BOUNCE: Sentiment Classification in Twitter using Rich Feature Sets
Nadin Kökciyan, Arda Çelebi, Arzucan Özgür, Suzan ÜsküdarlÄ · 2013
The widespread use of Twitter makes it very interesting to determine the opinions and the sentiments expressed by its users. The shortness of the length and the highly informal nature of tweets render it very difficult to automatically detect such information. This paper reports the results to a challenge, set forth by SemEval-2013 Task 2, to determine the positive, neutral, or negative sentiments of tweets. Two systems are explained: System A for determining the sentiment of a phrase within a tweet and System B for determining the sentiment of a tweet. Both approaches rely on rich feature sets, which are explained in detail. 1