural language linguistic analysis platform.
The model can process natural languages containing unidentified words and present
their meanings in a format that the computer can understand. Moreover, this study was
able to capture the meaning and application of latent semantic analysis and how its
statistical variance, PLSA generate model data to address challenges associated with
the inability of artificial intelligence and machine learning to acquire the meaning and
utilization of words in a data-controlled fashion. Finally, this study was able to explain
how explicit semantic analysis assists in semantic relatedness of natural language and
how sentiment analysis demonstrates favorable and unfavorable opinions for com-
petitive analysis. Reflectively, it was interesting to discover that semantic analysis is an
important aspect of natural language processing, which can be applied in computer
science, artificial intelligence, and other domains of learning. It was a significant dis-
covery because when the term semantic is introduced, the first conclusion is that it is
limited to the meaning of words and sentences. After reviewing the research papers, it
is concluded that the semantic analysis is a critical area in the field of machine learning
since there must be a mechanism for enabling machines to interpret natural languages
to domain-specific world knowledge. The interesting area, which this study did not
have time to cover, was syntactic-semantic analysis, especially word-class function
(WCF) as presented by [51]. Also, this research paper was published in the year 1997
and the paper was skimmed quickly. I think the word-oriented aspect of WCF would
have been an enriching area of focus, particularly on how words contribute funda-
mentally to language comprehension. In conclusion, a summary of the text reflects the
content in a simplified version. It reflects what the researcher did, and the personal
views concerning the research. This area is critical since it also reveals areas not
captured in the proposal and how they could have contributed to the overall enrichment
of the composition.

5 Conclusion

Based on the presentation in the technical part, it is evident that semantics is necessary
to process any natural language. [19] contend that in the absence of semantic analysis,
the results of machine learning may be ambiguous. In this regard, semantics is a field of
linguistics, which deals with the study and interpretation of the meaning and is critical
in natural language processing. To solve ambiguities and other challenges associated
with natural language processing, semantic classification is of great value. Hence, it is
important to collect knowledge on how people comprehend and utilize language to
develop appropriate methods and tools to make computers comprehend and manipulate
natural languages to undertake tasks such as machine translation. Moreover, it is clear
that sentiment analysis contributes to the building of accurate and reliable semantic
analysis of words and sentences and latent semantic analysis is applicable in the
management of knowledge repositories. Since probabilistic latent semantic analysis is
68 S. A. Salloum et al.

based on sound statistical application, it can be employed to enable machine learning to

handle the distinctions between the lexical and semantic level interpretations.
In summation, the critical review of sources related to semantic analysis revealed
the weakness of machine learning in processing natural languages. Positively, the
semantic analysis demonstrated that computer software with capacities such as those of
human beings can be developed to process texts composed in natural languages and
English and utilize them in machine translation. Hence, the proposal demonstrates the
capacity of semantic analysis in the whole framework of natural language processing
and the contribution in user interface investigations. Due to the time limitation, this
study could not focus vertically or deep dive into specific domain. However, this study
provides a robust foundation to proceed with the detailed research in coming months.

References
1. Alshurideh, M.T., Salloum, S.A., Al Kurdi, B., Monem, A.A., Shaalan, K.: Understanding
the quality determinants that influence the intention to use the mobile learning platforms: a
practical study. Int. J. Interact. Mob. Technol. 13(11), 157–183 (2019)
2. Salloum, S.A.S., Shaalan, K.: Investigating students’ acceptance of e-learning system in
higher educational environments in the UAE: applying the extended technology acceptance
model (TAM). The British University in Dubai (2018)
3. Salloum, S.A., Al-Emran, M., Shaalan, K., Tarhini, A.: Factors affecting the E-learning
acceptance: a case study from UAE. Educ. Inf. Technol. 24, 1–22 (2018)
4. Salloum, S.A., Alhamad, A.Q.M., Al-Emran, M., Monem, A.A., Shaalan, K.: Exploring
students’ acceptance of E-learning through the development of a comprehensive technology
acceptance model. IEEE Access 7, 128445–128462 (2019)
5. Mhamdi, C., Al-Emran, M., Salloum, S.A.: Text mining and analytics: a case study from
news channels posts on Facebook, vol. 740 (2018)
6. Salloum, S.A., AlHamad, A.Q., Al-Emran, M., Shaalan, K.: A survey of Arabic text mining,
vol. 740 (2018)
7. Salloum, S.A., Al-Emran, M., Abdallah, S., Shaalan, K.: Analyzing the Arab Gulf
newspapers using text mining techniques. In: International Conference on Advanced
Intelligent Systems and Informatics, pp. 396–405 (2017)
8. Salloum, S.A., Al-Emran, M., Shaalan, K.: Mining social media text: extracting knowledge
from Facebook. Int. J. Comput. Digit. Syst. 6(2), 73–81 (2017)
9. Salloum, S.A., Al-Emran, M., Monem, A.A., Shaalan, K.: Using text mining techniques for
extracting information from research articles. In: Studies in Computational Intelligence, vol.
740. Springer (2018)
10. Salloum, S.A., Mhamdi, C., Al-Emran, M., Shaalan, K.: Analysis and classification of
Arabic newspapers’ Facebook pages using text mining techniques. Int. J. Inf. Technol. Lang.
Stud. 1(2), 8–17 (2017)
11. Salloum, S.A., Al-Emran, M., Shaalan, K.: Mining text in news channels: a case study from
Facebook. Int. J. Inf. Technol. Lang. Stud. 1(1), 1–9 (2017)
12. Salloum, S.A., Al-Emran, M., Monem, A.A., Shaalan, K.: A survey of text mining in social
media: Facebook and Twitter perspectives. Adv. Sci. Technol. Eng. Syst. J 2(1), 127–133
(2017)
13. Chien, J.-T., Wu, M.-S.: Adaptive Bayesian latent semantic analysis. IEEE Trans. Audio.
Speech. Lang. Processing 16(1), 198–207 (2007)
 A Survey of Semantic Analysis Approaches 69

