{"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","doi":"10.1016/j.ipm.2025.104310","DOIUrl":null,"url":null,"abstract":"<div><div>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.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"63 1","pages":"Article 104310"},"PeriodicalIF":7.4000,"publicationDate":"2025-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Information Processing & Management","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0306457325002511","RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0
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.
期刊介绍:
Information Processing and Management is dedicated to publishing cutting-edge original research at the convergence of computing and information science. Our scope encompasses theory, methods, and applications across various domains, including advertising, business, health, information science, information technology marketing, and social computing.
We aim to cater to the interests of both primary researchers and practitioners by offering an effective platform for the timely dissemination of advanced and topical issues in this interdisciplinary field. The journal places particular emphasis on original research articles, research survey articles, research method articles, and articles addressing critical applications of research. Join us in advancing knowledge and innovation at the intersection of computing and information science.