BOUNCE: Sentiment classification in Twitter using rich feature sets

Nadin Kökciyan, Arda Celebi, Arzucan Ozgür, Suzan Usküdarli

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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.
Original languageEnglish
Title of host publicationSecond Joint Conference on Lexical and Computational Semantics (* SEM)
Subtitle of host publicationVolume 2: Proceedings of the Seventh International Workshopon Semantic Evaluation (SemEval 2013)
PublisherAssociation for Computational Linguistics (ACL)
Pages554-561
Number of pages8
Volume2
ISBN (Print)978-1-937284-49-7
Publication statusPublished - 15 Jun 2013
EventSeventh International Workshop on Semantic Evaluation 2013 - Atlanta, United States
Duration: 14 Jun 201315 Jun 2013

Conference

ConferenceSeventh International Workshop on Semantic Evaluation 2013
Abbreviated titleSemEval 2013
CountryUnited States
CityAtlanta
Period14/06/1315/06/13

Cite this