Event-Driven Emotion Cause Extraction with Corpus Construction

Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 1639–1649, Austin, Texas, November 1-5, 2016. c⃝2016 Association for Computational Linguistics Event-Driven Emotion Cause Extraction with Corpus Construction Lin Gui1, Dongyin Wu1, Ruifeng Xu1,2∗, Qin Lu3 and Yu Zhou1 1. School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen Graduate School, Shenzhen, China 2. Guangdong Provincial Engineering Technology Research Center for Data Science 3. Department of Computing, the Hong Kong Polytechnic University, Hong Kong guilin.nlp@gmail.com;wudongyinhit@gmail.com;xuruifeng@hitsz.edu.cn; csluqin@comp.polyu.edu.hk;zhouyu.nlp@gmail.com Abstract In this paper, we present our work in emo- tion cause extraction. Since there is no open dataset available, the lack of annotated re- sources has limited the research in this area. Thus, we first present a dataset we built using SINA city news. The annotation is based on the scheme of the W3C Emotion Markup Lan- guage. Second, we propose a 7-tuple defini- tion to describe emotion cause events. Based on this general definition, we propose a new event-driven emotion cause extraction method using multi-kernel SVMs where a syntactical tree based approach is used to represent events in text. A convolution kernel based multi- kernel SVM are used to extract emotion caus- es. Because traditional convolution kernels do not use lexical information at the terminal n- odes of syntactic trees, we modify the kernel function with a synonym based improvemen- t. Even with very limited training data, we can still extract sufficient features for the task. Evaluations show that our approach achieves 11.6% higher F-measure compared to refer- enced methods. The contributions of our work include resource construction, concept defini- tion and algorithm development. 1 Introduction With the rapid growth of Internet, people can easily share experiences and emotions through this power- ful medium anywhere and anytime. How to analyze the emotions of individuals through their writings becomes a new challenge for NLP. In recent years, s- ∗corresponding author tudies in emotion analysis focus on emotion classifi- cation including detection of emotions expressed by writers of text (Gao et al., 2013) as well as predic- tion of reader emotions (Chang et al., 2015). There are also some information extraction tasks in emo- tion analysis, such as extracting the feeler of emo- tion (Das and Bandyopadhyay, 2010). However, these methods need to observe emotion linked ex- pressions. Sometimes, however, we care more about the stimuli, or the cause of an emotion. For instance, manufacturers want to know why people love, or hate a certain product. The White House may al- so prefer to know the cause of the emotional text “Let us hit the streets” rather than the distribution of different emotions. There are three main challenges in the study of e- motion cause extraction. The first is that, up to now, there is no open dataset available for emotion cause extraction. This may explain why there are only few studies on emotion causes. The second is that, there is no formal definition about event in emotion cause extraction even though some researches claim that they extract events …

Content truncated to 500 words