SENTIMENT ANALYSIS ON MOVIE REVIEWS IN TAMIL LANGUAGE USING MACHINE LEARNING

Paper ID: EIJTEM_2025_12_4_222-232

Author's Name: Dr.B.Karthikeyan, Dr.R.Maheswari

Volume: 12

Issue: 4

Year: 2025

Page No: 222-232

Abstract:

Tamil (தமிழ) is a classical language and one of the main languages of the Dravidian language family. Nowadays, more people are commonly using their mother tongue to express their opinions and views on social media. Especially Indian languages are often used in social media messages. However, there are not as much work in sentiment analysis has been done for Indian languages like Hindi, Tamil, Kannada, etc. In this work, it is focused on Tamil-language YouTube comments. our objective is to classify the sentiment of the Tamil movies based on YouTube comments in tamil using Tamil SentiWordNet (TSWN). The primary sentiments categorization of Tamil films is identified using domain-specific ontology. In contextual semantics, the sentiment of a word may flip based on the neighboring word. So, we have used unigram, bigrams, and trigrams approaches for understanding sentiment of the comments in Tamil. The sentiment scoring has been applied by lexicon based and algorithm- based methods. In lexicon-based method it is further proceeded into five new approaches. Among those word count methods and manual scoring methods are based on the actual positive and negative corpus. Vader sentiment intensity analyzer, text blob and Afinn are based on the translated positive and negative corpus. In algorithm-based method the text document has been vectorized and its performance has been verified using various classification algorithms like Logistic Regression, Multinomial Naïve Bayes, Random Forest and Support Vector Machine. Their performances were noted and compared.

Keywords: Tamil, sentiment, reviews, corpus creation, lexicon based, text preprocessing.

References:

1. Chakravarthi, B., et al. (2020, December 17–21). Overview of the HASOC-DravidianCodeMix shared task on offensive language detection in Tamil and Malayalam. CEUR Workshop Proceedings, 3159. Retrieved from https://ceur.org/vol-3159
2. Kumar, A. M., et al. (2010, September). A novel data-driven algorithm for Tamil morphological generator. International Journal of Computer Applications, 6(12).
3. Mathan, T., & Manavalan. (2013, July 7). Stemmers for Tamil language: Performance analysis. Retrieved from https://www.academia.edu
4. Chakravarthi, B. R., et al. (2020, May 30). Corpus creation for sentiment analysis in code-mixed Tamil-English text. ACL Anthology.
5. Taboada, M., Brooke, J., Tofiloski, M., Voll, K., & Stede, M. (2011, June). Lexicon-based methods for sentiment analysis. Computational Linguistics, 37(2), 267–307.
6. Liu, B. (2012). Sentiment analysis and opinion mining. Synthesis Lectures on Human Language Technologies. Morgan & Claypool Publishers.
7. Regina, & Sengottuvelan, P. (2021). Analysis of sentiments in movie reviews using supervised machine learning technique. In Proceedings of the 2021 4th International Conference on Computing and Communications Technologies (ICCCT) (pp. 242–246). IEEE.
8. Abhishek, K., et al. (2020, May 25). Sentimental analysis for movie reviews. International Journal of Advanced Research in Computer Science.
9. Lone, M. Z. (2006, May). SentiWordNet 3.0: An enhanced lexical resource for sentiment analysis and opinion mining. Retrieved from https://www.academia.edu
10. Tripathi, & Trivedi, S. K. (2016). Sentiment analysis of Indian movie review with various feature selection techniques. In Proceedings of the 2016 IEEE International Conference on Advances in Computer Applications (ICACA) (pp. 181–185). IEEE.
11. Naidu, R., Bharti, S. K., Babu, K. S., & Mohapatra, R. K. (2017). Sentiment analysis using Telugu SentiWordNet. In Proceedings of the 2017 International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET) (pp. 666–670). IEEE.
12. Novendri, R., et al. (2020, June). Sentiment analysis of YouTube movie trailer comments using naïve Bayes. Bulletin of Computer Science and Electrical Engineering, 1(1), 26–32.
13. Thilagavathi, R., & Krishnakumari, K. (2018, April 24). Tamil-English language sentiment analysis system. International Journal of Engineering Research & Technology (IJERT).
14. Abdelrahman, S., et al. (2019, January 1). Sentiment analysis of English and Tamil tweets using path length similarity-based word sense disambiguation. Retrieved from https://www.semanticscholar.org
15. Jagdale, R., Shirsath, V., & Deshmukh, S. (2019). Sentiment analysis on product reviews using machine learning techniques. In Proceedings of CISC 2017 (pp. 693–702). Springer. https://doi.org/10.1007/978-981-13-0617-4_61
16. Ramanathan, V., et al. (2019, November 13). Predicting Tamil movies sentimental reviews using Tamil tweets. Journal of Computer Science, Science Publications.
17. Ramanathan, V., Thirunavukkarasu, M., & Thamarai, S. (2021). Sentiment analysis: An approach for analysing Tamil movie reviews using Tamil tweets. In Recent Advances in Modelling, Reliability and Computing Science (Vol. 3). B P International. https://doi.org/10.9734/bpi/ramrcs/v3/4845F
18. Thavareesan, S., & Mahesan, S. (2018, December). Review on sentiment analysis in Tamil texts. Journal of Science, 9(2), 1–6.
19. Se, S., Ravi, V., Kumar, M., & Soman, K. P. (2016). Predicting the sentimental reviews in Tamil movie using machine learning algorithms. Indian Journal of Science and Technology, 9. https://doi.org/10.17485/ijst/2016/v9i45/106482.

View PDF