In this chapter, we present our work in emotion cause extraction. Since there is no open dataset available, the lack of annotated resources has limited the research in this area. Thus, we first present an annotated dataset we built using SINA city news which follows the scheme of W3C Emotion Markup Language. We then present 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. Then, a convolution kernel and linear kernel based multi-kernel SVMs are used to extract emotion causes. Because traditional convolution kernels do not use lexical information as terminal nodes in syntactic trees are ignored, we modified the kernel function with a synonym based improvement. Even with a limited training set, we can still extract sufficient features for analysis. Evaluations show that our approach achieves 17% higher F-measure compared to other reported methods. The contributions of our work include both resources and algorithm development.
|Title of host publication||Social Media Content Analysis|
|Subtitle of host publication||Natural Language Processing and Beyond|
|Publisher||World Scientific Publishing Co. Pte Ltd|
|Number of pages||16|
|Publication status||Published - 1 Jan 2017|
ASJC Scopus subject areas
- Computer Science(all)