User-Centered Adaptive Information Retrieval

Information retrieval systems are critical for overcoming information overload. A major deficiency of existing retrieval systems is that they generally lack user modeling and are not adaptive to individual users. Personalization is expected to break this deficiency and significantly improve retrieval accuracy. In this thesis, we study how to put the user in the center of information retrieval process for the personalized search. We develop a decision-theoretic framework for optimizing interactive information retrieval based on eager user model updating. The framework emphasizes immediate and frequent feedback to bring maximum benefit of context to the user. It serves as a roadmap for studying retrieval models for personalized search. Specific retrieval models for exploiting implicit user context are developed to improve retrieval accuracy. Evaluation indicates that the user context information especially the clickthrough information can effectively and efficiently improve retrieval performance. Sometimes we need user effort to provide more information to improve the retrieval performance. In this scenario, we study how a retrieval system can brm active feedback. We frame the problem as a statistical decision problem, and examine several special cases in refining the framework. The experimental results indicate that the diversity in the presented documents is a desirable property. On the result representation side, we study how to exploit a user's clickthrough information to adaptively reorganize the clustering results. We propose four strategies for adapting clustering results based on user interactions. The simulation experiments show that the adaptation strategies have different performance for different types of users. We also conduct a user study on one adaptive clustering strategy to see if an adaptive clustering system can bring users better search utility than a static clustering system. The results show that there is generally no significant difference between the two systems from a user's perspective. We design and develop a client-side web search agent UCAIR for personalized search. UCAIR captures and exploits implicit context information to immediately rerank any documents that have not yet been seen by the user. User studies show that the UCAIR improves performance over a popular search engine, on which UCAIR search agent is built.

Name thesis:degree_name

Ph.D.

Level thesis:degree_level

Dissertation

Discipline thesis:degree_discipline

Computer Science

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2015

Author dc:creator

• Shen, Xuehua

Contributors dc:contributor

• ChenXiang Zhai

• Computer Science

Language dc:language

eng

Identifier

(MiAaPQ)AAI3290374

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/81790