Sentimental prediction model of personality based on CNN-LSTM in a social media environment

Issue title: Artificial Intelligence as a maturing and growing technology: An urgent need for intelligent systems

Guest editors: X. Yuan and M. Elhoseny

Article type: Research Article

Authors: Zhao, Jinghua^a | Lin, Jie^{b; *} | Liang, Shuang^a | Wang, Mengjiao^b

Affiliations: [a] School of Business, the University of Shanghai for Science and Technology, Shanghai, China | [b] School of Economics and Management, Tongji University, Shanghai, China

Correspondence: [*] Corresponding author. Jie Lin, School of Economics and Management, Tongji University, Shanghai, China. E-mail: [email protected].

Abstract: The paper first analyzes the correlation between text sentiment values and personality traits, proves that text sentiment can have a good support effect on user personality prediction, then on this basis, a method based on CNN-LSTM is proposed, which can be used to deeply analyze the sentiment analysis capability of the model, hoping to improve the precision of sentiment classification and lay a solid foundation for the next experiment. This experiment proves that the CNN-LSTM constructed in this paper can better predict the emotional tendency of the short text of microblog, has good generalization ability, and has higher precision than other methods.

Keywords: CNN-LSTM, sentiment annotation, social media, personality

DOI: 10.3233/JIFS-189348

Journal: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 2, pp. 3097-3106, 2021