Contextual semantics for sentiment analysis of Twitter
详细信息 查看全文
- 作者：Hassan Saifa ; h.saif@open.ac.uk" class="auth_mail" title="E-mail the corresponding author ; Yulan Heb ; y.he@cantab.net" class="auth_mail" title="E-mail the corresponding author ; Miriam Fernandeza ; m.fernandez@open.ac.uk" class="auth_mail" title="E-mail the corresponding author ; Harith Alania ; h.alani@open.ac.uk" class="auth_mail" title="E-mail the corresponding author
- 关键词：Sentiment analysis ; Contextual semantics ; Twitter
- 刊名：Information Processing & Management
- 出版年：2016
- 出版时间：January 2016
- 年：2016
- 卷：52
- 期：1
- 页码：5-19
- 全文大小：1295 K
文摘
- •
We propose a semantic sentiment representation of words called SentiCircle.
- •
SentiCircle captures the contextual semantic of words from their co-occurrences.
- •
SentiCircle updates the sentiment of words based on their contextual semantics.
- •
SentiCircle can be used to perform entity- and tweet-level level sentiment analysis.