Personalization in text information retrieval: A survey

Abstract

Personalization of information retrieval (PIR) is aimed at tailoring a search toward individual users and user groups by taking account of additional information about users besides their queries. In the past two decades or so, PIR has received extensive attention in both academia and industry. This article surveys the literature of personalization in text retrieval, following a framework for aspects or factors that can be used for personalization. The framework consists of additional information about users that can be explicitly obtained by asking users for their preferences, or implicitly inferred from users' search behaviors. Users' characteristics and contextual factors such as tasks, time, location, etc., can be helpful for personalization. This article also addresses various issues including when to personalize, the evaluation of PIR, privacy, usability, etc. Based on the extensive review, challenges are discussed and directions for future effort are suggested.

The Search as Learning Spaceship: Toward a Comprehensive Model of Psychological and Technological Facets of Search as Learning

“…A full discussion of approaches for the personalization of ranking and retrieval systems goes beyond the scope of this article. A good summary of current techniques can be found in Liu et al (2020) . The literature furthermore provides some examples that try to integrate search personalization into learning-oriented systems, e.g., Tan et al (2012) integrate measurements of the Web resource’s comprehensibility for the individual user into the ranking mechanism; Liu and Jung (2021) seek to model the development of user interest, as a feature relevant specifically to learning-related tasks; Rieh et al (2016) summarize how different kinds of search behavior can be linked to cognitive learning modes and thus, different search paradigms.…”

Services personalization in digital academic libraries: a Delphi study

“…Other topics posed in collaborative personalization include the exploitation of Web 2 technologies and tools to support this type of personalization. As Liu et al (2020) state, personalization of information retrieval has been given lot of attention both in academia and in industry, and has become increasingly common over the past two decades. Therefore, different users get different results for the same search.…”

Fairness in Information Access Systems

“…Returning to the lending example, a classication tool that estimates a potential borrower's risk of default should not return di erent risk scores or recommended decisions based on which loan o cer is currently using the system. Information access systems, however, are o en personalized (Liu et al, 2020).…”