Multi-label Text Classification Approach for Sentence Level News Emotion Analysis
Multiple emotions are often evoked in readers in response to text stimuli like news article. In this paper, we present a novel method for classifying news sentences into multiple emotion categories using Multi-Label K Nearest Neighbor classification technique. The emotion data consists of 1305 news sentences and the emotion classes considered are disgust, fear, happiness and sadness. Words and polarity of subject, verb and object of the sentences and semantic frames have been used as features. Experiments have been performed on feature comparison and feature selection.
KeywordsFeature Selection News Article Text Segment Word Feature Emotion Class
- 2.Strapparava, C., Mihalcea, R.: Semeval-2007 task 14: Affective text. In: Proceedings of the 4th International Workshop on the Semantic Evaluations (SemEval 2007), Prague, Czech Republic (June 2007)Google Scholar
- 3.Lin, K.H.Y., Yang, C., Chen, H.H.: Emotion classification of online news articles from the reader’s perspective. In: Web Intelligence, pp. 220–226 (2008)Google Scholar
- 4.Zhang, M., Zhou, Z.h.: Ml-knn: A lazy learning approach to multi-label learning. Pattern Recognition 40, 2007 (2007)Google Scholar