作者: Aniruddha Ghosh , Guofu Li , Tony Veale , Paolo Rosso , Ekaterina Shutova
DOI: 10.18653/V1/S15-2080
关键词:
摘要: This report summarizes the objectives and evaluation of SemEval 2015 task on sentiment analysis figurative language Twitter (Task 11). is first wholly dedicated to analyzing Twitter. Specifically, three broad classes are considered: irony, sarcasm metaphor. Gold standard sets 8000 training tweets 4000 test were annotated using workers crowdsourcing platform CrowdFlower. Participating systems required provide a fine-grained score an 11-point scale (-5 +5, including 0 for neutral intent) each tweet, evaluated against gold both Cosinesimilarity Mean-Squared-Error measure.