Search

Sentiment analysis is a very active and nowadays highly addressed research area. One of the problem in sentiment analysis is text classification in terms of its attitude, especially in reviews or comments from social media. In general, this problem can be solved by two different approaches: machine learning methods and based on lexicons. Methods based on lexicons require properly prepared lexicons which usually are obtained manually from experts and it costs a lot in terms of time and resources. This paper aims at automatic lexicon creation for sentiment analysis. There are proposed the methods based on Loopy Belief Propagation that starting from small set of seed words with a priori known sentiment value propagates the sentiment to whole Wordnet.

The main goal of the paper is to present that word’s sentiment can be discovered from propagation through well-defined word networks such as Word–Net. Therefore a new method for propagation of sentiment from a given word seed - Micro-WNOp corpus over the word network (WordNet 3.0) has been proposed and evaluated. The experimental studies proved that WordNet has a great potential in sentiment propagation, even if types of links (e.g. hyponymy, heteronymy etc.) and semantic meaning of words are not taken into consideration.

The paper examines two approaches to sentiment analysis: lexicon-based vs. supervised learning in the domain of movie reviews. In evaluation, the methods were compared using a standard movie review test collection. The results show that lexicon-based approach is easily outperformed by classification approach.