SentiFul: Generating a reliable lexicon for sentiment analysis

Alena Neviarouskaya*, Helmut Prendinger, Mitsuru Ishizuka

*この研究の対応する著者

研究成果: Conference contribution

46 被引用数 (Scopus)

抄録

The main drawback of any lexicon-based sentiment analysis system is the lack of scalability. Thus, in this paper, we will describe methods to automatically generate and score a new sentiment lexicon, called SentiFul, and expand it through direct synonymy relations and morphologic modifications with known lexical units. We propose to distinguish four types of affixes (used to derive new words) depending on the role they play with regard to sentiment features: propagating, reversing, intensifying, and weakening.

本文言語English
ホスト出版物のタイトルProceedings - 2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII 2009
DOI
出版ステータスPublished - 2009
外部発表はい
イベント2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII 2009 - Amsterdam
継続期間: 2009 9 102009 9 12

Other

Other2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII 2009
CityAmsterdam
Period09/9/1009/9/12

ASJC Scopus subject areas

  • 人工知能
  • コンピュータ ビジョンおよびパターン認識
  • 人間とコンピュータの相互作用
  • ソフトウェア

フィンガープリント

「SentiFul: Generating a reliable lexicon for sentiment analysis」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル