Group Recommendation Algorithm Incorporating User Personality and Movie Attractiveness

Traditional group recommendation algorithms ignore the influence of user personality traits and item attributes in preference modelling. To address this issue, this paper proposes a group recommendation algorithm that incorporates user personality and movie attractiveness. Firstly, a hybrid similarity based on ratings and personality is utilized for group division. Secondly, decision weights are computed by integrating user trustworthiness, professionalism, and personality factors, achieving the aggregation of preferences. Lastly, movie attractiveness is determined by the historical ratings data of each movie, and is weighted and combined with group preferences to derive the final recommendation list. Experimental results on real datasets show that the results of the proposed algorithm outperform the optimal results in the selected baseline algorithm. The efficacy of the proposed algorithm is validated.