Usefulness and Diminishing Returns: Evaluating Social Information in Recommender Systems

Social recommendation, which leverages users' social information to predict users' preferences, is a popular branch of recommender systems. Many existing studies have attempted to advance the performance of collaborative filtering methods by leveraging the user-user matrix to enhance user embedding learning with user's social connections. While the existing social recommender systems have demonstrated good performance in various recommendation tasks, the extent of social information usefulness in recommender systems remains unclear. This paper addresses the research gap by designing experiments to answer three research questions: (i) How useful is social information in varying user-item data sparsity? (ii) How much social information do the existing social recommendation models use? (iii) How valuable is social information for cold-start situations? Working towards answering the research questions, we introduce evaluation metrics to estimate the utilization of social information in the existing social recommendation models. We conducted experiments on three publicly available social recommendation datasets, and our results showed that there are diminishing returns when applying social information in recommender systems.

• Publication year

  2025

• Venue

  International Conference on Information and Knowledge Management

• Publication date

  2025-11-10

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1145/3746252.3761168
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Hierarchical Denoising for Robust Social Recommendation

  2025cited by this paper
• A self-supervised graph-learning method for reliable-relation identification in social recommendation

  2025cited by this paper
• Hu-Fu: efficient and secure spatial queries over data federation

  2025cited by this paper
• Graph Attention Network with High-Order Neighbor Information Propagation for Social Recommendation

  2024cited by this paper
• Self-Supervised Denoising through Independent Cascade Graph Augmentation for Robust Social Recommendation

  2024cited by this paper
• MADM: A Model-agnostic Denoising Module for Graph-based Social Recommendation

  2024cited by this paper
• Self-Supervised Multi-Channel Hypergraph Convolutional Network for Social Recommendation

  2021influential reference
• Dual Side Deep Context-aware Modulation for Social Recommendation

  2021cited by this paper
• Social Recommendation with Self-Supervised Metagraph Informax Network

  2021cited by this paper
• Social Boosted Recommendation With Folded Bipartite Network Embedding

  2020cited by this paper
• Dual Graph Attention Networks for Deep Latent Representation of Multifaceted Social Effects in Recommender Systems

  2019cited by this paper
• A Neural Influence Diffusion Model for Social Recommendation

  2019cited by this paper
• Modeling User Exposure with Explicit and Implicit Social Relations for Recommendation

  2019cited by this paper
• Graph Neural Networks for Social Recommendation

  2019influential reference
• Facial Expression Analysis under Partial Occlusion

  2018cited by this paper
• Deep Modeling of Social Relations for Recommendation

  2018cited by this paper
• Collaborative Filtering with Social Exposure: A Modular Approach to Social Recommendation

  2017cited by this paper
• Neural Collaborative Filtering

  2017cited by this paper
• Social Collaborative Filtering by Trust

  2017cited by this paper
• Item Silk Road: Recommending Items from Information Domains to Social Users

  2017cited by this paper
• Fast Matrix Factorization for Online Recommendation with Implicit Feedback

  2016cited by this paper
• TrustSVD: Collaborative Filtering with Both the Explicit and Implicit Influence of User Trust and of Item Ratings

  2015cited by this paper
• Dropout: a simple way to prevent neural networks from overfitting

  2014cited by this paper
• Leveraging Social Connections to Improve Personalized Ranking for Collaborative Filtering

  2014cited by this paper
• mTrust: discerning multi-faceted trust in a connected world

  2012cited by this paper
• A 61-million-person experiment in social influence and political mobilization

  2012cited by this paper
• eTrust: understanding trust evolution in an online world

  2012cited by this paper
• Second workshop on information heterogeneity and fusion in recommender systems (HetRec2011)

  2011cited by this paper
• Recommender systems with social regularization

  2011cited by this paper
• A matrix factorization technique with trust propagation for recommendation in social networks

  2010influential reference
• Influence and correlation in social networks

  2008cited by this paper
• SoRec: social recommendation using probabilistic matrix factorization

  2008cited by this paper
• Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence A Novel Bayesian Similarity Measure for Recommender Systems

  year unknowncited by this paper

• No citing papers are available for this paper.