Lexicon generation for emotion detection from text.

Bandhakavi, Anil; Wiratunga, Nirmalie; Massie, Stewart; Padmanabhan, Deepak

Abstract

General-purpose emotion lexicons (GPELs) that associate words with emotion categories remain a valuable resource for emotion detection. However, the static and formal nature of their vocabularies make them an inadequate resource for detecting emotions in domains that are inherently dynamic in nature. This calls for lexicons that are not only adaptive to the lexical variations in a domain but which also provide finer-grained quantitative estimates to accurately capture word-emotion associations. In this article, the authors demonstrate how to harness labeled emotion text (such as blogs and news headlines) and weakly labeled emotion text (such as tweets) to learn a word-emotion association lexicon by jointly modeling emotionality and neutrality of words using a generative unigram mixture model (UMM). Empirical evaluation confirms that UMM generated emotion language models (topics) have significantly lower perplexity compared to those from state-of-the-art generative models like supervised Latent Dirichlet Allocation (sLDA). Further emotion detection tasks involving word-emotion classification and document-emotion ranking confirm that the UMM lexicon significantly out performs GPELs and also state-of-the-art domain specific lexicons.

Citation

BANDHAKAVI, A., WIRATUNGA, N., MASSIE, S. and PADMANABHAN, D. 2017. Lexicon generation for emotion detection from text. IEEE intelligent systems [online], 32(1), pages 102-108. Available from: https://doi.org/10.1109/MIS.2017.22

• Journal Article Type: Article
• Acceptance Date: Feb 13, 2017
• Online Publication Date: Feb 13, 2017
• Publication Date: Feb 28, 2017
• Deposit Date: Feb 17, 2017
• Publicly Available Date: Feb 17, 2017
• Journal: IEEE intelligent systems
• Print ISSN: 1541-1672
• Electronic ISSN: 1941-1294
• Publisher: Institute of Electrical and Electronics Engineers (IEEE)
• Peer Reviewed: Peer Reviewed
• Volume: 32
• Issue: 1
• Pages: 102-108
• DOI: https://doi.org/10.1109/MIS.2017.22
• Keywords: Intelligent systems; Emotion detection; Domain specific lexicon; Mixture model; Word classification; Emotion ranking
• Public URL: http://hdl.handle.net/10059/2174
• Contract Date: Feb 17, 2017