A semantic Vector Space Model approach for sentiment analysis

Abstract: A response to growing availability of formal, informal, opinionated texts like film review, product review etc., an area of Sentiment Analysis has begun which raised the question that “What people think about a particular topic?”. This paper present a semantic VSM (vector space model) which capture sentiment and semantic similarities among words which we are using on the micro blogging sites. Semantic vector space model-based approaches used for a large amount of information could be obtained by analysis of generated word text by the humane on social networking sites. The purpose of this research is the construction and estimation of algorithms for the analysis and the classification of large amount of humane generated text data, will focus on sentiment analysis on twitter or similar social community environments.

Keywords: Machine learning concept, Classification, VSM Clustering, WEKA2.6.