Crowd-powered recommendation for continuous digital media access and exchange in social networks

Competence CenterInformation Retrieval and Machine Learning
ContactTill Plumbaum
Partners: JCP-ConsultMoviriGravity R&DTU DelftTuentiSoundCloudTelefonica I&D

Nowadays, millions of people use social networks, in which they are facing a constant stream of digital media. In order to keep pace with this data stream, novel recommendation techniques are required that face the challenge of providing recommendations that are simultaneously real-time, large-scale, socially informed, interactive and context aware. We refer to these recommendations as smartfeeds. 

In order to achieve such smartfeeds, it is necessary to go beyond passive information collection and also beyond users' immediate social circles. The CrowdRec project addresses this challenge by pioneering a breed of algorithms that combine crowdsourcing and recommendation algorithms to achieve a new generation of social smartfeeds for access and exchange of digital media in social networks. CrowdRec algorithms create a symbiosis between users and content: they establish reciprocal relationships that both satisfy users' digital media needs and connect media with users. 

CrowdRec is a collaborative project and is funded via the 7th Framework Programme ICT of the EC.