Two-Step Model for Sentiment Lexicon Extraction from Twitter Streams

In this study we explore a novel technique for creation of polarity lexicons from the Twitter streams in Russian and English. With this aim we make preliminary filtering of subjective tweets using general domain-independent lexicons in each language. Then the subjective tweets are used for extraction of domain-specific sentiment words. Relying on co-occurrence statistics of extracted words in a large unlabeled Twitter collections we utilize the Markov random field framework for the word polarity classification. To evaluate the quality of the obtained sentiment lexicons they are used for tweet sentiment classification and outperformed previous results.