作者: Amna Dridi , Mattia Atzeni , Diego Reforgiato Recupero
DOI: 10.1007/S13042-018-0805-X
关键词:
摘要: In this paper, a fine-grained supervised approach is proposed to identify bullish and bearish sentiments associated with companies stocks, by predicting real-valued score between − 1 + 1. We propose learned using several feature sets, consisting of lexical features, semantic features combination features. Our study reveals that most notably BabelNet synsets frames, can be successfully applied for Sentiment Analysis within the financial domain achieve better results. Moreover, comparative has been conducted our unsupervised approaches. The obtained experimental results show how outperforms others.