SEMANTIC EMOTION-TOPIC MODEL IN SOCIAL MEDIA ENVIRONMENT

Authors

  • RUIRONG XUE School of Computer Engineering and Science, Shanghai University, China
  • SUBIN HUANG School of Computer Engineering and Science, Shanghai University, China Anhui Polytechnic University, China
  • XIANGFENG LUO Shanghai Institute for Advanced Communication and Data Science, School of Computer Engineering and Science, Shanghai University, China
  • DANDAN JIANG School of Computer Engineering and Science, Shanghai University, China
  • YIKE GUO School of Computer Engineering and Science, Shanghai University, China Department of Computing, Imperial College London, British
  • YAN PENG School of Mechatronic Engineering and Automation, Shanghai University, China

Keywords:

Social emotion mining, Semantic discovery, Social emotion classification, Topic Model, Semantic Emotion Topic Model

Abstract

With the booming of social media users, more and more short texts with emotion labels appear in social media environment, which contain users' rich emotions and opinions about social events or enterprise products. Social emotion mining on social media corpus can help government or enterprise make their decisions. Emotion mining models involve statistical-based and graph-based approaches. Among them, the former approaches are more popular, e.g. Latent Dirichlet Allocation (LDA)-based Emotion Topic Model. However, they are suffering from bad retrieval performance, such as the bad accuracy and the poor interpretability, due to them only considering the bag-of-words or the emotion labels in social media media environment. In this paper, we propose a LDA-based Semantic Emotion-Topic Model (SETM) combining emotion labels and inter-word relations to enhance the retrieval performance in social media media environment. The performance influence of four factors on SETM are considered, i.e., association relations, computing time, topic number and semantic interpretability. Experimental results show that the accuracy of our proposed model is 0.750, compared with 0.606, 0.663 and 0.680 of Emotion Topic Model (ETM), Multilabel Supervised Topic Model (MSTM) and Sentiment Latent Topic Model (SLTM) respectively. Besides, the computing time of our model is reduced by 87.81% through limiting word frequency, and its accuracy is 0.703, compared with 0.501, 0.648 and 0.642 of the above baseline methods. Thus, the proposed model has broad prospects in social media media environment.

Downloads

Download data is not yet available.

Downloads

Issue

Section

Articles