Abstract
Arabic text sentiment analysis suffers from low accuracy due to Arabic-specific challenges (e.g., limited resources, morphological complexity, and dialects) and general linguistic issues (e.g., fuzziness, implicit sentiment, sarcasm, and spam). The limited resources problem requires efforts to build new and improved Arabic corpora and lexica. We propose a class-specific sentiment analysis (CLASENTI) framework. The framework includes a new annotation approach to build multi-faceted Arabic corpus and lexicon allowing for simultaneous annotation of different facets, including domains, dialects, linguistic issues, and polarity strengths. Each of these facets has multiple classes (e.g., the nine classes representing dialects found in the Arab world). The new corpus and lexicon annotations facilitate the development of new class-specific classification models and polarity strength calculation. For the new sentiment classification models, we propose a hybrid model combining corpus-based and lexicon-based models. The corpus-based model has two interrelated phases to build; (1) full-corpus classification models for all facets; and (2) class-specific models trained on filtered subsets of the corpus according to the performances of the full-corpus models. To calculate polarity strengths, the lexicon-based model filters the annotated lexicon based on the specific classes of the domain and dialect. As a case study, we collect and annotate 15274 reviews from various sources, including surveys, Facebook comments, and Twitter posts, pertaining to governmental services. In addition, we develop a new web-based application to apply the proposed framework on the case study. CLASENTI framework reaches up to 95% accuracy and 93% F1-Score surpassing the best-known sentiment classifiers implemented in Scikit-learn library that achieve 82% accuracy and 81% F1-Score for Arabic when tested on the same dataset.
- O. Abdelwahab, M. Bahgat, C. J. Lowrance, and A. Elmaghraby. 2015. Effect of training set size on SVM and naive Bayes for Twitter sentiment analysis. In Proceedings of the IEEE International Symposium on Signal Processing and Information Technology (ISSPIT’15). IEEE, 46--51. Google ScholarDigital Library
- M. Abdul-mageed and M. Diab. 2012. Toward building a large-scale Arabic sentiment lexicon. In Proceedings of the 6th International Global WordNet Conference. 18--22.Google Scholar
- M. Abdul-mageed, M. Diab, and S. Kübler. 2014. SAMAR: Subjectivity and sentiment analysis for Arabic social media. Comput. Speech Lang. 28, 20--37. Google ScholarDigital Library
- M. Abdul-mageed and M. T. Diab. 2012. AWATIF: A multi-genre corpus for modern standard arabic subjectivity and sentiment analysis. In Proceedings of the LREC International Conference on Language Resources and Evaluation. 3907--3914.Google Scholar
- M. Abdul-mageed and M. T. Diab. 2014. SANA: A large scale multi-genre, multi-dialect lexicon for arabic subjectivity and sentiment analysis. In Proceedings of the LREC 9th International Conference on Language Resources and Evaluation. 1162--1169.Google Scholar
- M. Abdul-mageed, M. T. Diab, and M. Korayem. 2011. Subjectivity and sentiment analysis of modern standard arabic. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics. 587--591. Google ScholarDigital Library
- M. Abdul-mageed and M. Korayem. 2010. Automatic identification of subjectivity in morphologically rich languages: The case of arabic. In Proceedings of the 1st Workshop on Computational Approaches to Subjectivity and Sentiment Analysis (WASSA’10). 2--6.Google Scholar
