Duygu Analizi İçin Yeni Bir Sözlük; NAYALex Duygu Sözlüğü

Öz

İletişimin ayrılmaz parçası olan duygular, farklı şekillerde (konuşma, jestler, yüz ifadeleri vb.) ortaya çıkmaktadır. Sosyal paylaşım platformlarında ise insanlar duygu ve düşüncelerini en çok metinsel paylaşımlar ile ifade etmektedir. İnsanların sosyal medya aracılığı ile paylaştığı metinler duygu durumları hakkında fikir vermektedir. Kişilik tespitinde duyguların sıklığının kişilik özellikleri ile ilişkili olduğunu gösteren birçok çalışma yapılmıştır. Dolayısıyla, sosyal medyada paylaşılan mesajlarda saklı olan duyguların tespiti ve ortaya çıkarılması önemlidir. Metinlerde saklı olan duygular kelime-duygu sözlükleriyle ortaya çıkarılabilmektedir. Bu sözlüklere baktığımızda en fazla sayıda duygu çıkarımı yapabilen NRC Duygu Sözlüğü, olumlu-olumsuz ile birlikte 8 farklı duyguyu ortaya çıkarabilmektedir. Ancak metin aracılığı ile duygularını yansıtan kişilerin duygularını, olumlu-olumsuz veya birkaç farklı duygu ile sınırlı tutmak çoğu zaman kişilik tespitinde yetersiz kalmaktadır. Bu çalışmada, paylaşılan metinlerden daha fazla duygu yakalamak için metinden olumlu-olumsuz ile birlikte (umut, kaygı, sevgi, karamsarlık, iyimserlik, öfke, korku, üzüntü vb.) 38 farklı duygu çıkarımı yapan NAYALex sözlüğü önerilmektedir. NRC Duygu Sözlüğüne ve Plutchik’in Temel Duyguların Psikoevrimsel Teorisine dayandırdığımız sözlüğümüzün her bir kelimesi 38 farklı duygudan en az biri ile ilişkilendirilmiş 6469 İngilizce kelimeden oluşmaktadır. Instagram kullanıcı paylaşımlarına ait 10000 farklı paylaşımdan oluşan veri setimiz üzerinde birtakım deneyler yaparak, NAYALex sözlüğümüzün uygulanabilirliği ve kullanılabilirliği gösterilmiştir. Diğer (LIWC, EmoSenticNet, NRC, Empath) duygu sözlükleriyle karşılaştırıldığında, sözlüğümüz Tiffany'nin belirttiği 154 duygu için %24,7 ile en kapsamlı duyguyu tespit edebilir.

Anahtar Kelimeler

• NRC
• NAYALex
• DuyguAnalizi
• DuyguSözlüğü
• Plutchik

A New Dictionary for Sentiment Analysis; NAYALex Emotion Dictionary

Abstract

Emotions, which are an integral part of communication, emerge in different ways (speech, gestures, facial expressions, etc.). On social sharing platforms, people express their feelings and thoughts mostly with textual shares. Textual sharings of people through social media give an idea about their emotional state.Many studies have been carried out showing that the frequency of emotions in personality inference is related to personality traits.Therefore, it is important to detect and reveal the emotions hidden in the messages shared on social media.Emotions are hidden in textual posts that people share via social media. It is crucial to detect and reveal the emotions hidden in the messages shared on social media. When we look at these lexicons, the NRC Emotion Lexicon, which can detect the greatest number of emotions, can reveal 8 different emotions in total, positive and negative. However, limiting the emotions of people who reflect their feelings through text to positive-negative or a few different emotions is often insufficient in personality determination. In this study, the NAYALex lexicon that can detect 38 different emotions (hope, anxiety, love, pessimism, optimism, anger, fear, sadness, etc.) from texts is proposed to recognize more emotions from shared texts. NRC Emotion Lexicon and each word of our lexicon, which we base on Plutchik'sPsychoevolutionary Theory of emotions, consists of 6469 English words associated with at least one of 38 different emotions. The applicability and usability of our NAYALexLexiconis demonstrated by conducting some experiments on our data set consisting of 10000 different posts belonging to Instagram users.Compared to other (LIWC, EmoSenticNet, NRC, Empath) emotion lexicons, our lexicon can detect the highest comprehensive emotion with 24.7% for the 154 emotions Tiffany stated.