14. Chang, C.-H., Kayed, M., Girgis, M.R., Shaalan, K.F.: A survey of web information
extraction systems. IEEE Trans. Knowl. Data Eng. 18(10), 1411–1428 (2006)
15. Al-Emran, M., Mezhuyev, V., Kamaludin, A., Shaalan, K.: The impact of knowledge
management processes on information systems: a systematic review. Int. J. Inf. Manage. 43
(July), 173–187 (2018)
16. Evangelopoulos, N., Zhang, X., Prybutok, V.R.: Latent semantic analysis: five method-
ological recommendations. Eur. J. Inf. Syst. 21(1), 70–86 (2012)
17. Kou, G., Peng, Y.: An application of latent semantic analysis for text categorization. Int.
J. Comput. Commun. Control 10(3), 357–369 (2015)
18. Alhashmi, S.F.S., Salloum, S. A., Abdallah, S.: Critical success factors for implementing
artificial intelligence (AI) projects in dubai government United Arab Emirates (UAE) health
sector: applying the extended technology acceptance model (TAM). In: International
Conference on Advanced Intelligent Systems and Informatics, pp. 393–405(2019)
19. Rajani, S., Hanumanthappa, M.: Techniques of semantic analysis for natural language
processing – a detailed survey. Int. J. Adv. Res. Comput. Commun. Eng. 5(2) (2016)
20. Farghaly, A., Shaalan, K.: Arabic natural language processing: challenges and solutions.
ACM Trans. Asian Lang. Inf. Process. 8(4), 14 (2009)
21. Liu, X., He, P., Chen, W., Gao, J.: Multi-task deep neural networks for natural language
understanding. arXiv Prepr. arXiv1901.11504 (2019)
22. Cambria, E., White, B.: Jumping NLP curves: a review of natural language processing
research. IEEE Comput. Intell. Mag. 9(2), 48–57 (2014)
23. Mahesh, K., Nirenburg, S.: Semantic classification for practical natural language processing.
In: Proceedings of Sixth ASIS SIG/CR Classification Research Workshop: An Interdisci-
plinary Meeting, pp. 116–139 (1995)
24. Chowdhury, G.G.: Natural language processing. Annu. Rev. Inf. Sci. Technol. 37(1), 51–89
(2003)
25. Calcagno, M.V., Barklund, P.J., Zhao, L., Azzam, S., Knoll, S.S., Chang, S.: Semantic
analysis system for interpreting linguistic structures output by a natural language linguistic
analysis system. Google Patents, 13 February 2007
26. Katayama, Y., Nakanishi, K., Yoshiura, H., Hirasawa, K.: System for processing natural
language including identifying grammatical rule and semantic concept of an undefined word.
Google Patents, 28 April 1992
27. Khan, A., Baharudin, B., Lee, L.H., Khan, K.: A review of machine learning algorithms for
text-documents classification. J. Adv. Inf. Technol. 1(1), 4–20 (2010)
28. Hutchison, P.D., Daigle, R.J., George, B.: Application of latent semantic analysis in AIS
academic research. Int. J. Account. Inf. Syst. 31, 83–96 (2018)
29. Hofmann, T.: Unsupervised learning by probabilistic latent semantic analysis. Mach. Learn.
42(1–2), 177–196 (2001)
30. Gabrilovich, E., Markovitch, S.: Computing semantic relatedness using Wikipedia-based
explicit semantic analysis. In: IJcAI, vol. 7, pp. 1606–1611 (2007)
31. Witten, I.H., Milne, D.N.: An effective, low-cost measure of semantic relatedness obtained
from Wikipedia links (2008)
32. Akerkar, R.: Natural language processing. In: Artificial Intelligence for Business, pp. 53–62.
Springer (2019)
33. Mäntylä, M.V., Graziotin, D., Kuutila, M.: The evolution of sentiment analysis—a review of
research topics, venues, and top cited papers. Comput. Sci. Rev. 27, 16–32 (2018)
34. Nasukawa, T., Yi, J.: Sentiment analysis: capturing favorability using natural language
processing. In: Proceedings of the 2nd International Conference on Knowledge Capture,
pp. 70–77 (2003)
70 S. A. Salloum et al.

