作者: Cynthia Van Hee , Marjan Van de Kauter , Orphee De Clercq , Els Lefever , Veronique Hoste
DOI: 10.3115/V1/S14-2070
关键词:
摘要: This paper describes our contribution to the SemEval-2014 Task 9 on sentiment analysis in Twitter. We participated both strands of task, viz. classification at message-level (subtask B), and polarity disambiguation particular text spans within a message A). Our experiments with variety lexical syntactic features show that systems benefit from rich feature sets for user-generated content. ranked ninth among 27 sixteenth 50 submissions task A B respectively.