The rapid development of artificial intelligence (AI) is reshaping how people seek, access, and use information, with significant implications for researchers, educators, and students. Increasingly, academic search engines, bibliographic databases, and digital libraries are integrating AI features, including generated and synthesized content, conversational interfaces, and intelligent recommendation. These tools promise to support discovery, synthesis, and learning, yet they also raise critical questions about search integrity, fairness, accountability, transparency, and ethics (FATE). In academic contexts, where reliability and credibility are paramount, the design and use of AI-mediated search systems require novel ideas and approaches. Building on previous work in interactive information retrieval (IIR), search as learning, and search user interface design, this workshop invites the CHIIR community to examine opportunities and challenges in developing and using AI-powered academic search systems for research and higher education.

Autonomous learning regards students as the center and orientation rather than teachers’ guidance. During autonomous learning, information seeking is not only a process of interactions with systems and stakeholders, but also a process of learning and cognitive transformation from low-level to high-level activities. This study investigated users’ cognitive process and cognitive paths, as well as the creation strategies for independent topic selection during the information seeking process. We conducted a longitudinal study through tracking interviews with eight university students who planned to select a topic for their theses or independent study. The interviews were conducted weekly to collect data of their cognitive process and seeking behaviors. It is found that: (1) four lower levels of cognitive process (understanding, applying, analyzing and evaluating) often occur during the stages before formulation, while creating occurs in the formulation stage; (2) three cognitive paths for topic selection were identified: "understand - apply - create", "understand - analyze - create" and "understand - analyze - evaluate - create", and (3) two creation strategies for topic selection according to the duration of creation stages were identified: Incubation and Verification. These results shed light on the design of search systems that could better assist the autonomous learning process and for users to accomplish creative learning tasks.

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.

Learning-related type of tasks has attracted much research attention recently but it is still not clear what factors would influence users learning outcomes and how. In this study, we conducted a user experiment to assess searchers learning outcomes and examine how information source selection strategies would influence their learning outcomes. In this experiment, thirty-two college students conducted search for two types of learning tasks: receptive tasks and critical tasks. Participants were asked to write down what they knew about the task before and after the search. For data analysis, we proposed a comprehensive assessment method, which used both quantitative measures (i.e. knowledge points, knowledge facets, knowledge scope, etc.) and qualitative measures to assess users' learning outcomes. Our results demonstrated that searchers' information source preferences influence their learning outcomes; i.e., encyclopedia-preferred sessions had better relevance of written summaries in receptive tasks and Q&A preferred sessions led to better relevance in critical tasks. Furthermore, searchers had two types of information source selection strategies: task-adaptive strategy and non-task-adaptive strategy. The results showed that searchers with task-adaptive strategy could gain better learning outcomes, e.g. knowledge points, facets, scope, depth, relevance and analyticity. This study highlighted the importance of information source selection strategies in learning-related type of tasks, and knowing how to select suitable information sources for different types of tasks may benefit the learning outcome for searchers.

Studies have examined how time constraints influence search behaviors; however, no effort has been spent on how time constraints may help predict document usefulness for personalization purposes. This study aims to fill this gap by researching the relationships between time constraints, search behaviors, and usefulness judgments. A controlled lab experiment was conducted with 40 participants searching for four tasks of two types (fact finding and information understanding), under two time conditions (with or without time constraints). Results show that time constraints and usefulness had interaction effects on first dwell time; while usefulness had positive relationship with total dwell time. Results indicate that knowing time constraints helps predict document usefulness from dwell time. The findings provide implications on personalization in information search.

This study used wheel activity as an indicator of users' browsing strategy, and explored the effects of various contextual factors on users' browsing patterns. Users' wheel activities were extracted from a search log in a user experiment, in which forty participants with different backgrounds conducted an online search in various contexts. To statistically test the potential effects of contexts on browsing strategy, we calculated three types of scroll-based variables to capture different types of browsing behaviors, and analyzed the effects of contextual factors via OLS regression analysis. Our results revealed that information understanding type tasks might lead to more proportion of revisit browsing range, while higher pressure level and higher pre-familiarity might lead to larger one-time browsing range; however, time constraint did not influence their browsing strategies. Our study also provided methodological implication for future interactive information retrieval studies by testifying and highlighting the usefulness of users' wheel activities in depicting online browsing patterns.

