SENTIMENT ANALYSIS OF MARATHI LANGUAGE

Authors

  • Mrs. Sujata Prashant Deshmukh Mrs. Nilima Patil Department of Information Technology, Fr. Conceicao Rodrigues College o f Engineering,

Keywords:

Abstract

Sentiment analysis offers many benefits and opportunities from business, government and consumer perspective in this digital data explosive age. According to Google, in partnership with KPMG India report (April-2017),  titled 'Indian Languages - Defining India's Internet',  currently India today has 234 million Indian Language users who are online, compared to 175 million English web users and expected 536 million Indians to use regional languages while online by 2021 [1]. However Marathi users are expected to make significant contribution to define India Internet volume. By considering aspects of Marathi language and benefits of sentiment analysis, this paper presents a approach to overcome the barriers and difficulties being faced for analyzing text in Marathi language. The proposed system detects hidden sentiments in text of Marathi language. The system uses sentiment analysis methodology in order to achieve desired functionality. In this system, a corpus based approach is proposed, i.e the creation of a diverse up to date corpus of Marathi keywords, along with their individual polarities, with respect to the WordNet, which is consider as a corpus. The algorithm is used to calculate the cumulative polarity of the text and ranhk the sentence as positive, negative or neutral on a set scale standard.

e scientific discovery could have made.This word shows the importance of Vedic period and Ancient Indian Education.

 

used for solving a specific problem, answering a question, introducing a new subject, raising interest, and surveying knowledge and attitudes. The present paper aims to tell about brainstorming and learning. 

 

References

Report 'Indian Languages - Defining India's Internet', A study by KPMG in India and Google April 2017

Sentiment analysis, https://en.wikipedia.org/wiki/Sentiment_analysis, accessed in Aug. 2016.

Alessia D’Andrea, Fernando Ferri, Patrizia Grifoni, “Approaches, Tools and Applications for Sentiment Analysis Implementation”, International Journal of Computer Applications (0975 – 8887) Volume 125 – No.3, September 2015

H. K. Walaa Medhat, Ahmed Hassan, “Sentiment analysis algorithms and applications: A survey,” Ain Shams Engineering Journal (2014) 5, 1093–111, 2014.

S. S. Namrata Godbole, Manjunath Srinivasaiah, “Large-scale sentiment analysis for news and blogs,” ICWSM’2007, Boulder, Colorado,USA, 2007.

G. Q. Soha Ahmed, Michael Pasquier, “Key issues in conducting sentiment analysis on Arabic social media text,” IIT`13, 2013.

D. J. Hatem Ghorben, “Sentiment analysis of french movie reviews,” Proceedings of the 7th Atlantic Web Intelligence Conference, AWIC 2011, pg. no. 19-28, 2011.

M. K. Yakshi sharma, Veenu mangat, “A practical approach to sentiment analysis of Hindi tweets,” 1st International Conference on Next Generation Computing Technologies (NGCT), pg. no. 677-680, 2015.

Denecke, Kerstin. "Using sentiwordnet for multilingual sentiment analysis." Data Engineering Workshop, 2008. ICDEW 2008. IEEE 24th International Conference on. IEEE, 2008.

Downloads

Published

2017-06-30

Issue

Vol. 6 No. 7 (2017): JUNE 2017

Section

Articles

License

Copyright Notice

Submission of an article implies that the work described has not been published previously (except in the form of an abstract or as part of a published lecture or academic thesis), that it is not under consideration for publication elsewhere, that its publication is approved by all authors and tacitly or explicitly by the responsible authorities where the work was carried out, and that, if accepted, will not be published elsewhere in the same form, in English or in any other language, without the written consent of the Publisher. The Editors reserve the right to edit or otherwise alter all contributions, but authors will receive proofs for approval before publication.

Copyrights for articles published in World Scholars journals are retained by the authors, with first publication rights granted to the journal. The journal/publisher is not responsible for subsequent uses of the work. It is the author's responsibility to bring an infringement action if so desired by the author.