Abstract Social media reflects the attitudes of the public towards specific events. Events are often related to persons, locations or organizations, the so-called Named Entities (NEs). This can define NEs as sentiment-bearing components. In this paper, we dive beyond NEs recognition to the exploitation of sentiment-annotated NEs in Arabic sentiment analysis. Therefore, we develop an algorithm to detect the sentiment of NEs based on the majority of attitudes towards them. This enabled tagging NEs with proper tags and, thus, including them in a sentiment analysis framework of two models: supervised and lexicon- based. Both models were applied on datasets of multi-dialectal content. The results revealed that NEs have no considerable impact on the supervised model, while employing NEs in the lexicon-based model improved the classification performance and outperformed most of the baseline systems.

References

[1] Abdulla N., Ahmed N., Shehab M., and Al- Ayyoub M., “Arabic Sentiment Analysis: Lexicon-Based and Corpus-Based,” in Proceedings of IEEE Jordan Conference on Applied Electrical Engineering and Computing Technologies, Amman, pp. 1-6, 2013.

[2] Abdulla N., Ahmed N., Shehab M., and Al- Ayyoub M., “Towards Improving The Lexicon- Based Approach for Arabic Sentiment Analysis,” International Journal of Information Technology and Web Engineering, vol. 9, no. 3, pp. 55-71, 2014.

[3] Altowayan A. and Tao L., “Word Embeddings for Arabic Sentiment Analysis,” in Proceedings of IEEE International Conference on Big Data, Washington, pp. 3820-3825, 2016.

[4] Darwish K., “Named Entity Recognition Using Cross-Lingual Resources: Arabic As An Example,” in Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, Sofia, pp. 1558-1567, 2013.

[5] El-Beltagy S. and Ali A. “Open Issues in the Sentiment Analysis of Arabic Social Media: A Case Study,” in Proceedings of 9th IEEE International Conference on Innovations in Information Technology, Abu Dhabi, pp. 215- 220, 2013.

[6] El-Beltagy S., Khalil T., Halaby A., and Hammad M., “Combining Lexical Features and a Supervised Learning Approach for Arabic Sentiment Analysis,” in Proceedings of International Conference on Intelligent Text Processing and Computational Linguistics, Konya, pp. 307-319, 2016.

[7] El-Makky N., Nagi K., El-Ebshihy A., Apady E., Hafez O., Mostafa S., and Ibrahim S., “Sentiment Analysis of Colloquial Arabic Tweets,” in Proceedings of the 3rd ASE International Conference on Social Informatics, Cambridge, pp. 1-9, 2013.

[8] Gridach M., “Character-Aware Neural Networks for Arabic Named Entity Recognition for Social Media,” in Proceedings of the 6th Workshop on South and Southeast Asian Natural Language Processing, Osaka, pp. 23-32, 2016.

[9] Karmani N., Soussou H., and Alimi A., “Tunisian Arabic Chat Alphabet Transliteration Using Probabilistic Finite State Transducers,” The International Arab Journal of Information Technology, vol. 16, no. 2, pp. 295-303, 2019.

[10] Karmani N., Tunisian Arabic Customer's Reviews Processing and Analysis for an Internet Supervision System, Thesis, Sfax University, 2017.

[11] Le Q. and Mikolov T., “Distributed Representations of Sentences and Documents,” in Proceedings of International Conference on Machine Learning, Beijing, pp. 1188-1196, 2014.

[12] Medhaffar S., Bougares F., Estève Y., and Hadrich-Belguith L., “Sentiment Analysis of Tunisian Dialects: Linguistic Resources and Experiments,” in Proceedings of the 3rd Arabic Natural Language Processing Workshop, Valencia, pp. 55-61, 2017.

[13] Mourad A. and Darwish K., “Subjectivity and Sentiment Analysis of Modern Standard Arabic 240 The International Arab Journal of Information Technology, Vol. 17, No. 2, March 2020 and Arabic Microblogs,” in Proceedings of the 4th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Atlanta, pp. 55-64. 2013.

[14] Mulki H., Haddad H., Gridach M., and Babaoğlu I., “Tw-StAR at SemEval-2017 Task 4: Sentiment classification of Arabic Tweets,” in Proceedings of the 11th International Workshop on Semantic Evaluation, At Vancouver, pp. 664- 669, 2017.

[15] Nabil M., Aly M., and Atiya A., “Astd: Arabic Sentiment Tweets Dataset,” in Proceedings of the Conference on Empirical Methods in Natural Language Processing, Lisbon, pp. 2515-2519, 2015.

[16] Piryani R., Madhavi D., and Singh V., “Analytical Mapping of Opinion Mining and Sentiment Analysis Research During 2000- 2015,” Information Processing and Management, vol. 53, no. 1, pp. 122-150, 2017.

[17] Salameh M., Mohammad S., and Kiritchenko S., “Sentiment after Translation: A Case-Study on Arabic Social Media Posts,” in Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Denver, pp. 767-777, 2015.

[18] Salameh M., Mohammad S., and Kiritchenko S., “How Translation Alters Sentiment,” Journal of Artificial Intelligence Research, vol. 55, pp. 95- 130, 2016.

[19] Sayadi K., Liwicki M., Ingold R., and Bui M., “Tunisian Dialect and Modern Standard Arabic Dataset for Sentiment Analysis: Tunisian Election Context,” To appear in IEEE Proceedings of ACLing, 2016.

[20] Yang B. and Cardie C., “Context-Aware Learning for Sentence-Level Sentiment Analysis With Posterior Regularization,” in Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, Baltimore, pp. 325- 335, 2014.

[21] Zahran M., Magooda A., Mahgoub A., Raafat H., Rashwan M., and Atyia A., “Word Representations in Vector Space and Their Applications for Arabic,” in Proceedings of International Conference on Intelligent Text Processing and Computational Linguistics, Cairo, pp. 430-443, 2015. Hala Mulki is a Ph.D. candidate at Computer Engineering Department, Konya Technical University, Turkey. She received her B.S. (2003) and MSc. (2009) from Aleppo University, Syria. Her research interests include Machine Learning and NLP. Hatem Haddad is Assistant Professor at Manouba University, Tunisia. He received his Ph.D. (2002) from University Grenoble Alpes, France. His current research interests include Machine Learning, NLP and Deep Learning. Mourad Gridach is a Postdoctoral Researcher at the University of Colorado, USA. He is a Professor at Ibn Zohr University, Morocco. His research interests include Artificial Intelligence, Computer Vision and NLP. Ismail Babaoğlu is Associate Professor at Department of Computer Engineering, Konya Technical University, Turkey. He received his Ph.D. (2010) from Selçuk University, Turkey. His research interests include swarm intelligence, and evolutionary algorithms.