Paper: Lyric-based Song Sentiment Classification with Sentiment Vector Space Model

ACL ID P08-2034
Title Lyric-based Song Sentiment Classification with Sentiment Vector Space Model
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2008
Authors

Lyric-based song sentiment classification seeks to assign songs appropriate sentiment labels such as light-hearted and heavy-hearted. Four problems render vector space model (VSM)-based text classification approach in- effective: 1) Many words within song lyrics actually contribute little to sentiment; 2) Nouns and verbs used to express sentiment are ambiguous; 3) Negations and modifiers around the sentiment keywords make particu- lar contributions to sentiment; 4) Song lyric is usually very short. To address these problems, the sentiment vector space model (s-VSM) is proposed to represent song lyric document. The preliminary experiments prove that the s- VSM model outperforms the VSM model in the lyric-based song sentiment classification task.