%0 Conference Paper %1 zigoris2006bayesian %A Zigoris, Philip %A Zhang, Yi %B Proceedings of the 15th ACM international conference on Information and knowledge management %C New York, NY, USA %D 2006 %I ACM %K implicit-feedback recommendation social-search study %P 397--404 %R 10.1145/1183614.1183672 %T Bayesian adaptive user profiling with explicit & implicit feedback %U http://doi.acm.org/10.1145/1183614.1183672 %X Research in information retrieval is now moving into a personalized scenario where a retrieval or filtering system maintains a separate user profile for each user. In this framework, information delivered to the user can be automatically personalized and catered to individual user's information needs. However, a practical concern for such a personalized system is the "cold start problem": any user new to the system must endure poor initial performance until sufficient feedback from that user is provided.To solve this problem, we use both explicit and implicit feedback to build a user's profile and use Bayesian hierarchical methods to borrow information from existing users. We analyze the usefulness of implicit feedback and the adaptive performance of the model on two data sets gathered from user studies where users' interaction with a document, or <i>implicit feedback</i>, were recorded along with explicit feedback. Our results are two-fold: first, we demonstrate that the Bayesian modeling approach effectively trades off between shared and user-specific information, alleviating poor initial performance for each user. Second, we find that implicit feedback has very limited unstable predictive value by itself and only marginal value when combined with explicit feedback. %@ 1-59593-433-2

@inproceedings{zigoris2006bayesian, abstract = {Research in information retrieval is now moving into a personalized scenario where a retrieval or filtering system maintains a separate user profile for each user. In this framework, information delivered to the user can be automatically personalized and catered to individual user's information needs. However, a practical concern for such a personalized system is the "cold start problem": any user new to the system must endure poor initial performance until sufficient feedback from that user is provided.To solve this problem, we use both explicit and implicit feedback to build a user's profile and use Bayesian hierarchical methods to borrow information from existing users. We analyze the usefulness of implicit feedback and the adaptive performance of the model on two data sets gathered from user studies where users' interaction with a document, or <i>implicit feedback</i>, were recorded along with explicit feedback. Our results are two-fold: first, we demonstrate that the Bayesian modeling approach effectively trades off between shared and user-specific information, alleviating poor initial performance for each user. Second, we find that implicit feedback has very limited unstable predictive value by itself and only marginal value when combined with explicit feedback.}, acmid = {1183672}, added-at = {2011-07-21T16:41:11.000+0200}, address = {New York, NY, USA}, author = {Zigoris, Philip and Zhang, Yi}, biburl = {https://www.bibsonomy.org/bibtex/2550585a9403d86bcd5faee274b314ae6/beate}, booktitle = {Proceedings of the 15th ACM international conference on Information and knowledge management}, description = {Bayesian adaptive user profiling with explicit & implicit feedback}, doi = {10.1145/1183614.1183672}, interhash = {80717b112017ecc75865b551449c3a8c}, intrahash = {550585a9403d86bcd5faee274b314ae6}, isbn = {1-59593-433-2}, keywords = {implicit-feedback recommendation social-search study}, location = {Arlington, Virginia, USA}, numpages = {8}, pages = {397--404}, publisher = {ACM}, series = {CIKM '06}, timestamp = {2011-07-21T16:41:11.000+0200}, title = {Bayesian adaptive user profiling with explicit \& implicit feedback}, url = {http://doi.acm.org/10.1145/1183614.1183672}, year = 2006 }