The measurement of knowledge gain in information retrieval has garnered significant attention, particularly in evaluating its relationship with user behaviors and its role in enhancing the learning experience by tracking progress toward learning objectives.Previous studies have focused on estimating knowledge acquisition based on a static and predefined representation of learning objectives for each search topic, assessing users' progress toward these fixed goals.However, users often differ in their interests, focusing on various aspects or subtopics within the same broader topic, which they express through diverse, topic-related queries.In this paper, we propose a personalized approach to knowledge gain measurement by adapting and extending an existing method for inferring learning subgoals based on user queries.Our approach extends this method by dynamically determining the number of subgoals for each user query, rather than using a fixed number.Knowledge gain estimation is then conducted based on these individualized subgoals while also incorporating the user's prior knowledge of the search topic to enhance personalization.Using 10 different topics, we compare our approach to a baseline method in which the learning goal representation remains uniform for all users within a given topic.

In the context of search as learning, users engage in search sessions to fill their information gaps and achieve their learning goals. Tracking the user’s state of knowledge is therefore essential for estimating how close they are to achieve these learning goals. In this respect, we extend a recently proposed approach that uses the recognition of entities present in the text to track the user’s knowledge. Our approach introduces a more complete representation by considering both the entities and their relations. More precisely, we represent both the user’s knowledge and the user’s learning goals (or target knowledge) as knowledge graphs.

A reliable representation of the user’s knowledge state during a learning search session is crucial to understand their real information needs. When a search system is aware of such a state, it can adapt the search results and provide greater support for the user’s learning objectives. A common practice to track the user’s knowledge state is to consider the content of the documents they read during their search session(s). However, most current work ignores entity mentions in the documents, which, when linked to knowledge graphs, can be a source of valuable information regarding the user’s knowledge. To fill this gap, we extend RULK—Representing User Knowledge in Search-as-Learning—with entity linking capabilities. The extended framework RULK represents and tracks user knowledge as a collection of such entities. It eventually estimates the user knowledge gain—learning outcome—by measuring the similarity between the represented knowledge and the learning objective. We show that our methods allow for up to 10% improvements when estimating user knowledge gains.

In this paper, we present a new benchmark collection that shows how 404 users’ knowledge changed over the course of a search-as-learning session. We estimate the knowledge a user gains from each visited document and monitor knowledge change on a document-by-document basis. We describe the specifics of how this collection was created and provide a use case that illustrates potential future applications.

We study the feasibility of using Belief, Desire and Intention agents for modeling the phenomena of urban growth and segregation. Uncertainty, typical of real world situations is modeled using possibility theory. We have also implemented a simple visualization tool whose aim is to track the changes in the model. Some preliminary experiments suggest that such an approach might allow a decision-maker to dynamically track the changes in the model. Besides, it is also possible to interact with the different steps of the simulation via the model. Our proposal makes it possible to simulate the interactions between cognitive agents in an economical environment while taking the spatial context into account.

This article proposes a framework for planning under uncertainty given a partially known initial state and a set of actions having nondeterministic (disjunctive) effects, some being more possible (normal) than the others. The problem, henceforth called possibilistic planning problem, is represented in an extension of the STRIPS formalism in which the initial state of the world and the graded nondeterministic effects of actions are described by possibility distributions. Two notions of solution plans are introduced: γ-acceptable plans that lead to a goal state with a certainty greater than a given threshold γ, and optimally safe plans that lead to a goal state with maximal certainty. It is shown that the search of a γ-acceptable plan amounts to solve a derived planning problem that has only pure (nongraded) nondeterministic actions. A sound and complete partial order planning algorithm, called NDP, has been developed for such classical nondeterministic planning problems. The generation of γ-acceptable and optimally safe plans is achieved by two sound and complete planning algorithms: POSPLAN that relies on NDP, and POSPLAN* that can be seen as a hierarchical version of POSPLAN. The possibilistic planning framework is illustrated throughout the article by an example in the agronomic domain. © 1997 John Wiley & Sons, Inc.