IJETSI

Title: A MULTIFACETED ARABIC SENTIMENT ANALYSIS
Authors: Manal Mustafa Ali, A. Shakour AlSamahi, Alaa Hamouda
\|\| \|\|
1,2,3Azher University, Computer and system Department, Cairo - Egypt
MLA 8 Ali, Manal M., et al. "A MULTIFACETED ARABIC SENTIMENT ANALYSIS." IJETSI, vol. 2, no. 3, 2017, pp. 604-618, ijetsi.org/more2017.php?id=52. APA Ali, M. M., AlSamahi, A. S., & Hamouda, A. (2017). A MULTIFACETED ARABIC SENTIMENT ANALYSIS. IJETSI, 2(3), 604-618. Retrieved from http://ijetsi.org/more2017.php?id=52 Chicago Ali, Manal M., A. S. AlSamahi, and Alaa Hamouda. "A MULTIFACETED ARABIC SENTIMENT ANALYSIS." IJETSI 2, no. 3 (2017), 604-618. http://ijetsi.org/more2017.php?id=52.
References References [1] A. Abbasi; H. Chen; A. Salem, "Sentiment Analysis in Multiple Languages: Feature Selection for Opinion Classification in Web Forums" ACM Transactions on Information Systems, Vol. 26, No. 3, Article 12, June 2008. [2] A. Agarwal, B. Xie, I. Vovsha, O. Rambow, R. Passonneau, "Sentiment Analysis of Twitter Data", In Proceedings of the ACL 2011 Workshop on Languages in Social Media, pp. 30-38, 2011. [3] Alexander Hogenboom; Daniella Bal; Flavius Frasincar; Malissa Bal; Franciska de Jong; Uzay Kaymak "Exploiting Emoticons in Sentiment Analysis" 28th Annual ACM Symposium on Applied Computing, Coimbra, Portugal, pp. 703 - 710, Mar. 2013. [4] Ashraf S. Hussein, "Visualizing document similarity using n-grams and latent semantic analysis" SAI Computing Conference (SAI), IEEE, pp. 269 - 279, Sep. 2016. [5] Bashar Al Shboul; Mahmoud AlAyyoub; Yaser Jararweh, "Multi-Way Sentiment Classification of Arabic Reviews", 6th International Conference on Information and Communication Systems (ICICS), IEEE, pp. 206 -211, April 2015. [6] Bing Liu "Sentiment Analysis: A Multi-Faceted Problem" IEEE Intelligent Systems, Vol.25, No.3, pp. 76 - 80, Aug. 2010. [7] Danushka Bollegala; Tingting Mu; John Y. Goulermas "Cross-domain Sentiment Classification using Sentiment Sensitive Embeddings" IEEE Transactions on Knowledge and Data Engineering, Vol. 28, No. 2, Pages: 398 - 410, Feb. 2016. [8] Erik Cambria; "Affective Computing and Sentiment Analysis", IEEE Intelligent Systems. Vol. 31, Issue: 2, pp. 102 -107 March/April 2016. [9] Erik Cambria; Bjo?rn Schuller,.; Yunqing Xia,.; Catherine Havasi,.; "New Avenues in Opinion Mining and Sentiment Analysis", IEEE Intelligent Systems, Vol. 28, No.2, pp. 15-21, March /April 2013. [10] Enas Sedki; Abdelfattah Alzaqah; Arafat Awajan, "Arabic Text Dimensionality Reduction Using Semantic Analysis", WSEAS TRANSACTIONS on INFORMATION SCIENCE and APPLICATIONS. Vol. 12, pp. 209 - 218, 2015 [11] Fawaz S. Al-Anzi; Dia AbuZeina, "Toward an enhanced Arabic text classification using cosine similarity and Latent Semantic Indexing" Elsevier, April 2016 [12] Felipe Bravo-Marquez; Marcelo Mendoza; Barbara Poblete, "Combining Strengths, Emotions and Polarities for Boosting Twitter Sentiment Analysis", WISDOM'13, August 11 2013, Chicago, IL, USA, ACM, 2013. [13] Hossam S. Ibrahim; Sherif M. Abdou; Mervat Gheith, "Sentiment Analysis for Modern Standard Arabic and Colloquial", International Journal on Natural Language Computing (IJNLC), Vol. 4, No.2, pp. 95 - 109, April 2015. [14] Jaber Alwedyan; Wa'el Musa Hadi; Ma'an Salam; Hussein Y.Mansour, "Categorize Arabic Data Sets Using MultiClass Classification Based on Association Rule Approach", International Conference on Intelligent Semantic Web-Services and Applications (ISWSA'11), Amman, Jordan, ACM, April 2011. [15] J. Bernabe-Moreno; A. TejedaLorente ; C. Porcel ; H. Fujita; E. HerreraViedma; "CARESOME: A system to enrich marketing customers acquisition and retention campaigns using social media information" Elsevier, pp. 163-179, 2015. [16] Jasy Liew Suet Yan; Howard R. Turtle, "Exploring Fine-Grained Emotion Detection in Tweets", Proceedings of NAACL-HLT, Association for Computational Linguistics. San Diego, California, Pp. 73-80, June 2016. [17] Keng-Pei Lin; Ming-Syan Chen, "On the Design and Analysis of the PrivacyPreserving SVM Classifier", IEEE Transactions on Knowledge and Data Engineering, Vol. 23, No. 11, pp. 1704 -1717, 2011. [18] Kouloumpis, E., Wilson, T., Moore, J.: Twitter sentiment analysis: The good the bad and the omg! Proceedings of the Fifth International Association for the Advancement of Artificial Intelligence (AAAI) Conference on Weblogs and Social Media, pp. 538 - 541, 2011. [19] Le Zhang; Ponnuthurai Nagaratnam Suganthan "Random Forests with ensemble of feature spaces" Pattern Recognition. Elsevier, Vol. 47, No. 10, pp. 3429-3437, April 2014. [20] M.A.Jawale; D.N.Kyatanavar; A.B.Pawar; "Design of Automated Sentiment or Opinion Discovery System to Enhance Its Performance", Proc. of Int. Conf. on Advances in Information Technology and Mobile Communication, pp.48 - 58, 2013. [21] Mayy M. Al-Tahrawi ,"Arabic Text Categorization Using Logistic Regression" I.J. Intelligent Systems Technologies and Applications (IJISA), Vol. 7, No.6, pp. 71- 78, May 2015 [22] Mohammad Al-A'abed; Mahmoud Al-Ayyoub, "A Lexicon-Based Approach for Emotion Analysis of Arabic Social Media Content" Proceedings of the International Computer Sciences and Informatics Conference (ICSIC), pp. 343 - 351, 2016. [23] Mohammed Al-Kabi; Noor M. AlQudah; Izzat Alsmadi, Muhammad Dabour; Heider Wahsheh "Arabic / English Sentiment Analysis: An Empirical Study" ICICS'13, April 23-25, Irbid, Jordan, ACM, 2013. [24] Mohamed Attia; Mohsen A. A. Rashwan; Mohamed A. S. A. A. AlBadrashiny "Fassieh; a Semi-Automatic Visual Interactive Tool for Morphological, PoS-Tags, Phonetic, and Semantic Annotation of Arabic Text Corpora" IEEE Transactions on Audio, Speech, and Language Processing . Vol. 17, No. 5, pp. 916 - 925, Aug. 2009. [25] Mohammad S. Khorsheed; Abdulmohsen O. Al-Thubaity "Comparative evaluation of text classification techniques using a large diverse Arabic dataset" Language Resources and Evaluation, Springer, Vol. 47, No. 2, pp. 513 - 538, March, 2013. [26] Mohammad Abdul-Mageed; Mona Diab; Sandra Kubler; "SAMAR: Subjectivity and sentiment analysis for Arabic social media" Computer Speech & Language, ACM, Volume 28, Issue 1, Pp. 20-37, Jan. 2014. [27] Musa Alkhalifa; Horacio Rodriguez, "Automatically Extending Named Entities Coverage of Arabic WordNet using Wikipedia" International Journal on Information and Communication Technologies, Vol. 3, No. 3, pp. 20 - 36, June 2010. [28] Nandini Burade; Ankita Kendhe " A Review on Opinion Mining through Customer Experiences" International Journal of Computer Applications(IJCA). Vol. 107, No 18, pp. 37- 39, Dec. 2014. [29] Nizar A. Ahmed, Mohammed A. Shehab, Mahmoud Al-Ayyoub and Ismail Hmeidi "Scalable Multi-Label Arabic Text Classification", 6th International Conference on Information and Communication Systems (ICICS), IEEE, pp. 212 - 217, 2015. [30] Nora Al-Twairesh; Hend Al-Khalifa; AbdulMalik Al-Salman1, "AraSenTi: LargeScale Twitter-Specific Arabic Sentiment Lexicons" Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics. Pp. 697-705, Berlin, Germany, Aug. 2016. [31] Nurfadhlina Mohd Sharef; Harnani Mat Zin; Samaneh Nadali "Overview and Future [Opportunities of Sentiment Analysis Approaches for Big Data" Journal of Computer Sciences, 12 (3), pp. 153-168, 2016. [32] Pollyanna Goncalves; Daniel Hasan Dalip; Helen Costa; Marcos Andre Goncalves; Fabricio Benevenuto, "On the Combination of "Off-The-Shelf" Sentiment Analysis Methods" Pisa, Italy, ACM, April 2016. [33] Pollyanna Gonçalves; Matheus Araujo "Comparing and Combining Sentiment Analysis Methods". Proceeding COSN'13 of the