%0 Conference Paper %1 puolamki2005combining %A Puolamäki, Kai %A Salojärvi, Jarkko %A Savia, Eerika %A Simola, Jaana %A Kaski, Samuel %B Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval %C New York, NY, USA %D 2005 %I ACM %K eytracking implicit-feedback recommendation search %P 146--153 %R 10.1145/1076034.1076062 %T Combining eye movements and collaborative filtering for proactive information retrieval %U http://doi.acm.org/10.1145/1076034.1076062 %X We study a new task, proactive information retrieval by combining implicit relevance feedback and collaborative filtering. We have constructed a controlled experimental setting, a prototype application, in which the users try to find interesting scientific articles by browsing their titles. Implicit feedback is inferred from eye movement signals, with discriminative hidden Markov models estimated from existing data in which explicit relevance feedback is available. Collaborative filtering is carried out using the User Rating Profile model, a state-of-the-art probabilistic latent variable model, computed using Markov Chain Monte Carlo techniques. For new document titles the prediction accuracy with eye movements, collaborative filtering, and their combination was significantly better than by chance. The best prediction accuracy still leaves room for improvement but shows that proactive information retrieval and combination of many sources of relevance feedback is feasible. %@ 1-59593-034-5

@inproceedings{puolamki2005combining, abstract = {We study a new task, proactive information retrieval by combining implicit relevance feedback and collaborative filtering. We have constructed a controlled experimental setting, a prototype application, in which the users try to find interesting scientific articles by browsing their titles. Implicit feedback is inferred from eye movement signals, with discriminative hidden Markov models estimated from existing data in which explicit relevance feedback is available. Collaborative filtering is carried out using the User Rating Profile model, a state-of-the-art probabilistic latent variable model, computed using Markov Chain Monte Carlo techniques. For new document titles the prediction accuracy with eye movements, collaborative filtering, and their combination was significantly better than by chance. The best prediction accuracy still leaves room for improvement but shows that proactive information retrieval and combination of many sources of relevance feedback is feasible.}, acmid = {1076062}, added-at = {2011-07-21T17:06:22.000+0200}, address = {New York, NY, USA}, author = {Puolam\"{a}ki, Kai and Saloj\"{a}rvi, Jarkko and Savia, Eerika and Simola, Jaana and Kaski, Samuel}, biburl = {https://www.bibsonomy.org/bibtex/22468014a95109f90316972a7fab2c4a6/beate}, booktitle = {Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval}, description = {Combining eye movements and collaborative filtering for proactive information retrieval}, doi = {10.1145/1076034.1076062}, interhash = {1f0a1a21b47f702223de6fcd0ee30788}, intrahash = {2468014a95109f90316972a7fab2c4a6}, isbn = {1-59593-034-5}, keywords = {eytracking implicit-feedback recommendation search}, location = {Salvador, Brazil}, numpages = {8}, pages = {146--153}, publisher = {ACM}, series = {SIGIR '05}, timestamp = {2011-07-21T17:06:22.000+0200}, title = {Combining eye movements and collaborative filtering for proactive information retrieval}, url = {http://doi.acm.org/10.1145/1076034.1076062}, year = 2005 }