- M. Abdul-mageed, S. Kübler, and M. Diab. 2012. Samar: A system for subjectivity and sentiment analysis of arabic social media. In Proceedings of the 3rd Workshop in Computational Approaches to Subjectivity and Sentiment Analysis. Association for Computational Linguistics, 19--28. Google ScholarDigital Library
- N. Abdulla, N. Ahmed, M. Shehab, and M. Al-ayyoub. 2013. Arabic sentiment analysis: Lexicon-based and corpus-based. In Proceedings of the IEEE Applied Electrical Engineering and Computing Technologies (AEECT13). 1--6.Google Scholar
- N. Ahmed. 2018. Large-scale arabic sentiment corpus and lexicon building for concept-based sentiment analysis systems. Doctor of Philosophy in Computer Engineering, Hacettepe University Turkey. Retrieved from http://www.openaccess.hacettepe.edu.tr:8080/xmlui/bitstream/handle/11655/4170/10176094.pdf?sequence=18isAllowed=y.Google Scholar
- A. J. S. Al mukhaiti, S. Siddiqui, and K. Shaalan. 2017. Dataset built for arabic sentiment analysis. In Proceedings of the International Conference on Advanced Intelligent Systems and Informatics. Springer, 406--416.Google Scholar
- M. N. Al-kabi, I. M. Alsmadi, A. H. Gigieh, H. A. Wahsheh, and M. M. Haidar. 2014. Opinion mining and analysis for arabic language. Int. J. Adv. Comput. Sci. Appl. 5, 181--195.Google Scholar
- R. Al-Sabbagh and R. Girju. 2012. YADAC: Yet another dialectal arabic corpus. In Proceedings of the LREC International Conference on Language Resources and Evaluation. 2882--2889.Google Scholar
- A. Al-Sallab, R. Baly, H. Hajj, K. B. Shaban, W. El-Hajj, and G. Badaro. 2017. AROMA: A recursive deep learning model for opinion mining in arabic as a low resource language. ACM Trans. Asian Low-Res. Lang. Info. Process. 16, 25. Google ScholarDigital Library
- M. Al-Smadi, B. Talafha, M. Al-ayyoub, and Y. Jararweh. 2018. Using long short-term memory deep neural networks for aspect-based sentiment analysis of Arabic reviews. Int. J. Mach. Learn. Cybernet. 1--13.Google Scholar
- S. S. Alotaibi. 2015. Sentiment analysis in the arabic language using machine learning. Colorado State University. Libraries.Google Scholar
- S. S. Alotaibi and C. W. Anderson. 2016. Extending the knowledge of the arabic sentiment classification using aforeign external lexical source. In International Journal on Natural Language Computing (IJNLC'16) 5, 3 (2016), 1--11.Google Scholar
- M. A. Aly and A. F. Atiya. 2013. LABR: A large scale arabic book reviews dataset. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). Vol. 2. 494--498.Google Scholar
- G. Badaro, R. Baly, H. Hajj, N. Habash, and W. El-hajj. 2014. A large scale Arabic sentiment lexicon for Arabic opinion mining. In Proceedings of the EMNLP 2014 Workshop on Arabic Natural Language Processing (ANLP'14). 165--173.Google Scholar
- R. Baly, G. Badaro, A. Hamdi, R. Moukalled, R. Aoun, G. El-khoury, A. El-sallab, H. Hajj, N. Habash. and K. Bashir Shaban. 2017. OMAM at semeval-2017 task 4: Evaluation of english state-of-the-art sentiment analysis models for arabic and a new topic-based model. In Proceedings of the 11th International Workshop on Semantic Evaluations (SemEval’17). Association for Computational Linguistics, 594--601.Google Scholar
- R. Baly, H. Hajj, N. Habash, K. B. Shaban, and W. El-hajj. 2017. A sentiment treebank and morphologically enriched recursive deep models for effective sentiment analysis in arabic. ACM Trans. Asian Low-Res. Lang. Info. Process. 16, 23. Google ScholarDigital Library
- W. Boag, P. Potash and A. Rumshisky. 2015. Twitter-hawk: A feature bucket approach to sentiment analysis. Proceedings of the International Workshop on Semantic Evaluations (SemEval’15). 640--646.Google Scholar
- E. Cambria, S. Poria, R. Bajpai, and B. Schuller. 2016. SenticNet 4: A semantic resource for sentiment analysis based on conceptual primitives. In Proceedings of the 26th International Conference on Computational Linguistics: Technical Papers (COLING 2016). 2666--2677.Google Scholar
