4) Extending FrameNet for Sentiment Analysis

Resumo

Inglês:  We provide a contribution that points up the potential use of frame semantics and FrameNet in particular for sentiment analysis . We address several key problems incurrent sentiment analysis, which is characterized by shallow approaches, pragmatic focus, and ad-hoc creatiod of data sets and methods. We argue that progress towards deep analysis depends on a) enriching shallow representations with linguistically motivated, rich information, and b)focusing different branches of research and combining resources and work forces to join hands with related work in NLP. We propose SentiFrameNet, anextension to FrameNet, as a novel representation for sentiment analysis that is tailored to these aims.
KEYWORDS: sentiment analysis; FrameNet representation; scale structures