Tagungsbeiträge

Engaging the Crowd for Better Job Recommendations

AutorBenjamin Kille, Fabian Abel
QuelleWorkshop on Crowdsourcing and Human Computation for Recommender Systems 
LinksBibTeX 

Today, people more and more use business-oriented social networks such as LinkedIn or XING to explore career opportunities and find an interesting jobs. Similarly, companies use those platforms to identify candidates for open positions and post job offers in order to advertise to attract appropriate candidates. Job recommendation systems thus have to solve a reciprocal recommendation problem and have to satisfy the expectations of both users who aim for interesting jobs and companies who aim for appropriate applicants. In this paper, we discuss challenges of building a reciprocal job recommendation system. Based on an analysis of profile and interaction data, we highlight potential features that such a recommendation system can exploit and discuss opportunities of integrating a user feedback cycle into the recommender algorithm.