Over the last few years, the generation of computerized information has increased exponentially. Most people use digital media to share news and their views on a topic. To analyze this outsized web information, new analytical techniques are required which automatically portrays the data open on the Web. Most of us are more comfortable in expressing our viewpoints and outlooks in Mother tongue. Sentiments of the social users on various topics expressed in their own mother tongue leads to the necessity of mining the sentiments in various dialects. In fact, some data do not have an effect on the classification result even removing them and some carries similar meanings, therefore a pre-processing phase has to accomplish and thus the dataset can be more precise. In this paper, the authors are focusing on pre-processing the words given by the user through their reviews in the social networking sites expressed in Malayalam language. The authors calculated the reduction in word count after performing the preprocessing processes and the experiments shows that more than 20% of word count reduction occurred.

Opinion Mining, POS Tagging, Stemming, Stopword Removal, Malayalam

[1] Shastri, G., “Kannada morphological analyser and generator using trie”,. IJCSNS, 11(1), 112, 2011
[2] Ramanathan, A., & Rao, D. D., “A lightweight stemmer for Hindi”, In the Proceedings of EACL, 2003
[3] Gagandeep Kaur, Kamaldeep Kaur, “Sentiment Detection from Punjabi Text using Support Vector Machine”, International Journal of Scientific Research in Computer Science and Engineering, 5(6), 39-46., 2017
[4] Islam, M., Uddin, M., & Khan, M., “A light weight stemmer for Bengali and its Use in spelling Checker”, 2007.
[5] Akram, Q. U. A., Naseer, A., & Hussain, S. “Assas-Band, an affix-exception-list based Urdu stemmer”, In Proceedings of the 7th workshop on Asian language resources (pp. 40-46). Association for Computational Linguistics, 2009
[6] Dutta, P. K., “An Online Semi Automated Part of Speech Tagging Technique Applied To Assamese” (Doctoral dissertation), 2013.
[7] Kasthuri, M., & Kumar, S. B. R., “An improved rule based iterative affix stripping stemmer for Tamil language using K-mean clustering”, International Journal of Computer Applications, 94(13), 2014
[8] Prajitha, U., Sreejith, C., & Raj, P. R., “LALITHA: A light weight Malayalam stemmer using suffix stripping method”, In Control Communication and Computing (ICCC), 2013 International Conference on (pp. 244-248). IEEE, 2013.
[9] Pragisha, K., & Reghuraj, P. C., “STHREE: Stemmer for Malayalam using three pass algorithm”, In Control Communication and Computing (ICCC), 2013 International Conference on (pp. 149-152). IEEE, 2013.
[10] Jayan, J. P., Rajeev, R. R., & Sherly, E.. “A hybrid statistical approach for named entity recognition for malayalam language”. In Proceedings of the 11th Workshop on Asian Language Resources (pp. 58-63), 2013
[11] Nair, D. S., Jayan, J. P., & Sherly, E., “SentiMa-sentiment extraction for Malayalam”, In Advances in Computing, Communications and Informatics (ICACCI, 2014 International Conference on (pp. 1719-1723). IEEE, 2014.
[12] K, Manju & Peter S, David & Mary idicula, Sumam, “An Extractive Multi-document Summarization System for Malayalam News Documents”. 10.4108/eai.27-2-2017.152340.
[13] Renjith, S. R., & Sony, P, “An automatic text summarization for Malayalam using sentence extraction”. In Proceedings of 27th IRF International Conference, 14th June, 2015
[14] Willett, P, “The Porter stemming algorithm: then and now. Program”, 40(3), 219-223, 2006