Aspect-level sentiment capsule network for micro-video click-through rate prediction

• Published in: World wide web (Bussum) 2021-07, Vol.24 (4), p.1045-1064
• Main Authors: Han, Yuqiang, Gu, Pan, Gao, Wei, Xu, Guandong, Wu, Jian
• Format: Article
• Language: English
• Subjects: Algorithms; Computer Science; Database Management; Datasets; Feature extraction; Feedback; Information Systems Applications (incl.Internet); Negative feedback; Operating Systems; Positive feedback; Preferences; Recommender systems; Special Issue on Web Intelligence =Artificial Intelligence in the Connected World; User behavior; User generated content; Video; World Wide Web
• ISSN: 1386-145X; 1573-1413
• DOI: 10.1007/s11280-020-00858-z

Micro-videos, a new form of videos that are constrained in duration, gain significant popularity in recent years. The volume and rate of online micro-videos urgently calls for effective recommendation algorithms to help users find their interested ones. Although some previous works have investigated how to model users’ historical behaviors to predict the click-through rate of micro-videos, they are generally based on positive feedback only but overlook the negative which can help understand user preference at a finer granularity. The positive and negative feedback jointly imply the user’s different sentiments on different aspects, where each aspect is one component of a micro-video such as video_scene and video_subject . To this end, we propose an a spect-level s entiment cap sule network( ASCap ) for micro-video click-through rate prediction by aggregating both positive and negative feedback, with an attempt to make the prediction more explainable. More specifically, an aspect-specific gating mechanism is firstly utilized to extract the aspect-level features from the target micro-video and the user’s positive and negative feedback. Then, in the following sentiment capsule network, the aspect-level features of the target micro-video are paired with those of positive and negative feedback respectively to identify their sentiments and form the sentiment capsules. Finally, the prediction layer is employed to calculate the overall click probability based on the sentiment capsules. Experimental results on two real-world micro-video datasets demonstrate that the proposed method significantly outperforms the state-of-the-art methods.