Learning user sentiment orientation in social networks for sentiment analysis

Abstract

Sentiment analysis on social networks mines users’ opinions, emotions, and attitudes to derive useful insights into community opinions and can improve the sales strategies of e-commerce platforms. Existing sentiment analysis methods are primarily based on complex user social relations and text data. However, they only use social relations among users and ignore the interactions of user sentiment orientation. In this paper, we designed a novel USON model to learn user sentiment orientation in social networks that fuses the interaction of users and their opinions. We define the score of the user sentiment orientation according to the sentiment polarity distribution of the opinion datasets. Then, we rebuilt a user social network, which is an attribute network with scores of user sentiment orientation as node attributes and social relations as edges. Finally, we integrated user representations with opinion representations for sentiment analysis. Experimental results on Amazon and Yelp show that the performance of our proposed model is significantly higher than that of state-of-the-art methods.