In this paper, we address the problem of personalization in question answering (QA). We describe the personalization component of YourQA; our web-based QA system, which creates individual models of users based on their reading level and interests.
First, we explain how user models are dynamically created, saved and updated to filter and re-rank the answers. Then, we focus on how the user's interests are used in YourQA. Finally, we introduce a methodology for user-centered evaluation of personalized QA. Our results show a significant improvement in the user's satisfaction when their profiles are used to personalize answers.
|Title of host publication
|AI(ASTERISK)IA 2007: ARTIFICIAL INTELLIGENCE AND HUMAN-ORIENTED COMPUTING
|R Basili, MT Pazienza
|Place of Publication
|Number of pages
|Published - 2007
|10th Congress of the Italian-Association-for-Artificial-Intelligence - Rome
Duration: 10 Sept 2007 → 13 Sept 2007
|10th Congress of the Italian-Association-for-Artificial-Intelligence
|10/09/07 → 13/09/07