Research Area:  Machine Learning

Abstract:

A recommendation system is an integral part of any modern online shopping or social network platform. The product recommendation system as a typical example of the legacy recommendation systems suffers from two major drawbacks: recommendation redundancy and unpredictability concerning new items (cold start). These limitations take place because the legacy recommendation systems rely only on the users previous buying behavior to recommend new items. Incorporating the users social features, such as personality traits and topical interest, might help alleviate the cold start and remove recommendation redundancy. Therefore, in this article, we propose Meta-Interest, a personality-aware product recommendation system based on user interest mining and metapath discovery. Meta-Interest predicts the users interest and the items associated with these interests, even if the users history does not contain these items or similar ones. This is done by analyzing the users topical interests and, eventually, recommending the items associated with the users interest. The proposed system is personality-aware from two aspects; it incorporates the users personality traits to predict his/her topics of interest and to match the users personality facets with the associated items. The proposed system was compared against recent recommendation methods, such as deep-learning-based recommendation system and session-based recommendation systems. Experimental results show that the proposed method can increase the precision and recall of the recommendation system, especially in cold-start settings.

Keywords:  
recommendation system
redundancy
unpredictability
social feature
mining
metapath

Author(s) Name:  Sahraoui Dhelim, Huansheng Ning, Nyothiri Aung, Runhe Huang, Jianhua Ma

Publisher name:  IEEE

DOI:  https://doi.org/10.1109/TCSS.2020.3037040

Volume Information:  Volume 8

Paper Link:   https://ieeexplore.ieee.org/abstract/document/9269396