The Limits of Words: Expanding a Word-Based Emotion Analysis System with Multiple Emotion Dictionaries and the Automatic Extraction of Emotive Expressions
Source abstract
Abstract
Wide adoption of social media has caused an explosion of information stored online, with the majority of that information containing subjective, opinionated, and emotional content produced daily by users. The field of emotion analysis has helped effectively process such human emotional expressions expressed in daily social media posts. Unfortunately, one of the greatest limitations of popular word-based emotion analysis systems has been the limited emotion vocabulary. This paper presents an attempt to extensively expand one such word-based emotion analysis system by integrating multiple emotion dictionaries and implementing an automatic extraction mechanism for emotive expressions. We first leverage diverse emotive expression dictionaries to expand the emotion lexicon of the system. To do that, we solve numerous problems with the integration of various dictionaries collected using different standards. We demonstrate the performance improvement of the system with improved accuracy and granularity of emotion classification. Furthermore, our automatic extraction mechanism facilitates the identification of novel emotive expressions in an emotion dataset, thereby enriching the depth and breadth of emotion analysis capabilities. In particular, the automatic extraction method shows promising results for applicability in further expansion of the dictionary base in the future, thus advancing the field of emotion analysis and offering new avenues for research in sentiment analysis, affective computing, and human–computer interaction.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Sentiment Analysis and Opinion Mining
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Text Information Processing Laboratory, Kitami Institute of Technology, Kitami 090-8507, Japan
Institute of Middle and Far Eastern Studies, Faculty of International and Political Studies, Jagiellonian University, 30-387 Krakow, Poland
Independent Researcher, Sapporo 060-0808, Japan
Langauge Media Laboratory, Hokkaido University, Sapporo 060-0808, Japan
References (44)
Show source-provided references
1. Beigi, G., Hu, X., Maciejewski, R., and Liu, H. (2016). An Overview of Sentiment Analysis in Social Media and Its Applications in Disaster Relief. Sentiment Analysis and Ontology Engineering: An Environment of Computational Intelligence, Springer.10.1007/978-3-319-30319-2_13 ↗
2. Extraction of emotions from multilingual text using intelligent text processing and computational linguistics10.1016/j.jocs.2017.01.010 ↗
3. Gaind, B., Syal, V., and Padgalwar, S. (2019). Emotion detection and analysis on social media. arXiv.
4. A survey of sentiment analysis in social media10.1007/s10115-018-1236-4 ↗
5. Information Extraction and Sentiment Analysis to Gain Insight into the COVID-19 Crisis10.1007/978-981-16-2594-7_28 ↗
6. ML-Ask: Open source affect analysis software for textual input in Japanese10.5334/jors.149 ↗
7. Nakamura, A. (1993). Kanjo Hyogen Jiten [Dictionary of Emotive Expressions], Tokyodo Publishing. (In Japanese).
8. Sharma, S., Kumar, P., and Kumar, K. (2017, January 5–8). LEXER: Lexicon Based Emotion Analyzer. Proceedings of the International Conference on Pattern Recognition and Machine Intelligence, Kolkata, India.10.1007/978-3-319-69900-4_47 ↗
9. Lexicon-based emotion analysis in Turkish
10. Emotion classification and crowd source sensing—A lexicon based approach10.1109/ACCESS.2019.2892624 ↗
11. Sentence-level emotion detection framework using rule-based classification10.1007/s12559-017-9503-3 ↗
12. A rule-based approach to emotion cause detection for Chinese micro-blogs10.1016/j.eswa.2015.01.064 ↗
13. Text-based emotion prediction system using machine learning approach10.1088/1757-899X/769/1/012022 ↗
14. Deep learning based emotion analysis of microblog texts10.1016/j.inffus.2020.06.002 ↗
15. Training highly multiclass classifiers
16. Hejima, I. (1995). A Short Dictionary of Feelings and Emotions in English and Japanese, Tokyodo Shuppan.
17. Murakami, M. (2002). Love, Hate and Everything in Between: Expressing Emotions in Japanese, Kodansha International.
18. Kobayashi, T., Ishii, K., Edani, N., Kondo, Y., and Adachi, Y. (2021, January 18–20). Kanjogo Jisho to Kanjo Bunseki Shisutemu EEAS [Dictionariy of Emotion Expression and Emotion Analysis System EEAS]. Proceedings of the 83rd National Convention of IPSJ, Online. (In Japanese).
19. A Proposal of Emotion Estimation Method for Words and Construction of Word-Emotion Dictionary10.5057/jjske.TJSKE-D-18-00104 ↗
20. Huang, D.S., Li, K., and Irwin, G.W. (2006). Statistical Analysis of a Japanese Emotion Corpus for Natural Language Processing. Computational Intelligence, Springer.
