SENTIMENT ANALYSIS AND CLASSIFICATION OF ARAB JORDANIAN FACEBOOK COMMENTS FOR JORDANIAN TELECOM COMPANIES USING LEXICON-BASED APPROACH AND MACHINE LEARNING

(Received: 7-Apr.-2020, Revised: 6-Jun.-2020 , Accepted: 8-Jun.-2020)

Authors Khalid M.O. Nahar, Amerah Jaradat, Mohammed Salem Atoum, Firas Ibrahim,

Keywords #Jordan Telecom #Sentiment analysis #Lexicon-based #Polarity #Facebook comments #Machine learning #NLP

Abstract Sentiment Analysis (SA) is a technique used for identifying the polarity (positive, negative) of a given text, using Natural Language Processing (NLP) techniques. Facebook is an example of a social media platform that is widely used among people living in Jordan to express their opinions regarding public and special focus areas. In this paper, we implemented the lexicon-based approach for identifying the polarity of the provided Facebook comments. The data samples are from local Jordanian people commenting on a public issue related to the services provided by the main telecommunication companies in Jordan (Zain, Orange and Umniah). The produced results regarding the evaluated Arabic sentiment lexicon were promising. By applying the user-defined lexicon based on the common Facebook posts and comments used by Jordanians, it scored (60%) positive and (40%) negative. The general lexicon accuracy was (98%). The lexicon was used to label a set of unlabeled Facebook comments to formulate a big dataset. Using supervised Machine Learning (ML) algorithms that are usually used in polarity classification, the researchers introduced them to our formulated dataset. The results of the classification were 97.8, 96.8 and 95.6% for Support Vector Machine (SVM), K-Nearest Neighbour (K-NN) and Naïve Bayes (NB) classifiers, respectively.

References

[1] M. D. Devika, C. Sunitha and A. Ganesh, "Sentiment Analysis: A Comparative Study on Different Approaches," Procedia Comput. Sci., vol. 87, no. June, pp. 44–49, 2016.

[2] B. Liu, Sentiment Analysis (Introduction and Survey) and Opinion Mining, [Online], Available: http://citeseerx.ist.psu.edu/viewdoc/download? doi=10.1.1.244.9480&rep=rep1&type=pdf, 2012.

[3] R. K. Bakshi, N. Kaur, R. Kaur and G. Kaur, "Opinion Mining and Sentiment Analysis," Proc. of the IEEE 3rd Int. Conf. Comput. Sustain. Glob. Dev. (INDIACom), vol. 2, no. 1, pp. 452–455, 2016.

[4] A. Chandra Pandey, D. Singh Rajpoot and M. Saraswat, "Twitter Sentiment Analysis Using Hybrid Cuckoo Search Method," Inf. Process. Manag., vol. 53, no. 4, pp. 764–779, 2017.

[5] R. M. Duwairi and I. Qarqaz, "Arabic Sentiment Analysis Using Supervised Classification," Proc. of the 1st International Workshop on Social Networks Analysis, Management and Security (SNAMS - 2014), pp. 579–583, Barcelona, Spain, August 2014.

[6] R. M. Duwairi, "Sentiment Analysis for Dialectical Arabic," Proc. of the 6th Int. Conf. Inf. Commun. Syst. (ICICS), DOI: 10.1109/IACS.2015.7103221, pp. 166–170, Amman, Jordan, 2015.

[7] A. Al Sallab, H. Hajj, G. Badaro, R. Baly, W. El Hajj and K. Bashir Shaban, "Deep Learning Models for Sentiment Analysis in Arabic," Proceedings of the Second Workshop on Arabic Natural Language Processing, DOI: 10.18653/v1/W15-3202, pp. 9–17, Beijing, China, 2015.

[8] H. K. Aldayel and A. M. Azmi, "Arabic Tweets Sentiment Analysis - A Hybrid Scheme," J. Inf. Sci., vol. 42, no. 6, pp. 782–797, 2015.

[9] H. Mulki, H. Haddad, M. Gridach and I. Babaoğlu, "Tw-StAR at SemEval-2017 Task 4: Sentiment Classification of Arabic Tweets," Proc. of the 11th International Workshop on Semantic Evaluations (SemEval-2017), DOI: 10.18653/v1/S17-2110, pp. 664–669, Vancouver, Canada, 2018.

[10] N. Al-Twairesh, H. Al-Khalifa, A. Al-Salman and Y. Al-Ohali, "AraSenTi-Tweet: A Corpus for Arabic Sentiment Analysis of Saudi Tweets," Procedia Comput. Sci., vol. 117, pp. 63–72, 2017.

[11] H. Najadat, A. Al-Abdi and Y. Sayaheen, "Model-based Sentiment Analysis of Customer Satisfaction for the Jordanian Telecommunication Companies," Proc. of the 9th International Conference on Information and Communication Systems (ICICS 2018), DOI: 10.1109/IACS.2018.8355429, 2018.

[12] L. Lulu and A. Elnagar, "Automatic Arabic Dialect Classification Using Deep Learning Models," Procedia Comput. Sci., vol. 142, pp. 262–269, 2018.

[13] A. Soumeur, M. Mokdadi, A. Guessoum and A. Daoud, "Sentiment Analysis of Users on Social Networks: Overcoming the Challenge of the Loose Usages of the Algerian Dialect," Procedia Computer Science, vol. 142, pp. 26-37, 2018.

