成果速递：硕士生李文龙提出考虑员工竞争状态的众包任务推荐算法

Title:Incorporating worker rivalry into task recommendations on crowdsourcing platforms: A novel framework for boosting participation and efficiency

Authors: Hefu Liu, Wenlong Li, Meng Chen, Juntao Wu; 

Journal:Information Processing & Management; 

URL: https://doi.org/10.1016/j.ipm.2025.104310

abstract: 

Crowdsourcing platforms have demonstrated significant advantages in addressing complex business and societal challenges. However, their task recommendation systems face dual challenges stemming from information overload and inadequate modeling of competitive relationships. While existing studies primarily utilize collaborative filtering and content-based approaches for task recommendation, these methods typically overlook the systematic impact of dynamic rivalry among workers in open crowdsourcing environments. To address this gap, we propose the Crowdsourcing Task Recommendation model with Competitive Relationships among Workers (CTRCRW), integrating a three-dimensional rivalry modeling mechanism (rivalry-similarity, repeated competition, and evenly matched competition) with deep learning techniques. Specifically, CTRCRW develops a multi-dimensional rivalry quantification approach and introduces a Rivalry Attention Module (RAM), leveraging graph neural networks combined with cosine similarity weights and a learnable gating mechanism to capture explicit competitive behaviors and implicit psychological motivations. Experiments on real-world datasets confirm that CTRCRW significantly improves recommendation accuracy and competitive rationality, effectively reducing workers’ search costs. This study contributes to theory and methodology for relationship-driven recommendations in crowdsourcing, providing generalized insights for resource allocation in complex interactive environments.