Detecting Multi-label emotions from code-mixed Facebook Status Updates

Swarnangini Sinha; Kanak Saxena; Nisheeth Joshi

doi:10.17485/IJST/v14i31.1122

Article

Detecting Multi-label emotions from code-mixed Facebook Status Updates

VIEWS 1255
PDF 233

Indian Journal of Science and Technology

DOI: 10.17485/IJST/v14i31.1122

Year: 2021, Volume: 14, Issue: 31, Pages: 2542-2549

Original Article

Detecting Multi-label emotions from code-mixed Facebook Status Updates

Swarnangini Sinha^1*, Kanak Saxena², Nisheeth Joshi³

¹Research Scholar, Department of Computer Science, Banasthali Vidyapith, Rajasthan, 304022, India
²Department of Computer Application, Samrat Ashok Technological Institute, Vidisha, 464001, Madhya Pradesh, India
³Department of Computer Science, Banasthali Vidyapith, Rajasthan, 304022, India

*Corresponding Author
Email: [email protected]

Received Date:17 June 2021, Accepted Date:24 July 2021, Published Date:22 September 2021

This work is licensed under a Creative Commons Attribution 4.0 International License.

Abstract

Objectives: With the growth of Social Media and the increasing use of English-Hindi (Hinglish) in linguistically diverse countries such as India, it is becoming increasingly important to analyse Hinglish-language content on Social Media platforms like Facebook. Prior sentiment and emotion analyses have only focused on single-label classification, ignoring the possibility of coexisting emotions within one instance. By analysing code-mixed Facebook status updates, the study aims to investigate multiple emotions. Method: 15,995 English-Hindi mixed Facebook status updates are annotated with emotions like joy, sadness, anger, fear, trust, disgust, surprise, anticipation, and love. Different pre-processing techniques are used to normalize the noisy data to produce more accurate results. We apply five different multi-level classification algorithms with word-level and character n-gram approaches to test the best classification results. Findings: The results of the experiment indicate that a status update can evoke multiple emotions rather than just one. Precision, recall, F1 score, and accuracy using both Micro and Macro averaging are used to evaluate the performance of different classifiers. As compared to other classification algorithms, the Classifier Chains algorithm with its 2-6-gram approach has the highest accuracy of 86% with a precision of 0.98. As compared to other classifiers, the Classifier Chains algorithm offered better results due to its ability to consider the correlations between class labels. Applications: The article focuses on the multi-label emotion classification task, which examines whether a Facebook status update shows none, one, or more of the nine emotions as outlined by Plutchik’s wheel of emotions. Considering the emotion of a text can support decision-making processes in various ways.

Keywords: Social Media; Emotion Analysis; Code-Mixed; MultiLabel 29 Classification; Emojis; Lexicons

