Abstract: Any modern online retail or social networking platform includes a recommendation mechanism. As an example of outdated recommendation systems, the product recommendation system has two key flaws: recom-mendation redundancy and unpredictability when it comes to new things (cold start). These limitations arise be-cause traditional recommendation systems rely solely on the user's previous purchasing activity to make new item recommendations. Incorporating the user's social characteristics, such as personality traits and topical inter-ests, could help ease the cold start and eliminate redundant recommendations. As a result, we provide Meta-Interest, a personality-aware product recommendation system based on user interest mining and metapath identi-fication, in this article. Even if the user's history does not contain these or similar items, Meta-Interest predicts the user's interest and the objects linked with these interests. This is accomplished by evaluating the user's subject interests and, as a result, proposing goods related to those interests. In two ways, the proposed system is personal-ity-aware: it uses the user's personality features to forecast his or her themes of interest and to link the user's per-sonality facets to the associated items. Recent recommendation methods, such as deep-learning-based recom-mendation systems and session-based recommendation systems, were compared to the suggested system. The proposed strategy can improve the precision and recall of the recommendation system, especially in cold-start circumstances, according to experimental data.
Big-five model, personality computing, product recommendation, recommendation system, social networks, so-cial computing, user interest mining, and user modelling are all terms that can be used to describe the Big-five model.

| DOI: 10.17148/IARJSET.2022.9653