Interactive Intent Modeling from Multiple Feedback Domains

Pedram Daee, Joel Pyykkö, Dorota Glowacka, Samuel Kaski

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

In exploratory search, the user starts with an uncertain information need and provides relevance feedback to the system's suggestions to direct the search. The search system learns the user intent based on this feedback and employs it to recommend novel results. However, the amount of user feedback is very limited compared to the size of the information space to be explored. To tackle this problem, we take into account user feedback on both the retrieved items (documents) and their features (keywords). In order to combine feedback from multiple domains, we introduce a coupled multi-armed bandits algorithm, which employs a probabilistic model of the relationship between the domains. Simulation results show that with multi-domain feedback, the search system can find the relevant items in fewer iterations than with only one domain. A preliminary user study indicates improvement in user satisfaction and quality of retrieved information.
Original languageEnglish
Title of host publicationProceedings of the 21st International Conference on Intelligent User Interfaces
Place of PublicationNew York, NY, USA
Number of pages5
ISBN (Print)978-1-4503-4137-0
Publication statusPublished - Mar 2016
Event 21st International Conference on Intelligent User Interfaces - Sonoma, United States
Duration: 7 Mar 201610 Mar 2016

Publication series

NameIUI '16


Conference 21st International Conference on Intelligent User Interfaces
Abbreviated titleIUI 2016
Country/TerritoryUnited States
Internet address


Dive into the research topics of 'Interactive Intent Modeling from Multiple Feedback Domains'. Together they form a unique fingerprint.

Cite this