- C. Catal and M. Nangir. 2017. A sentiment classification model based on multiple classifiers. Appl. Soft Comput. 50, 135--141. Google ScholarDigital Library
- N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer. 2002. SMOTE: Synthetic minority over-sampling technique. J. Artific. Intell. Res. 16, 321--357. Google ScholarDigital Library
- H. Chen, W. Chung, J. J. Xu, G. Wang, Y. Qin, and M. Chau. 2004. Crime data mining: A general framework and some examples. Computer 37, 50--56. Google ScholarDigital Library
- J. M. Cotelo, F. L. Cruz, F. Enríquez, and J. Troyano. 2016. Tweet categorization by combining content and structural knowledge. Info. Fusion 31, 54--64. Google ScholarDigital Library
- R. Cotterell and C. Callison-burch. 2014. A multi-dialect, multi-genre corpus of informal written Arabic. In Proceedings of the Language Resources and Evaluation Conference (LREC’14).Google Scholar
- M. Diab, N. Habash, O. Rambow, M. Altantawy, and Y. Benajiba. 2010. COLABA: Arabic dialect annotation and processing. In Proceedings of the LREC Workshop on Semitic Language Processing. 66--74.Google Scholar
- A. Eesee and N. Omar. 2016. A hybrid method for arabic educational sentiment analysis. J. Appl. Sci. 16, 216.Google ScholarCross Ref
- A. El-halees and others. 2011. Arabic opinion mining using combined classification approach. In Proceedings of the 12th International Arab Conference on Information Technology. Naif Arab University for Security Sciences, 264--271. http://repository.nauss.edu.sa/handle/123456789/55412.Google Scholar
- H. Elfardy and M. T. Diab. 2013. Sentence level dialect identification in arabic. Assoc. Comput. Ling. 2, 456--461.Google Scholar
- H. Elsahar and S. R. El-beltagy. 2015. Building large arabic multi-domain resources for sentiment analysis. In International Conference on Intelligent Text Processing and Computational Linguistics. Springer, 23--34.Google Scholar
- A. Esuli and F. Sebastiani. 2006. Sentiwordnet: A publicly available lexical resource for opinion mining. In Proceedings of the 5th edition of the International Conference on Language Ressources and Evaluation (LREC’06). Citeseer, 417--422.Google Scholar
- R.-E. Fan, K.-W. Chang, C.-J. Hsieh, X.-R. Wang, and C.-J. Lin. 2008. LIBLINEAR: A library for large linear classification. J. Mach. Learn. Res 9, 1871--1874. Google ScholarDigital Library
- N. Farra, E. Challita, R. A. Assi, and H. Hajj. 2010. Sentence-level and document-level sentiment mining for Arabic texts. In Proceedings of the IEEE International Conference on Data Mining Workshops (ICDMW’10). IEEE, 1114--1119. Google ScholarDigital Library
- E. Ferrara, W.-Q. Wang, O. Varol, A. Flammini, and A. Galstyan. 2016. Predicting online extremism, content adopters, and interaction reciprocity. In Proceedings of the International Conference on Social Informatics. Springer, 22--39.Google Scholar
- A. B. Goldberg and X. Zhu. 2006. Seeing stars when there aren't many stars: graph-based semi-supervised learning for sentiment categorization. In Proceedings of the 1st Workshop on Graph Based Methods for Natural Language Processing. Association for Computational Linguistics, 45--52. Google ScholarDigital Library
- N. Y. Habash. 2010. Introduction to arabic natural language processing. Synth. Lect. Human Lang. Technol. 3, 1--187.Google ScholarCross Ref
- A. Hamdi, K. Shaban, and A. Zainal. 2016. A review on challenging issues in arabic sentiment analysis. J. Comput. Sci. 12, 471--481.Google ScholarCross Ref
- L. Hamers, Y. Hemeryck, G. Herweyers, M. Janssen, H. Keters, R. Rousseau, and A. Vanhoutte. 1989. Similarity measures in scientometric research: The jaccard index versus salton's cosine formula. Info. Process. Manage. 25, 315--318. Google ScholarDigital Library
