Research on Recommendation Strategies Integrating Emotional Tendency and User Influences
Jing Chen, Liuqian Duan, Hong Zhang · 2020
At present, the topic model based on LDA as an information recommendation method has the defect of neglecting the emotional information in social platform. Therefore, a microblog user recommendation strategy I-TES (influence topic emotionality similarity model) is proposed which combines emotional orientation with user influence model in this paper. Firstly, the user's theme distribution and emotional tendency is obtained based on JST model, the JS distance is used to calculate the similarity of user's theme probability distribution, and the two is combined to get the user's interest similarity score. Secondly, the user's influence measurement indicators are summarized into microblog influence, user's activity and fan's influence, and the weights of the three indicators are calculated according to AHP(analytic hierarchy process). Finally, the combination of the two is used to obtain the final score as the recommendation result. The strategy is tested on Sina Weibo user data set, and the experiment shows that this strategy has higher recommendation accuracy than the traditional recommendation method.