As a significant contextual factor in information search, topic knowledge has been gaining increased research attention. We report on a study of the relationship between information searchers' topic knowledge and their search behaviors, and on an attempt to predict searchers' topic knowledge from their behaviors during the search. Data were collected in a controlled laboratory experiment with 32 undergraduate journalism student participants, each searching on 4 tasks of different types. In general, behavioral variables were not found to have significant differences between users with high and low levels of topic knowledge, except the mean first dwell time on search result pages. Several models were built to predict topic knowledge using behavioral variables calculated at 3 different stages of search episodes: the first‐query‐round, the middle point of the search, and the end point. It was found that a model using some search behaviors observed in the first query round led to satisfactory prediction results. The results suggest that early‐session search behaviors can be used to predict users' topic knowledge levels, allowing personalization of search for users with different levels of topic knowledge, especially in order to assist users with low topic knowledge.

Knowing, in real time, whether a current searcher in an information retrieval system finds the search task difficult can be valuable for tailoring the system's support for that searcher. This study investigated searcher's behaviors at different stages of the search process; they are: 1) first-round point at the beginning of the search, right before searchers issued their second query; 2) middle point, when searchers proceeded to the middle of the search process, and 3) end point, when searchers finished the whole task. We compared how the behavioral features calculated at these three points were different between difficult and easy search tasks, and identified behavioral features during search sessions that can be used in real-time to predict perceived task difficulty. In addition, we compared the prediction performance at different stages of search process. Our results show that a number of user behavioral measures at all three points differed between easy and difficult tasks. Query interval time, dwell time on viewed documents, and number of viewed documents per query were important predictors of task difficulty. The results also indicate that it is possible to make relatively accurate prediction of task difficulty at the first query round of a search. Our findings can help search systems predict task difficulty which is necessary in personalizing support for the individual searcher.

We report on an investigation of behavioral differences between users in difficult and easy search tasks. Behavioral factors that can be used in real-time to predict task difficulty are identified. User data was collected in a controlled lab experiment (n=38) where each participant completed four search tasks in the genomics domain. We looked at user behaviors that can be obtained by systems at three levels, distinguished by the time point when the measurements can be done. They are: 1) first-round level at the beginning of the search, 2) accumulated level during the search, and 3) whole-session level by the end of the search. Results show that a number of user behaviors at all three levels differed between easy and difficult tasks. Models predicting task difficulty at all three levels were developed and evaluated. A real-time model incorporating first-round and accumulated levels of behaviors (FA) had fairly good prediction performance (accuracy 83%; precision 88%), which is comparable with the model using the whole-session level behaviors which are not real-time (accuracy 75%; precision 92%). We also found that for efficiency purpose, using only a limited number of significant variables (FC_FA) can obtain a prediction accuracy of 75%, with a precision of 88%. Our findings can help search systems predict task difficulty and adapt search results to users.

Personalization of search results offers the potential for significant improvement in information retrieval performance. User interactions with the system and documents during information-seeking sessions provide a wealth of information about user preferences and their task goals. In this paper, we propose methods for analyzing and modeling user search behavior in search sessions to predict document usefulness and then using information to personalize search results. We generate prediction models of document usefulness from behavior data collected in a controlled lab experiment with 32 participants, each completing uncontrolled searching for 4 tasks in the Web. The generated models are then tested with another data set of user search sessions in radically different search tasks and constrains. The documents predicted useful and not useful by the models are used to modify the queries in each search session using a standard relevance feedback technique. The results show that application of the models led to consistently improved performance over a baseline that did not take account of user interaction information. These findings have implications for designing systems for personalized search and improving user search experience.

Click through events in search results pages (SERPs) are not reliable implicit indicators of document relevance. A user's task and domain knowledge are key factors in recognition and link selection and the most useful SERP document links may be those that best match the user's domain knowledge. User study participants rated their knowledge of genomics MeSH terms before conducting 2004 TREC Genomics Track tasks. Each participant's document knowledge was represented by their knowledge of the indexing MeSH terms. Results show high, intermediate, and low domain knowledge groups had similar document selection SERP rank distributions. SERP link selection distribution varied when participant knowledge of the available documents was analyzed. High domain knowledge participants usually selected a document with the highest personal knowledge rating. Low domain knowledge participants were reasonably successful at selecting available documents of which they had the most knowledge, while intermediate knowledge participants often failed to do so. This evidence for knowledge effects on SERP link selection may contribute to understanding the potential for personalization of search results ranking based on user domain knowledge.

In this paper, we report findings on how user behaviors vary in tasks with different difficulty levels as well as of different types. Two behavioral signals: document dwell time and number of content pages viewed per query, were found to be able to help the system detect when users are working with difficult tasks.