Keywords

• NRC
• NAYALex
• Emotion Analysis
• Emotion Lexicon
• Plutchik

References

1. Alarid, M. (2016). Recruitment and radicalization: The role of social media and new technology. Impunity: Countering illicit power in war and transition, 313-330.
2. Baccianella, S., Esuli, A., & Sebastiani, F. (2010). Sentiwordnet 3.0: An enhanced lexical resource for sentiment analysis and opinion mining. Lrec, 10, 2200-2204.
3. Breck, E., Choi, Y., & Cardie, C. (2007, January). Identifying expressions of opinion in context. In IJCAI (Vol. 7, pp. 2683-2688).
4. Cambria, E., Schuller, B., Xia, Y., & Havasi, C. (2013). New avenues in opinion mining and sentiment analysis. IEEE Intelligent systems, 28(2), 15-21.
5. Colombetti, G. (2009). From affect programs to dynamical discrete emotions. Philosophical Psychology, 22(4), 407-425.
6. Deng, L., & Wiebe, J. (2015). Mpqa 3.0: An entity/event-level sentiment corpus. In Proceedings of the 2015 conference of the North American chapter of the association for computational linguistics: human language technologies (pp. 1323-1328).
7. Devika, M. D., Sunitha, C., & Ganesh, A. (2016). Sentiment analysis: a comparative study on different approaches. Procedia Computer Science, 87, 44-49.
8. Drews, M. (2007). Robert Plutchik's Psychoevolutıonary Theory Of Basıc Emotıons.( Erişim tarihi: 12.07.2021, http://www.adliterate.com/archives/Plutchik.emotion.theorie.POSTER.pdf)