- M. Hammad and E. Hemayed. 2013. Automating credibility assessment of arabic news. In Proceedings of the 5th International Conference on Social Informatics. Springer, 139--152. Google ScholarDigital Library
- H. Han, W.-Y. Wang, and B.-H. Mao. 2005. Borderline-SMOTE: A new over-sampling method in imbalanced data sets learning. In Proceedings of the International Conference on Intelligent Computing Springer, 878--887. Google ScholarDigital Library
- V. Hatzivassiloglou and K. R. Mckeown. 1997. Predicting the semantic orientation of adjectives. In Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics and Eighth Conference of the European Chapter of the Association for Computational Linguistics. Association for Computational Linguistics, 174--181. Google ScholarDigital Library
- H. S. Ibrahim, S. M. Abdou, and M. Gheith. 2015. Sentiment analysis for modern standard arabic and colloquial. ArXiv Preprint Arxiv:1505.03105.Google Scholar
- H. Kanayama and T. Nasukawa. 2006. Fully automatic lexicon expansion for domain-oriented sentiment analysis. In Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 355--363. Google ScholarDigital Library
- M. Karanasou, C. Doulkeridis, and M. Halkidi. 2015. DsUniPi: An SVM-based approach for sentiment analysis of figurative language on twitter. In Proceedings of the SemEval@ NAACL-HLT, 709--713.Google Scholar
- M. Korayem, D. Crandall, and M. Abdul-mageed. 2012. Subjectivity and sentiment analysis of arabic: A survey. In International Conference on Advanced Machine Learning Technologies and Applications. Springer, 128--139.Google Scholar
- M. Kubat and S. Matwin. 1997. Addressing the curse of imbalanced training sets: One-sided selection. In Proceedings of the ICML 14th International Conference on Machine Learning. 179--186.Google Scholar
- A. Kumar, O. Irsoy, J. Su, J. Bradbury, R. English, B. Pierce, P. Ondruska, I. Gulrajani, and R. Socher. 2015. Ask me anything: Dynamic memory networks for natural language processing. CoRR, abs/1506.07285.Google Scholar
- J. Laurikkala. 2001. Improving identification of difficult small classes by balancing class distribution. In Proceedings of the 8th Conference on Artificial Intelligence in Medicine in Europe. Springer, 63--66. Google ScholarDigital Library
- T. Li, Y. Zhang, and V. Sindhwani. 2009. A non-negative matrix tri-factorization approach to sentiment classification with lexical prior knowledge. In Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language. Association for Computational Linguistics, 244--252. Google ScholarDigital Library
- B. Liu. 2012. Sentiment analysis and opinion mining. Synth. Lect. Human Lang. Technol. 5, 1--167. Google ScholarDigital Library
- L. Lusa. 2012. Evaluation of smote for high-dimensional class-imbalanced microarray data. In Proceedings of the 11th International Conference on Machine Learning and Applications (ICMLA’12). IEEE, 89--94. Google ScholarDigital Library
- I. Mani and I. Zhang. 2003. kNN approach to unbalanced data distributions: A case study involving information extraction. In Proceedings of Workshop on Learning From Imbalanced Datasets.Google Scholar
- C. D. Manning, P. Raghavan, and H. Schütze. 2008. Introduction to Information Retrieval. Cambridge University Press. Google ScholarDigital Library
- W. Medhat, A. Hassan, and H. Korashy. 2014. Sentiment analysis algorithms and applications: A survey. Ain Shams Eng. J. 5, 1093--1113.Google ScholarCross Ref
- G. A. Miller. 1995. WordNet: A lexical database for english. Commun. ACM 38, 39--41. Google ScholarDigital Library