References

Internet usage in India - statistics & facts. 2020. Available from: https://www.statista.com/topics/2157/internet-usage-in-india
Teens, Social Media and Technology 2018. 2018. Available from: https://www.pewresearch.org/internet/2018/05/31/teens-social-media-technology-2018
Leading countries based on Facebook audience size as of January 2021 (in millions) 2021. Available from: https://www.statista.com/statistics/268136/top-15-countries-based-on-number-of-facebook-users.Dateaccessed:05/06/2021
Facebook by the Numbers: Stats, Demographics & Fun Facts. Available from: https://www.omnicoreagency.com/facebook-statistics
M.Mohammad S. Sentiment Analysis: Detecting Valence, Emotions, and Other Affectual States from Text. Emotion Measurement. 2016;p. 201–237. Available from: https://doi.org/10.1016/B978-0-08-100508-8.00009-6
Koustav R, Shruti R, Rafiya B, Kalika B, Monojit C, Niloy G. Understanding Language Preference for Expression of Opinion and Sentiment: What do Hindi English Speakers do on Twitter. Proceedings of EMNLP. 2016;p. 1131–1141. Available from: https://www.aclweb.org/anthology/D16-1121.pdf
Clercq OD, Balahur A, Sedoc J, Barriere V, Tafreshi S, Buechel S. Shared Task: Predicting Empathy and Emotion in Reaction to News Stories. Proceedings of the Eleventh Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis. Proceedings of the 11th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis. 2021;p. 92–104. Available from: https://aclanthology.org/2021.wassa-1.10.pdf
Wadhawan A, Aggarwal A. Towards Emotion Recognition in Hindi-English Code-Mixed Data: A Transformer Based Approach. arXiv preprint . 2021. Available from: https://arxiv.org/pdf/2102.09943v2.pdf
Deepanshu V, Aditya B, Vinay S, Sarfaraz AS, Manish S. Corpus Creation and Emotion Prediction for Hindi-English Code-Mixed Social Media Text. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop. Akhtar Syed Sarfaraz. p. 128–135.
Robert P, Kellerman H. A general Psychoevolutionary Theory. In: Theories of Emotion. (pp. 3-33) Academic Press. 1980.
Shashank S, Srinivas PYKL, Chandra BR. Sentiment analysis of code - Mix script. International Conference on Computing and Network Communications. 2015;p. 530–534. doi: 10.1109/CoCoNet.2015.7411238
Shashank S, Srinivas PYKL, Chandra BR. Text normalization of code mix and sentiment analysis. International Conference on Advances in Computing, Communications, and Informatics (ICACCI). 2015;p. 1468–1473. doi: 10.1109/ICACCI.2015.7275819
Jamatia A, Gamback B, Das A. Part-of-Speech Tagging for Code-Mixed English-Hindi Twitter and Facebook Chat Messages. Proceedings of Recent Advances in Natural Language Processing. 2015;p. 239–248. Available from: https://1library.net/document/q01g3lxz-speech-tagging-mixed-english-hindi-twitter-facebook-messages.html
Raghavi KC, Chinnakotla MK, Shrivastava M. "Answer ka type kya he?": Learning to Classify Questions in Code-Mixed Language. Proceedings of the 24th International Conference on World Wide Web. 2015;p. 853–858. Available from: https://doi.org/10.1145/2740908.2743006
Utsab B, Amitava D, Wagner J, Jennifer F. Code Mixing: A Challenge for Language Identification in the Language of Social Media. Proceedings of 1st Workshop on Computational Approaches to Code Switching. 2014;p. 13–23. Available from: https://www.aclweb.org/anthology/W14-3902.pdf
Utsab B, Joachim W, Grzegorz C, Jennifer F. DCU-UVT: Word-Level Language Classification with Code-Mixed Data. Proceedings of The First Workshop on Computational Approaches to Code Switching. 2014;p. 127–132. Available from: https://aclanthology.org/W14-3915.pdf
Amitava D, GB. Identifying Languages at the Word Level in Code-Mixed Indian social media Text. Proceedings of 11th Int. Conf. Nat. Lang. Process. Goa. 2014;p. 169–178. Available from: https://www.aclweb.org/anthology/W14-5152.pdf
Yogarshi V, Spandana G, Jatin S, Kalika B, Monojit C. POS Tagging of English-Hindi Code-Mixed Social Media Content. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2014;p. 974–979. Available from: https://www.aclweb.org/anthology/D14-1105.pdf
Souvick G, Satanu G, Dipankar D. Part-of-speech Tagging of Code-Mixed Social Media Text. Proceedings of 2nd Workshop on Computational Approaches to Code Switching. 2016;p. 90–97. Available from: https://www.aclweb.org/anthology/W16-5811.pdf
Dinkar S, Savitha M, Debraj R, Devansh S, Kashyap D. Sentiment analysis of mixed language employing Hindi-English code switching. International Conference on Machine Learning and Cybernetics (ICMLC). 2015;p. 271–276. doi: 10.1109/ICMLC.2015.7340934
Rupal B, Yashvardhan S, Shubham S. Sentiment Analysis for Mixed Script Indic Sentences. International Conference on Advances in Computing. 2016;p. 524–529. doi: 10.1109/ICACCI.2016.7732099
Abdul-Mageed M, Mona D, Sandra K. SAMAR: Subjectivity and sentiment analysis for Arabic social media. Computer Speech and Language. 2014;28(1):20–37. doi: 10.1016/j.csl.2013.03.001
Das A, Bandyopadhyay S. Subjectivity Detection in English, and Bengali: A CRF-based Approach. In: Proceedings of 7th International Conference on Natural Language Processing Macmillan Publishers. 2009.
Grigorios T, Ioannis K, Ioannis V. Multi-label Classification: An Overview. International Journal of Data Warehousing and Mining . 2009;3:1–13. doi: 10.4018/jdwm.2007070101
Read J. Scalable Multi-label Classification. thesis
Saif M, Peter T, D. Crowdsourcing a Word-Emotion Association Lexicon. Computational Intelligence. 2013;29(3):436–465.
Jesse R, Bernhard P, Geoﬀ H, Eibe F. Classifier Chains for Multi-label Classification. Machine Learning. 2011;85(333). Available from: https://doi.org/10.1007/s10994-011-5256-5
Dominik H, Robin S, Weiwei C, Eyke H. Multilabel classification for exploiting cross-resistance information in HIV-1 drug resistance prediction. Bioinformatics. 2013;29(16):1946–1952. Available from: https://doi.org/10.1093/bioinformatics/btt331
Newton S, Alvares CE, Carolina MM, Diana LH. A Comparison of Multi-label Feature Selection Methods using the Problem Transformation Approach. Electronic Notes in Theoretical Computer Science. 2013;292(292):135–150. doi: 10.1016/j.entcs.2013.02.010
Min-Ling Z, Zhi-Hua Z. ML-KNN: A lazy learning approach to multi-label learning. Pattern Recognition. 2007;40(7):2038–2048. doi: 10.1016/j.patcog.2006.12.019

Copyright

© 2021 Sinha et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Published By Indian Society for Education and Environment (iSee)