9. Drews, M., & Krohn, M. (2007). Robert Plutchik’s Psychoevolutionary theory of basic emotions. University of Applied Sciences Postdam, Germany. Retrieved from http://www. markusdrews. de/Plutchiks. Emotionstheorie. PLAKAT. pdf.
10. Fast, E., Chen, B., & Bernstein, M. S. (2016, May). Empath: Understanding topic signals in large-scale text. In Proceedings of the 2016 CHI conference on human factors in computing systems (pp. 4647-4657).
11. Hatzivassiloglou, V., & McKeown, K. (1997, July). Predicting the semantic orientation of adjectives. In 35th annual meeting of the association for computational linguistics and 8th conference of the european chapter of the association for computational linguistics (pp. 174-181).
12. Hidalgo, C. R., Tan, E. S. H., & Verlegh, P. W. (2015). The social sharing of emotion (SSE) in online social networks: A case study in Live Journal. Computers in Human Behavior, 52, 364-372.
13. Hussein, D. M. E. D. M. (2018). A survey on sentiment analysis challenges. Journal of King Saud University-Engineering Sciences, 30(4), 330-338.
14. Kamps, J., Marx, M., Mokken, R. J., & De Rijke, M. (2004, May). Using WordNet to measure semantic orientations of adjectives. In LREC (Vol. 4, pp. 1115-1118).
15. Koto, F., & Adriani, M. (2015, December). HBE: Hashtag-based emotion lexicons for twitter sentiment analysis. In Proceedings of the 7th Forum for Information Retrieval Evaluation (pp. 31-34).
16. Koumpouri, A., Mporas, I., & Megalooikonomou, V. (2015, September). Evaluation of Four Approaches for" Sentiment Analysis on Movie Reviews" The Kaggle Competition. In Proceedings of the 16th International Conference on Engineering Applications of Neural Networks (INNS) (pp. 1-5).
17. Kušen, E., Cascavilla, G., Figl, K., Conti, M., & Strembeck, M. (2017, August). Identifying emotions in social media: comparison of word-emotion lexicons. In 2017 5th International Conference on Future Internet of Things and Cloud Workshops (FiCloudW) (pp. 132-137). IEEE.
18. Li, F., Pan, S. J., Jin, O., Yang, Q., & Zhu, X. (2012, July). Cross-domain co-extraction of sentiment and topic lexicons. In Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 410-419).
19. Lin, C. K., Lee, Y. Y., Yu, C. H., & Chen, H. H. (2014, November). Exploring ensemble of models in taxonomy-based cross-domain sentiment classification. In Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management (pp. 1279-1288).
20. Liu, B. (2012). Sentiment analysis and opinion mining. Synthesis lectures on human language technologies, 5(1), 1-167.
21. Medhat, W., Hassan, A., & Korashy, H. (2014). Sentiment analysis algorithms and applications: A survey. Ain Shams engineering journal, 5(4), 1093-1113.
22. Mohammad, S. (2011). Sentiment and Emotion Lexicons. ( Erişim tarihi: 12.07.2021, http://saifmohammad.com/WebPages/lexicons.html).
23. Mohammad, S. (2016) NRC Word-Emotion Association Lexicon. (Erişim tarihi: 12.07.2021, http://saifmohammad.com/WebPages/NRC-Emotion-Lexicon.html).
24. Mohammad, S. M., Zhu, X., Kiritchenko, S., & Martin, J. (2015). Sentiment, emotion, purpose, and style in electoral tweets. Information Processing & Management, 51(4), 480-499.
25. Mohammad, S., & Kiritchenko, S. (2013, June). Using nuances of emotion to identify personality. In Seventh International AAAI Conference on Weblogs and Social Media.
26. Pang, B., & Lee, L. (2009). Opinion mining and sentiment analysis. Comput. Linguist, 35(2), 311-312.
27. Pang, B., Lee, L., & Vaithyanathan, S. (2002). Thumbs up? Sentiment classification using machine learning techniques. arXiv preprint cs/0205070.
28. Pennebaker, J. W., Francis, M. E., & Booth, R. J. (2001). Linguistic inquiry and word count: LIWC 2001. Mahway: Lawrence Erlbaum Associates, 71(2001), 2001.
29. Plutchik, R. (1980). A general psychoevolutionary theory of emotion. In Theories of emotion (pp. 3-33). Academic press.
30. Plutchik, R. (2001). The nature of emotions: Human emotions have deep evolutionary roots, a fact that may explain their complexity and provide tools for clinical practice. American scientist, 89(4), 344-350.
31. Poria, S., Gelbukh, A., Cambria, E., Yang, P., Hussain, A., & Durrani, T. (2012, October). Merging SenticNet and WordNet-Affect emotion lists for sentiment analysis. In 2012 IEEE 11th international conference on signal processing (Vol. 2, pp. 1251-1255). IEEE.
32. Rao, D., & Ravichandran, D. (2009, March). Semi-supervised polarity lexicon induction. In Proceedings of the 12th Conference of the European Chapter of the ACL (EACL 2009) (pp. 675-682).
33. Ravi, K., & Ravi, V. (2015). A survey on opinion mining and sentiment analysis: tasks, approaches and applications. Knowledge-based systems, 89, 14-46.
34. Song, K., Gao, W., Chen, L., Feng, S., Wang, D., & Zhang, C. (2016, July). Build emotion lexicon from the mood of crowd via topic-assisted joint non-negative matrix factorization. In Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval (pp. 773-776).
35. Staiano, J., & Guerini, M. (2014). Depechemood: a lexicon for emotion analysis from crowd-annotated news. arXiv preprint arXiv:1405.1605.
36. Turney, P. D. (2002). Thumbs up or thumbs down? Semantic orientation applied to unsupervised classification of reviews. arXiv preprint cs/0212032.
37. Woolf, N. (2016). As fake news takes over Facebook feeds, many are taking satire as fact. The Guardian. Accessed, 1, 04-18.
38. Yessenalina, A., Yue, Y., & Cardie, C. (2010, October). Multi-level structured models for document-level sentiment classification. In Proceedings of the 2010 conference on empirical methods in natural language processing (pp. 1046-1056).