- A. Mourad and K. Darwish. 2013. Subjectivity and sentiment analysis of modern standard arabic and arabic microblogs. In Proceedings of the 4th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, 55--64.Google Scholar
- A. Mukwazvure and K. Supreethi. 2015. A hybrid approach to sentiment analysis of news comments. In Proceedings of the 4th International Conference on Reliability, Infocom Technologies and Optimization (ICRITO’15). IEEE, 1--6.Google Scholar
- M. Nabil, M. Aly, and A. F. Atiya. 2015. ASTD: Arabic sentiment tweets dataset. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. 2515--2519.Google Scholar
- D. Najar and S. Mesfar. 2017. Opinion mining and sentiment analysis for arabic on-line texts: Application on the political domain. International Journal of Speech Technology 20, 575--585. Google ScholarDigital Library
- H. M. Nguyen, E. W. Cooper and K. Kamei. 2011. Borderline over-sampling for imbalanced data classification. Int. J. Knowl. Eng. Soft Data Parad. 3, 4--21. Google ScholarDigital Library
- H. Pajupuu, R. Altrov, and J. Pajupuu. 2016. Identifying polarity in different text types. Folklore: Electronic Journal of Folklore 64 (2016), 126--138.Google Scholar
- B. Pang and L. Lee. 2008. Opinion mining and sentiment analysis. Found. Trends Info. Retriev. 2, 1--135. Google ScholarDigital Library
- F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, and V. Dubourg. 2011. Scikit-learn: Machine learning in python. J. Mach. Learn. Res. 12, 2825--2830. Google ScholarDigital Library
- R. Prabowo and M. Thelwall. 2009. Sentiment analysis: A combined approach. J. Informetr. 3, 143--157.Google ScholarCross Ref
- E. Refaee and V. Rieser. 2014. An arabic twitter corpus for subjectivity and sentiment analysis. In Proceedings of the 9th International Conference on Language Resources and Evaluation (LREC’14). European Language Resources Association.Google Scholar
- E. Refaee and V. Rieser. 2015. Benchmarking machine translated sentiment analysis for arabic tweets. In Proceedings of the NAACL-HLT 2015 Student Research Workshop (SRW’15). 71.Google Scholar
- V. G. C. RM. 2014. Performance evaluation of machine learning classifiers in sentiment mining. ArXiv Preprint Arxiv:1402.3891.Google Scholar
- M. Romanov. 2013. Toward the digital history of the pre-modern muslim world: Developing text-mining techniques for the study of arabic biographical collections. Compar. Oriental Manuscript Studies Newslett. 4.Google Scholar
- M. Rushdi-saleh, M. T. Martín-valdivia, L. A. Ureña-lópez, and J. M. Perea-ortega. 2011. Bilingual experiments with an arabic-english corpus for opinion mining. In Proceedings of the International Conference Recent Advances in Natural Language Processing 2011. 740--745.Google Scholar
- M. Rushdi-saleh, M. T. Martín Valdivia, L. A. Ureña lópez, and J. M. Perea Ortega. 2011. OCA: Opinion corpus for Arabic. J. Amer. Soc. Info. Sci. Technol. 62, 2045--2054. Google ScholarDigital Library
- J. A. Sáez, B. Krawczyk, and M. Woźniak. 2016. Analyzing the oversampling of different classes and types of examples in multi-class imbalanced datasets. Pattern Recogn. 57, 164--178. Google ScholarDigital Library
- Olena Kummer, Jacques Savoy, and Rue Emile Argand. 2012. Feature selection in sentiment analysis. In Proceedings of the CORIA 2012, 9th Information Retrieval Conference. Citeseer, Bordeaux, France.Google Scholar
- M. A. Shehab, O. Badarneh, M. Al-ayyoub, and Y. Jararweh. 2016. A supervised approach for multi-label classification of arabic news articles. In Proceedings of the 7th International Conference on Computer Science and Information Technology (CSIT’16). IEEE, 1--6.Google Scholar
- A. M. Shoukry. 2013. Arabic sentence level sentiment analysis. Thesis. The American University in Cairo.Google Scholar