35. Abraham, A., Hassanien, A.-E., Snášel, V.: Computational Social Network Analysis:
Trends. Tools and Research Advances. Springer, Heidelberg (2009)
36. Ghali, N., Panda, M., Hassanien, A.E., Abraham, A., Snasel, V.: Social networks analysis:
tools, measures and visualization. In: Computational Social Networks, pp. 3–23. Springer
(2012)
37. Salloum, S.A., Mhamdi, C., Al Kurdi, B., Shaalan, K.: Factors affecting the adoption and
meaningful use of social media: a structural equation modeling approach. Int. J. Inf. Technol.
Lang. Stud. 2(3), 96–109 (2018)
38. Al-Maroof, R.S., Salloum, S.A., AlHamadand, A.Q.M., Shaalan, K.: A unified model for the
use and acceptance of stickers in social media messaging. In: International Conference on
Advanced Intelligent Systems and Informatics, pp. 370–381 (2019)
39. Agarwal, A., Xie, B., Vovsha, I., Rambow, O., Passonneau, R.: Sentiment analysis of
Twitter data. In: Proceedings of the Workshop on Language in Social Media (LSM 2011),
pp. 30–38 (2011)
40. Baets, W., Oldenboom, E., Hosken, C.: The potential of semantic analysis for business
(education). Available SSRN 3364133 (2019)
41. Salloum, S.A., Al-Emran, M., Shaalan, K.: A survey of lexical functional grammar in the
Arabic context. Int. J. Com. Net. Tech. 4(3), 141–147 (2016)
42. Godbole, N., Srinivasaiah, M., Skiena, S.: Large-scale Sentiment analysis for news and
blogs. Icwsm 7(21), 219–222 (2007)
43. Delmonte, R. Pallotta, V.: Opinion mining and sentiment analysis need text understanding.
In: Advances in Distributed Agent-Based Retrieval Tools, pp. 81–95. Springer (2011)
44. Al-Batah, M.S., Mrayyen, S., Alzaqebah, M.: Investigation of naive bayes combined with
multilayer perceptron for arabic sentiment analysis and opinion mining. JCS 14(8), 1104–
1114 (2018)
45. Chopra, F.K., Bhatia, R.: A critical review of sentiment analysis. Int. J. Comput. Appl. 149
(10), 37–40 (2016)
46. Pak, A., Paroubek, P.: Twitter as a corpus for sentiment analysis and opinion mining. In:
LREc, vol. 10, no. 2010, pp. 1320–1326 (2010)
47. Rahate, R.S., Emmanuel, M.: Feature selection for sentiment analysis by using svm. Int.
J. Comput. Appl. 84(5), 24–32 (2013)
48. Hofmann, T.: Probabilistic latent semantic analysis. In: Proceedings of the Fifteenth
Conference on Uncertainty in Artificial Intelligence, pp. 289–296 (1999)
49. Medagoda, N., Shanmuganathan, S., Whalley, J.: A comparative analysis of opinion mining
and sentiment classification in non-English languages. In: 2013 International Conference on
Advances in ICT for Emerging Regions (ICTer), pp. 144–148 (2013)
50. Mukherjee, S., Bhattacharyya, P.: Sentiment analysis in Twitter with lightweight discourse
analysis. In: Proceedings of COLING 2012, pp. 1847–1864 (2012)
51. Helbig, H., Hartrumpf, S.: Word class functions for syntactic-semantic analysis. In:
Proceedings of the 2nd International Conference on Recent Advances in Natural Language
Processing (RANLP 1997), pp. 312–317 (1997)

View publication stats