Comments Prediction Model on Emotional Analysis Based on Bayes Classification. (June 2020)

• Record Type: Journal Article
• Authors: Chen, Xuegang; Duan, Sheng; Wang, Luda
• Is Part Of: Journal of physics. Volume 1575(2020)
• Publication Date: 2020-06
• Subjects: Physics -- Congresses; 530.5
• DOI: 10.1088/1742-6596/1575/1/012020
• Languages: English
• ISSNs: 1742-6588

Abstract

Abstract: The comments of e-commerce platform are the information feedback of users on the purchase of goods, which shows the concerns and emotional tendencies of the commodity. The research has important research value for enterprises. In this paper, we constructed the analysis model of e-commerce comments. Firstly, reptile obtained data to segment word segmentation, and then use the characteristics of the initial selection model to review data and transfer matrix conversion, using Bayes probability model to prediction work, finally through the prediction error to select the optimal characteristics of the model. Through the empirical study of the commentary data of BOE, the results show the method is effective, and has better performance and higher classification accuracy.