21. Sakai, T., Ptaszynski, M., and Masui, F. (2019, January 4–7). Kao Moji Patsu ni Motozui ta Kao Moji no Jido Seisei no Kano Sei ni Kansuru Chosa [Study on Potential of Automatic Emotion Generation based on Emoticon Parts]. Proceedings of the 33rd Annual Conference of the Japanese Society for Artificial Intelligence, Tokyo, Japan. (In Japanese).
22. Ptaszynski, M., Dybala, P., Rzepka, R., Araki, K., and Momouchi, Y. (2012, January 2–6). YACIS: A Five-Billion-Word Corpus of Japanese Blogs Fully Annotated with Syntactic and Affective Information. Proceedings of the AISB/IACAP World Congress, Birmingham, UK.
23. Twitter emotion analysis in earthquake situations
24. Steinborn, V., Maronikolakis, A., and Schütze, H. (2023). Politeness Stereotypes and Attack Vectors: Gender Stereotypes in Japanese and Korean Language Models. arXiv.
25. Automatically annotating a five-billion-word corpus of Japanese blogs for sentiment and affect analysis10.1016/j.csl.2013.04.010 ↗
26. Kudo, T. (2024, May 19). Mecab: Yet Another Part-of-Speech and Morphological Analyzer. Available online: http://mecab.sourceforge.net/.
27. A circumplex model of affect10.1037/h0077714 ↗
28. A method for automatic estimation of meaning ambiguity of emoticons based on their linguistic expressibility10.1016/j.cogsys.2019.09.022 ↗
29. Mikolov, T., Chen, K., Corrado, G., and Dean, J. (2013). Efficient estimation of word representations in vector space. arXiv.
30. Le, Q., and Mikolov, T. (2014, January 22–24). Distributed Representations of Sentences and Documents. Proceedings of the International Conference on Machine Learning, PMLR, Beijing, China.
31. Manabe, H., Oka, T., Umikawa, S., Takaoka, K., Uchida, Y., and Asahara, M. (2019, January 12–15). Fukusu Ryudo no Bunkatsu Kekka ni Motozuku Nihongo Tango Bunsan Hyogen [Japanese Word Distributed Representation Based on Multi-Granular Segmentation Results]. Proceedings of the 25th Annual Conference of the Association for Natural Language Processing (NLP2019), Nagoya, Japan.
32. Enriching Word Vectors with Subword Information10.1162/tacl_a_00051 ↗
33. Joulin, A., Grave, E., Bojanowski, P., Douze, M., Jégou, H., and Mikolov, T. (2016). FastText.zip: Compressing text classification models. arXiv.
34. Bag of Tricks for Efficient Text Classification
35. Ptaszynski, M., Momouchi, Y., Maciejewski, J., Dybala, P., Rzepka, R., and Araki, K. (2014). Annotating Japanese Blogs with Syntactic and Affective Information. Mining User Generated Content, Chapman and Hall/CRC.
36. Leonova, V. (2020, January 16–19). Review of Non-English Corpora Annotated for Emotion Classification in Text. Proceedings of the Databases and Information Systems: 14th International Baltic Conference, DB&IS 2020, Tallinn, Estonia. Proceedings 14.
37. Ihasz, P.L., Van, T.H., and Kryssanov, V.V. (2015, January 17–19). A Computational Model for Conversational Japanese. Proceedings of the 2015 International Conference on Culture and Computing (Culture Computing), Kyoto, Japan.10.1109/Culture.and.Computing.2015.43 ↗
38. Nasser, A. (2018). Large-Scale Arabic Sentiment Corpus and Lexicon Building for Concept-Based Sentiment Analysis Systems. [Ph.D. Thesis, Graduate School of Science and Engineering of Hacettepe University].
39. Barbaresi, A. (2016, January 12). Efficient Construction of Metadata-Enhanced Web Corpora. Proceedings of the 10th Web as Corpus Workshop, Berlin, Germany.10.18653/v1/W16-2602 ↗
40. Ptaszynski, M., Rzepka, R., Araki, K., and Momouchi, Y. (2012, January 16–19). A Robust Ontology of Emotion Objects. Proceedings of the Eighteenth Annual Meeting of The Association for Natural Language Processing (NLP-2012), Silchar, India.
41. Taku Kudo, Y.M. (September, January 31). Japanese Dependency Analysis using Cascaded Chunking. Proceedings of the CoNLL 2002: 6th Conference on Natural Language Learning 2002 (COLING 2002 Post-Conference Workshops), Taipei, Taiwan.10.3115/1118853.1118869 ↗
42. A statistical approach to mechanized encoding and searching of literary information10.1147/rd.14.0309 ↗
43. A statistical interpretation of term specificity and its application in retrieval10.1108/eb026526 ↗
44. Robertson, S.E., Walker, S., Jones, S., Hancock-Beaulieu, M.M., and Gatford, M. (1995). Okapi at TREC-3, NIST. NIST Special Publications (SPs).10.6028/NIST.SP.500-225.city ↗