[14] J. O. Atoum and M. Nouman, "Sentiment Analysis of Arabic Jordanian Dialect Tweets," Int. J. Adv. Comput. Sci. Appl., vol. 10, no. 2, pp. 256–262, 2019.

[15] M. Bouaziz and T. Ohtsuki, "Multi-class Sentiment Analysis in Twitter: What If Classification Is Not the Answer," IEEE Access, vol. 6, pp. 64486-64502, 2018.

[16] S. Kiritchenko, S. M. Mohammad and M. Salameh, "SemEval-2016 Task 7: Determining Sentiment Intensity of English and Arabic Phrases," Proc. of the 10th International Workshop on Semantic Evaluation (SemEval-2016), DOI: 10.18653/v1/S16-1004, San Diego, California, 2016.

[17] A. Al-Thubaity, Q. Alqahtani and A. Aljandal, "Sentiment Lexicon for Sentiment Analysis of Saudi Dialect Tweets," Procedia Computer Science, vol. 142, pp. 301-307, 2018.

[18] R. M. Duwairi and M. El-Orfali, "A Study of the Effects of Pre-processing Strategies on Sentiment Analysis for Arabic Text," Journal of Information Science, vol. 40, no. 4, pp. 501–513, 2014.

[19] M. Mataoui, O. Zelmati and M. Boumechache, "A Proposed Lexicon-based Sentiment Analysis Approach for the Vernacular Algerian Arabic," Res. Comput. Sci., vol. 110, pp. 55-70, 2016.

[20] S. L. Lo, E. Cambria, R. Chiong et al., "Multilingual Sentiment Analysis: From Formal to Informal and Scarce Resource Languages," Artif. Intell. Rev., vol. 48, pp. 499–527, 2017.

[21] O. Oueslati, A. I. S. Khalil and H. Ounelli, "Sentiment Analysis for Helpful Reviews Prediction," International Journal of Advanced Trends in Computer Science and Engineering, vol. 7, no. 3, pp. 34-40, DOI: 10.30534/ijatcse/2018/02732018, 2018.

[22] E. Cambria, "Affective Computing and Sentiment Analysis," IEEE Intelligent Systems, vol. 31, no. 2, pp. 102-107, DOI: 10.1109/MIS.2016.31, 2016.

[23] E. Cambria, S. Poria, D. Hazarika and K. Kwok, "SenticNet 5: Discovering Conceptual Primitives for Sentiment Analysis by Means of Context Embeddings," Proc. of the 32nd AAAI Conference on Artificial Intelligence (AAAI-18), pp. 1795–1802, New Orleans, Louisiana, USA, 2018.

[24] I. Al-Agha and O. Abu-Dahrooj, "Multi-level Analysis of Political Sentiments Using Twitter Data: A Case Study of the Palestinian-Israeli Conflict," Jordanian Journal of Computers and Information Technology (JJCIT), vol. 5, no. 3, December 2019.

[25] S. Kumar, V. Koolwal and K. K. Mohbey, "Sentiment Analysis of Electronic Product Tweets Using Big Data Framework," Jordanian Journal of Computers and Information Technology (JJCIT), vol. 5, no. 1, April 2019.

[26] A. Al-Shaikh, R. Al-Sayyed and A. Sleit, "A Case Study for Evaluating Facebook Pages with Respect to Arab Mainstream News Media," Jordanian Journal of Computers and Information Technology (JJCIT), vol. 3, no. 3, December 2017.

[27] A. Bouziane, D. Bouchiha, N. Doumi and M. Malki, "Toward an Arabic Question Answering System over Linked Data," Jordanian Journal of Computers and Information Technology (JJCIT), vol. 4, no. 2, August 2018.

[28] E. Al-Shawakfa, "A Rule-based Approach to Understand Questions in Arabic Question Answering," Jordanian Journal of Computers and Information Technology (JJCIT), vol. 2, no. 3, Dec. 2016.

[29] Oueslati et al., "A Review of Sentiment Analysis Research in Arabic Language," Future Generation Computing Systems, vol. 112, pp. 408-430, 2020.

[30] K. Nahar, N. Alhindawi, O. Al-Hazaimeh, R. M. Al-Khatib and A. Al-Akhras, "NLP and IR-based Solution for Confirming Classification of Research Papers," Journal of Theoretical and Applied Information Technology, vol. 96, pp. 5269-5279, 2018.

[31] M. Alshanaq, K. Nahar and K. Halawani, "AQAS: Arabic Question Answering System Based on SVM, SVD and LSI," Journal of Theoretical and Applied Information Technology, vol. 97, pp. 681-691, 2019.

[32] K. Nahar, M. Alshanaq, A. Manasrah, R. Alshorman and I. Alazzam, "A Holy Quran Reader/Reciter Identification System Using Support Vector Machine," International Journal of Machine Learning and Computing, vol. 9, pp. 458-464, 2019.

[33] K. Nahar, A. Al Eroud, M. Barahoush and A. Al-Akhras, "SAP: Standard Arabic Profiling Toolset for Textual Analysis," International Journal of Machine Learning and Computing, vol. 9, pp. 222-229, 2019.

[34] K. Nahar, R. Al-Khatib, M. Alshanaq, M. Daradkeh and R. Malkawi, "Direct Text Classifier for Thematic Arabic Discourse Documents," International Arab Journal of Information Technology, vol. 17, (Published Online), 2020.