Paper: A Topic Model for Building Fine-grained Domain-specific Emotion Lexicon

ACL ID P14-2069
Title A Topic Model for Building Fine-grained Domain-specific Emotion Lexicon
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2014
Authors

Emotion lexicons play a crucial role in sen- timent analysis and opinion mining. In this paper, we propose a novel Emotion-aware LDA (EaLDA) model to build a domain- specific lexicon for predefined emotions that include anger, disgust, fear, joy, sad- ness, surprise. The model uses a mini- mal set of domain-independent seed words as prior knowledge to discover a domain- specific lexicon, learning a fine-grained emotion lexicon much richer and adap- tive to a specific domain. By comprehen- sive experiments, we show that our model can generate a high-quality fine-grained domain-specific emotion lexicon.