• P-ISSN 0974-6846 E-ISSN 0974-5645

Indian Journal of Science and Technology


Indian Journal of Science and Technology

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

Original Article

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

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


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


  1. 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
  2. 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
  3. Robert P, Kellerman H. A general Psychoevolutionary Theory. In: Theories of Emotion. (pp. 3-33) Academic Press. 1980.
  4. 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
  5. 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
  6. 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
  7. 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
  8. 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
  9. 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
  10. 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
  11. 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
  12. 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
  13. 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
  14. 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
  15. 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
  16. 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
  17. Saif M, Peter T, D. Crowdsourcing a Word-Emotion Association Lexicon. Computational Intelligence. 2013;29(3):436–465.
  18. 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
  19. 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
  20. 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
  21. 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


© 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)


Subscribe now for latest articles and news.