- N. F. F. D. Silva, L. F. Coletta, and E. R. Hruschka. 2016. A survey and comparative study of tweet sentiment analysis via semi-supervised learning. ACM Comput. Surveys 49, 15. Google ScholarDigital Library
- V. Sindhwani and P. Melville. 2008. Document-word co-regularization for semi-supervised sentiment analysis. In Proceedings of the 8th IEEE International Conference on Data Mining (ICDM'08). IEEE, 1025--1030. Google ScholarDigital Library
- R. Socher, A. Perelygin, J. Y. Wu, J. Chuang, C. D. Manning, A. Y. Ng, and C. Potts. 2013. Recursive deep models for semantic compositionality over a sentiment treebank. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’13). 1642.Google Scholar
- K. Sparck Jones. 1972. A statistical interpretation of term specificity and its application in retrieval. J. Document. 28, 11--21.Google ScholarCross Ref
- Miniwatts Marketing Group. 2016. Internet World Users By Language - Top 10 Languages. https://www.internetworldstats.com/stats7.htm.Google Scholar
- Y. Sun, A. K. Wong, and M. S. Kamel. 2009. Classification of imbalanced data: A review. Int. J. Pattern Recogn. Artific. Intell. 23, 687--719.Google ScholarCross Ref
- M. Taboada, J. Brooke, M. Tofiloski, K. Voll, and M. Stede. 2011. Lexicon-based methods for sentiment analysis. Comput. Linguist. 37, 267--307. Google ScholarDigital Library
- K. Taghva, R. Elkhoury, and J. S. Coombs. 2005. Arabic stemming without a root dictionary. In Proceedings of the International Conference on Information Technology: Coding and Computing (ITCC'05). 152--157. Google ScholarDigital Library
- I. Tomek. 1976. Two modifications of CNN. IEEE Trans. Syst., Man Cybernet. 6, 769--772.Google Scholar
- P. D. Turney. 2002. Thumbs up or thumbs down?: Semantic orientation applied to unsupervised classification of reviews. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, 417--424. Google ScholarDigital Library
- A. Yousefpour, R. Ibrahim, and H. N. Abdull hamed. 2014. A novel feature reduction method in sentiment analysis. International Journal of Innovative Computing 4, 1 (2014), 34--40.Google Scholar
- O. F. Zaidan and C. Callison-burch. 2011. The arabic online commentary dataset: An annotated dataset of informal arabic with high dialectal content. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, 37--41. Google ScholarDigital Library
Index Terms
- CLASENTI: A Class-Specific Sentiment Analysis Framework
Recommendations
Exploring weakly supervised latent sentiment explanations for aspect-level review analysis
CIKM '13: Proceedings of the 22nd ACM international conference on Information & Knowledge ManagementIn sentiment analysis, aspect-level review analysis has been an important task because it can catalogue, aggregate, or summarize various opinions according to a product's properties. In this paper, we explore a new concept for aspect-level review ...
Fuzzy Subjective Sentiment Phrases: A Context Sensitive and Self-Maintaining Sentiment Lexicon
WI-IAT '14: Proceedings of the 2014 IEEE/WIC/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT) - Volume 01In this paper, we present a novel self-maintaining, domain-independent, and context-sensitive Sentiment Lexicon (SL) which finds and maps opinion words and phrases to a fuzzy sentiment score ranging from strong negative to strong positive. We show that ...
Joint sentiment/topic model for sentiment analysis
CIKM '09: Proceedings of the 18th ACM conference on Information and knowledge managementSentiment analysis or opinion mining aims to use automated tools to detect subjective information such as opinions, attitudes, and feelings expressed in text. This paper proposes a novel probabilistic modeling framework based on Latent Dirichlet ...
Comments