Leveraging Recommender Systems for the Creation and Maintenance of Structure within Collaborative Social Media Platforms
Eva Zangerle · 2012
During the last decade, the web transformed from a web of information con-sumers to a web of information producers. In particular, the advent of online social media platforms is hugely responsible for this shift as people now ac-tively post information in knowledge bases, engage in online communities and contribute to social media platforms. Hence, a vast amount of new informa-tion is produced each day. This publicly available data is an invaluable source of information which still is to be fully exploited. Due to the broad span of users of such systems (originating from different cultures and backgrounds, speaking different languages, etc.), the information provided features a lim-ited amount of common structure, as e.g., objects are named differently and information is structured differently. This is a severe constraint in regards to the performance of search facilities. This thesis proposes to facilitate recommender systems to create and maintain a common structure within collaborative social media platforms aiming at im-proving search performance. For this purpose, two different recommender sys-tems for two showcase platforms are presented. The first recommender system provides recommendations for structuring information within a semistructured information system whereas the second recommender systems is a hashtag rec-ommender system for microblogging services.