Prefer2SD: A Human-in-the-Loop Approach to Balancing Similarity and Diversity in In-Game Friend Recommendations

2025-03-08

AI Summary

Online game friend recommendation faces the challenge of balancing similarity and diversity under dynamically evolving user preferences, hindering player retention and strong social tie formation. To address this, we propose a human-in-the-loop iterative recommendation framework that introduces a novel closed-loop mechanism integrating visual analytics, interactive control, and dynamic weight optimization—enabling domain experts to adjust the similarity-diversity trade-off in real time across distinct player cohorts. Our approach departs from conventional algorithm-only paradigms by embedding explainable, human-controllable intervention directly into the recommendation pipeline. Evaluated through a 12-participant controlled study, multi-case analysis, and expert interviews, our method achieves statistically significant improvements: +23.6% in recommendation quality (NDCG@5) and +31.2% in social connection strength (interaction rate) over baselines. This work establishes a new, interpretable, and controllable paradigm for dynamic social recommendation.

Technology Category

• Humans and AI: Game Design — Virtual Humans, NPCs and Autonomous Characters
• Data Mining & Knowledge Management: Recommender Systems
• Application Domains: Humanities & Computational Social Science

Application Category

• User Modeling, Personalization and Recommendation: Social recommender systems and personalization for the social Web
• Economics, Online Markets and Human Computation: Economics and fairness of platforms and recommendation systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

In-game friend recommendations significantly impact player retention and sustained engagement in online games. Balancing similarity and diversity in recommendations is crucial for fostering stronger social bonds across diverse player groups. However, automated recommendation systems struggle to achieve this balance, especially as player preferences evolve over time. To tackle this challenge, we introduce Prefer2SD (derived from Preference to Similarity and Diversity), an iterative, human-in-the-loop approach designed to optimize the similarity-diversity (SD) ratio in friend recommendations. Developed in collaboration with a local game company, Prefer2D leverages a visual analytics system to help experts explore, analyze, and adjust friend recommendations dynamically, incorporating players' shifting preferences. The system employs interactive visualizations that enable experts to fine-tune the balance between similarity and diversity for distinct player groups. We demonstrate the efficacy of Prefer2SD through a within-subjects study (N=12), a case study, and expert interviews, showcasing its ability to enhance in-game friend recommendations and offering insights for the broader field of personalized recommendation systems.

Problem

• Balancing similarity and diversity in in-game friend recommendations.
• Addressing evolving player preferences in automated recommendation systems.
• Enhancing social bonds across diverse player groups through optimized recommendations.

Innovation

• Human-in-the-loop approach for friend recommendations
• Visual analytics system for dynamic recommendation adjustment
• Interactive visualizations to balance similarity and diversity