Lyric-based Sentiment Polarity Classification of Thai Songs

Simple item page
dc.contributor.authorSrinilta, Chutimet
dc.contributor.authorSunhem, Wisuwat
dc.contributor.authorTungjitnob, Suchat
dc.contributor.authorThasanthiah, Saruta
dc.contributor.authorVatathanavaro, Supawit
dc.date.accessioned2026-08-06T10:14:58Z
dc.date.available2026-08-06T10:14:58Z
dc.date.issued2017-01-01
dc.description.abstractSong sentiment polarity provides outlook of a song. It can be used in automatic music recommendation system. Sentiment polarity classification based solely on lyrics is challenging. It involves understanding linguistic knowledge, song characteristics and emotional interpretation of words. Since lyric is in a form of text. Techniques used in text mining, text sentiment analysis and music mood classification are studied and used together in our proposed model. Two types of classifier are proposed—lexicon-based classifier and machine learning-based classifier. N-gram model is used in feature set generation. Features are filtered by Information Gain. Feature weighting scheme is employed. We create a sentiment lexicon from Thai song corpus. Full lyric and certain parts of lyric are chosen for datasets. We evaluate our models under various environments. The best average accuracy achieved is 68%.
dc.identifier.citationLecture Notes in Engineering and Computer Science, 2227, 364-368, 2017
dc.identifier.issn20780958
dc.identifier.other2-s2.0-85042173224
dc.identifier.urihttps://dspace.kmitl.ac.th/handle/123456789/7183
dc.sourceLecture Notes in Engineering and Computer Science
dc.subjectLyric
dc.subjectMusic mood classification
dc.subjectNeural network
dc.subjectSentiment polarity analysis
dc.subjectThai songs
dc.titleLyric-based Sentiment Polarity Classification of Thai Songs
dc.typeConference Paper

Files

Collections

Research