first ACM conference on Online social networks. Boston, MA, USA, ACM, pp. 27-38, Oct. 2013. [34] Sarah O. Alhumoud; Mawaheb I. Altuwaijri; Tarfa M. Albuhairi; Wejdan M. lohaideb, "Survey on Arabic Sentiment Analysis in Twitter", World Academy of Science, Engineering and Technology, International Journal of Social, Behavioral, Educational, Economic, Business and Industrial Engineering Vol. 9, No. 1, pp. 364 -368, 2015. [35] Sameh Alansary; Magdy Nagi; "The International Corpus of Arabic: Compilation, Analysis and Evaluation" Proceedings of the EMNLP 2014 Workshop on Arabic Natural Language Processing (ANLP), pp. 8-17, Doha, Qatar, Oct. 2014. [36] Sameh Alansary; Magdy Nagi; Noha Adly, "A Suite of Tools for Arabic Natural Language Processing: A UNL Approach", 1st International Conference on Communications, Signal Processing, and their Applications (ICCSPA), pp. 1 - 6, 2013. [37] Sanjeera Siddiqui; Azza Abdel Monem; Khaled Shaalan "Towards Improving Sentiment Analysis in Arabic", Proceedings of the International Conference on Advanced Intelligent Systems and Informatics (AISI), Springer International Publishing, pp. 114-123, Oct. 2016. [38] Thais Mayumi Oshiro; Pedro Santoro Perez; Jos'e Augusto Baranauskas "How Many Trees in a Random Forest", MLDM 2012, Verlag Berlin Heidelberg, Springer, pp. 154-168, 2012. [39] Vidisha M. Pradhan; Jay Vala ; Prem Balani , "A Survey on Sentiment Analysis Algorithms for Opinion Mining", International Journal of Computer Applications (IJCA) Vol. 133 - No.9, pp. 7 -11, Jan. 2016. [40] Walaa M.; Ahmed H.; Hoda K.; "Sentiment analysis algorithms and applications: A survey", Ain Shams Engineering Journal, ElSevier, Vol. 5, No. 4, Pp. 1093-1113, Dec. 2014. [41] Yan Dang, Yulei Zhang, and Hsinchun Chen "A Lexicon-Enhanced Method for Sentiment Classification: An Experiment on Online Product Reviews" IEEE Intelligent Systems, Vol. 25, No. 4, pp. 46- 53, July /Aug. 2010. [42] Zakaria Elberrichi; Karima Abidi, "Arabic Text Categorization: a Comparative Study of Different Representation Modes", International Arab Journal of Information Technology, Vol. 9, no. 5, pp. 465 -470, Sep. 2012.
Abstract: This paper explores a method that uses International Corpus for Arabic (ICA) and Arabic WordNet (AWN) for sentiment classification of Arabic content. The highly inflictive nature of Arabic diminishes the effectiveness of conventional Bag of Words (BoW). The classical BoW is considered insufficient to form a representative vector for large scale social media content as it ignores possible relations between terms. The proposed work overcomes this limitation by incorporating different feature sets and performing cascaded analysis that fundamentally contains lexical analysis, morphological analysis, and semantic analysis. ICA is used to handle Arabic morphological pluralism. AWN semantically is exploited to extract generic and semantic relations for the lexical units over all the dataset. Moreover, specific feature extraction components are integrated to account for the linguistic characteristics of Arabic. Finally, we can leverage from social media standard features such as emoticons and smileys. So, a system for automatic Emotion Detection (ED) and mood recognitions was built to provide further sentiment insight and classification power. The optimal feature combination for each of the different emotions was determined using a combination of machine learning and rule- based methods. Experimentally, the results revealed that incorporation of morphological characteristics, semantic knowledge and emotional state description in feature vector is superior to classical BoW representation, in terms of feature reduction (31% reduction percentage) and accuracy results (FMeasure was increased up to 89%).

IJETSI is Member of