Social Recommender Systems for Professional Communities

Social Recommender Systems are successful in e-commerce applications for suggesting/receiving new product information to/from trusted persons. Professional communities have similar needs to find newest tools, relevant events, similar people. But the abundance of available information makes it hard for the communities to trace and analyze all the information. To support the needs of professional communities the social recommender system should support the collection and analysis of social media in a open repository. Collecting, sharing, analyzing, creation of timelines, etc. should be supported by the recommender system. In future research the support can be extended for running projects offering more analytic capabilities for project management. The thesis work is based on existing prototypes developed at the chair: the Requirements Bazaar, a platform for large-scale social requirements engineering, SWeVA, a Web-based platform for viusal analytics and AERCS, a recommender system for computer scientists seeking collaboration opportunities.