CFP last date
22 April 2024
Reseach Article

An Evaluation of Sentiment Analysis and Classification Algorithms for Arabic Textual Data

by Ayman Mohamed Mostafa
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 158 - Number 3
Year of Publication: 2017
Authors: Ayman Mohamed Mostafa
10.5120/ijca2017912770

Ayman Mohamed Mostafa . An Evaluation of Sentiment Analysis and Classification Algorithms for Arabic Textual Data. International Journal of Computer Applications. 158, 3 ( Jan 2017), 29-36. DOI=10.5120/ijca2017912770

@article{ 10.5120/ijca2017912770,
author = { Ayman Mohamed Mostafa },
title = { An Evaluation of Sentiment Analysis and Classification Algorithms for Arabic Textual Data },
journal = { International Journal of Computer Applications },
issue_date = { Jan 2017 },
volume = { 158 },
number = { 3 },
month = { Jan },
year = { 2017 },
issn = { 0975-8887 },
pages = { 29-36 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume158/number3/26890-2017912770/ },
doi = { 10.5120/ijca2017912770 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-07T00:03:51.976934+05:30
%A Ayman Mohamed Mostafa
%T An Evaluation of Sentiment Analysis and Classification Algorithms for Arabic Textual Data
%J International Journal of Computer Applications
%@ 0975-8887
%V 158
%N 3
%P 29-36
%D 2017
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Sentiment analysis is a recent advance in text mining applications for analyzing textual data according to orientation of human comments to determine whether they are positive, negative, or neutral. Different data mining techniques and algorithms such as support vector machine, naïve Bayes, decision tree, k-nearest neighbor and other techniques are used for analyzing textual data. These techniques are evaluated based on Arabic language due to its richness and diversity that can lead to difficulties in analyzing and mining large number of morphological and linguistic words that can lead to different meaning. This research provides sophisticated categorization of most or all recent articles according to the algorithms used in analyzing sentiment data. A comparison table for the proposed algorithms is presented that explains each algorithm and its use in mining and analysis of Arabic textual data and provides different evaluation for each sentiment analysis and classification algorithm according to different categories such as sentiment type, feature selection, sentiment polarity, domain oriented , data scope and data source, algorithm used in the sentiment analysis or classification, and the best algorithm result during the analysis and mining process. The experimental results explain that support vector machine algorithm presents high accuracy with approximately 77% when compared to other text mining algorithms. Different algorithms of sentiment analysis and classifications are evaluated based on their use in Arabic language which has not been evaluated before.

