Emotion Detection with Neural Personal Discrimination

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, pages 5499–5507, Hong Kong, China, November 3–7, 2019. c⃝2019 Association for Computational Linguistics 5499 Emotion Detection with Neural Personal Discrimination Xiabing Zhou1, Zhongqing Wang1∗, Shoushan Li1, Guodong Zhou1, Min Zhang1 1School of Computer Scienceand Technology, Soochow University, China wangzq.antony@gmail.com, {zhouxiabing, lishoushan, gdzhou, minzhang}@suda.edu.cn Abstract There have been a recent line of works to auto- matically predict the emotions of posts in so- cial media. Existing approaches consider the posts individually and predict their emotion- s independently. Different from previous re- searches, we explore the dependence among relevant posts via the authors’ backgrounds, since the authors with similar backgrounds, e.g., gender, location, tend to express similar emotions. However, such personal attributes are not easy to obtain in most social media websites, and it is hard to capture attributes- aware words to connect similar people. Ac- cordingly, we propose a Neural Personal Dis- crimination (NPD) approach to address above challenges by determining personal attributes from posts, and connecting relevant posts with similar attributes to jointly learn their emo- tions. In particular, we employ adversarial discriminators to determine the personal at- tributes, with attention mechanisms to aggre- gate attributes-aware words. In this way, social correlationship among different posts can be better addressed. Experimental results show the usefulness of personal attributes, and the effectiveness of our proposed NPD approach in capturing such personal attributes with sig- nificant gains over the state-of-the-art models. 1 Introduction The advent of social media and its prosperity en- able the creation of massive online user-generated content including opinions and product reviews. Analyzing such user-generated contents allows to detect the users’ emotional states, which are useful for various downstream applications. In the literature, there are a large number of works on emotion detection (Roberts et al., 2012; Abdul-Mageed and Ungar, 2017; Gupta et al., 2017), both discrete and neural models have been ∗ corresponding auther used to predict the emotions of posts in social me- dia. For example, Roberts et al. (2012) used a series of binary SVM classifiers to detect the e- motion of a post, while Gupta et al. (2017) used sentiment based semantic embedding and a LST- M model to learn the representation of a post for emotion detection. Different from previous researches, which con- sider each post individually, we think that post- s in social media are much correlated by the au- thors’ backgrounds. Motivated by the principle of homophily (Lazarsfeld et al., 1954), the idea that similarity and connection tend to co-occur, or “birds of a feather flock together”, suggests that users, connected by mutual personal backgrounds, may hold similar opinions toward a post (Thelwal- l, 2010). In the literature, the personal attributes, such as gender, location, age, have been proved useful in personal background construction (Li et al., 2016): people with different attributes tend to express their emotions through different ways. For example, the happiness emotion in [E1] is expressed through some …

Content truncated to 500 words