山西大学学报（自然科学版）2025，Vol.48Issue(4)：741-751,11.DOI:10.13451/j.sxu.ns.2025027
融合社交影响扩散的长尾物品推荐模型
Long-tail Recommendation Method Incorporating Social Influence Diffusion Model
摘要
Abstract
In recommendation systems,the long-tail distribution of user ratings and interaction frequencies poses challenges for ex-tracting the features of long-tail items.Existing methods either overly focus on tail items while neglecting their connections with head items or disregard the influence of social networks on user preferences,thereby impacting recommendation performance.To ad-dress these issues,this paper proposes a novel long-tail recommendation model called LoSidi(Long-tail Recommendation Method Incorporating Social Influence Diffusion).Firstly,for each user,the model aggregates samples of social neighbors at various layers and integrates these with the popular items the user has interacted with to generate user interest embeddings.Secondly,the potential features of long-tail items are mined by calculating the similarity between long-tail items and the head items the user has interacted with.Finally,the LoSidi model establishes links between users and long-tail items,predicting scores and generating recommenda-tions for these items.Experimental results on widely-used datasets demonstrate that the proposed model significantly improves the novelty and diversity of users'recommendation lists.关键词
推荐系统/社会推荐/长尾问题/图神经网络Key words
recommender system/social recommendation/long tail problem/graph neural network分类
信息技术与安全科学引用本文复制引用
张槟淇,尉译心,王文剑..融合社交影响扩散的长尾物品推荐模型[J].山西大学学报（自然科学版）,2025,48(4):741-751,11.基金项目
国家自然科学基金(62076154) （62076154）
山西省科技重大专项计划"揭榜挂帅"项目(202101020101019) （202101020101019）