References
  1. Mikalai, T., and Themis, P. “Survey on mining subjective data on the web,” International Journal of Data Mining and Knowledge Discovery, vol. 24, p. 478-514, 2012
  2. Wilson, T., Wiebe, J., and Hoffman, P. “Recognizing contextual polarity in phrase-level sentiment analysis,” ACM International Conference on Human Language Technology (HLT), p.347-354. 2005
  3. Hagenau, M., Liebmann, M., and Neumann, D. “Automated news reading: stock price prediction based on financial news using context-capturing features,” International Journal of Decision Support Systems, ELSEVIER, vol. 55, p.685-697, 2013
  4. Liang-Chih, Y., Jheng-Long, W., Pei-Chann, C., and Hsuan-Shou, C. “Using a contextual entropy model to expand emotion words and their intensity for the sentiment classification of stock market news,” International Journal of Knowledge-Based Systems, ELSEVIER, vol. 41, p. 89–97, 2013
  5. Isa, M., and Piek, V. “A lexicon model for deep sentiment analysis and opinion mining applications,” International Journal of Decision Support Systems, ELSEVIER, vol. 53, p. 680–688, 2012
  6. Medhat, W., Hassan, A., and Korashy, H. “Sentiment analysis algorithms and applications: A survey,” Ain Shams Engineering Journal, ELSEVIER, vol.5, p.1093-1113, 2014
  7. Abdul-Mageed, M., Diab, M., and Kubler, S. “SAMAR: Subjectivity and sentiment analysis for Arabic social media,” International Journal of Computer Speech and Language, ELSEVIER, vol.28, p.20-37, 2014
  8. Abdul-Mageed, M., Diab, M. and Korayem, M. “Subjectivity and sentiment analysis of modern standard arabic,” International Conference of Association for Computational Linguistics, p. 587-591, 2011
  9. Al-Kabi, M., Alsmadi, I., Gigieh, A., Wahsheh, H., and Haidar M., “Opinion Mining and Analysis for Arabic Language,” International Journal of Advanced Computer Science and Applications, vol. 5, pp. 181-195, 2014
  10. Duwairi, R., Marji, R., Shaban, N., and Rushaidat, S. “Sentiment analysis in arabic tweets,” IEEE International Conference on Information and Communication Systems (ICICS), p. 1-6, 2014
  11. Duwairi, R., and Qarqaz, I. “Arabic sentiment analysis using supervised classification,” IEEE International Conference on Future Internet of Things and Cloud, p. 579-583, 2014
  12. Abdulla, N., Majdalawi, R., Mohammed, S., Al-Ayyoub, M., and Al-KabI, M. “Automatic Lexicon Construction for Arabic Sentiment Analysis,” IEEE International Conference on Future Internet of Things and Cloud, p. 547-552, 2014
  13. Ahmed, S., Pasquier, M., and Qadah, G. “Key issues in conducting sentiment analysis on arabic social media Text,” IEEE International Conference on Innovations in Information Technology (IIT),p.72-77, 2013
  14. El-Beltagy, S., and Ali, A. “Open issues in the sentiment analysis of Arabic social media: A case study,” IEEE International Conference on on Innovations in Information Technology (IIT), p.215-220, 2013
  15. Ibrahim, M., and Salim, N. “Opinion analysis for twitter and Arabic tweets: A systematic literature review,” Journal of Theoretical and Applied Information Technology, vol. 56, p.338-348, 2013
  16. Abdulla, N., Ahmed, N., Shehab, M., and Al-Ayyoub, M. “Arabic sentiment analysis: lexicon-based and corpus-based,” IEEE International Conference on Applied Electrical Engineering and Computing Technologies (AEECT), p.1-6, 2013
  17. Khasawneh, R., Wahsheh, H., AL-Kabi, M., and Alsmadi, I. “Sentiment analysis of arabic social media content: A comparative study,” IEEE International Conference for Internet Technology and Secured Transactions (ICITST), p.101-106, 2013
  18. Al-Kabi, M., Abdulla, N., and Al-Ayyoub, M. “An analytical study of arabic sentiments: Maktoob case study,” IEEE International Conference for Internet Technology and Secured Transactions (ICITST), p.89-94, 2013
  19. Elarnaoty, M., AbdelRahman, S., and Fahmy, A. “A machine learning approach for opinion holder extraction In arabic language,” International Journal of Artificial Intelligence & Applications (IJAIA), vol.3, p.45-63, 2012
  20. Saleh, M., Valdivia, M., López, L., and Ortega, J. “Bilingual experiments with an arabic-english corpus for opinion mining,” International Conference on Recent Advances in Natural Language Processing, p.740-745, 2011
  21. Colbaugh, R. and Glass, K. “Agile sentiment analysis of social media content for security informatics applications,” IEEE International European Conference on Intelligence and Security Informatics, p.327-331, 2011
  22. Elhawary, M. and Elfeky, M. “Mining arabic business reviews,” IEEE International Conference on Data Mining Workshops, p.1108-1113, 2010
  23. Ahmed, K. and Almas, Y. “Visualizing sentiments in financial texts,” IEEE International Conference on Information Visualization, p.363-368, 2005
  24. Mahyoub, F., Siddiqui, M., and Dahab, M. “Building an arabic sentiment lexicon using semi-supervised learning,” Journal of King Saud University–Computer and Information Sciences, vol. 26, p. 417-424, 2014
  25. Al-Radaideh, Q., and Twaiq, L. “Rough set theory for arabic sentiment classification,” IEEE International Conference on Future Internet of Things and Cloud, p.559-564, 2014
  26. Akaichi, J. “Sentiment classification at the time of the Tunisian uprising,” IEEE International European Conference on Network Intelligence, pp.38-45, 2014
  27. Faqeeh, M., Abdulla, N., Al-Ayyoub, Y., and Quwaider, M. “Cross-lingual short-text document classification for Facebook comments,” IEEE International Conference on Future Internet of Things and Cloud, p.573-578, 2014
  28. Rafea, A., and Mostafa, N. “Topic extraction in social media,” IEEE International Conference on Collaboration Technologies and Systems, p.94-98, 2013
  29. Akaichi, J., Dhouioui, Z., and Pérez, M. “Text mining Facebook status updates for sentiment classification,” IEEE International Conference on System Theory, Control and Computing, p.640-645, 2013
  30. Omar, N., Albared, M., Al-Shabi, A., and Al-Moslmi, T. “Ensemble of classification algorithms for subjectivity and sentiment analysis of Arabic customers' reviews,” International Journal of Advancements in Computing Technology(IJACT), vol.5, p.77-85, 2013
  31. Hassan, T., Soliman, A., and Ali, M. “Mining social networks’ Arabic slang comments,” International European Conference on Data Mining (ECDM), 2013
  32. Shoukry, A., and Rafea, A. “Sentence-level Arabic sentiment analysis,” IEEE International Conference on Collaboration Technologies and Systems (CTS), p.546-550, 2012
  33. Farra, N., Challita, E., Abou Assi, R., and Hajj, H. “Sentence-level and document-level sentiment mining for Arabic texts”, IEEE International Conference on Data Mining Workshops (ICDMW), p. 1114-1119, 2010
  34. Mountassir, A., Benbrahim, H., and Berrada, I. “Some methods to address the problem of unbalanced sentiment classification in an Arabic context,” IEEE International Conference on Colloquium in Information Science and Technology (CIST), p.43-48, 2012
  35. El-Halees, A. “Opinion mining from Arabic comparative sentences,” International Arab Conference on Information Technology, p.265-271, 2012
  36. Itani, M., Hamandi, L., Zantout, R., and Elkabani, I. “Classifying sentiment in Arabic social networks: Naïve search versus Naïve bayes,” IEEE International Conference on Advances in Computational Tools for Engineering Applications (ACTEA), p.192-197, 2012
  37. Abdul-Mageed, M. and Diab, M. “AWATIF: A multi-genre corpus for modern standard Arabic subjectivity and sentiment analysis,” International Conference on Language Resources and Evaluation (LREC), p. 3907-3914, 2012
  38. Mountassir, A., Benbrahim, H. , and Berrada, I. “An empirical study to address the problem of unbalanced data sets in sentiment classification,” IEEE International Conference on Systems, Man, and Cybernetics, p.3298-3303, 2012
  39. El-Halees, A. “Arabic opinion mining using combined classification approach,” International Arab Conference on Information Technology, 2011
  40. Helmy, T. and Daud, A. “Intelligent agent for information extraction from Arabic text without machine translation,” International Workshop on Cross-Cultural and Cross-Lingual Aspects of the Semantic Web, 2010x
Index Terms

Computer Science
Information Sciences

Keywords

Sentiment Analysis Sentiment Classification Arabic Textual Data Text Mining Support Vector Machine