Using Collaborative Filtering to Automate Worker-Job Recommendations for Crowdsourcing Services
Julian Jarrett, M. Brian Blake · 2016
Generally, in crowdsourcing, providers advertise their task offerings (i.e. the open call model) largely to crowdworkers who subscribe their interest in working (i.e. subscription model). The combined open call and subscription model represent significant bottlenecks for recruitment in the paradigm of crowdsourcing. Consequently, attracting and retaining a crowd are the major challenges to the success of a crowdsourcing platform and forming a labor market. To address this problem, we introduce a worker-job matching model for crowdsourcing supported by a service-oriented architecture. The service-oriented architecture implements a push-pull mechanism and an underlying algorithm based on collaborative filtering techniques. Preliminary studies show that the infrastructure can effectively infer the levels of expertise of potential crowdworkers based on their profile and past performance history.