Back close

Sentiment analysis of tamil movie reviews via feature frequency count

Publication Type : Journal Article

Thematic Areas : Center for Computational Engineering and Networking (CEN)

Publisher : International Journal of Applied Engineering Research

Source : International Journal of Applied Engineering Research

Campus : Coimbatore

School : Department of Electronics and Communication Engineering, School of Engineering

Center : Computational Engineering and Networking

Year : 2015

Abstract : The digital community paves the way for huge volume of opinion rich reviews from forums, blogs, discus-sions and so on. In divergence with common text classification approach, word count in the document are used as features. Metalevel features are taken from hand labeled Tamil movie reviews. Once the feature is extracted, they are used as input for supervised machine learning algorithms for further classification. Generally the frequency of occurrence of keyword is more suitable feature in overall sentiment analysis and not necessarily indicated by repeated use of keywords. Experimental results point out the proposed method in this paper which shows considerable accuracy in detecting sentimental information in Tamil. Accuracy of about 65. © Research India Publications.

Admissions Apply Now