Benoît Lemaire

A glass box approach to adaptive hypermedia

Utilising adaptive interface techniques in the design of systems introduces certain risks. An adaptive interface is not static, but will actively adapt to the perceived needs of the user. Unless carefully designed, these changes may lead to an unpredictable, obscure and uncontrollable interface. Therefore the design of adaptive interfaces must ensure that users can inspect the adaptivity mechanisms, and control their results. One way to do this is to rely on the users understanding of the application and the domain, and relate the adaptivity mechanisms to domain-specific concepts. We present an example of an adaptive hypertext help system POP, which is being built according to these principles, and discuss the design considerations and empirical findings that lead to this design.

A System To Assess the Semantic Content of Student Essays.

This paper presents Apex, a system that can automatically assess a student essay based on its content. It relies on Latent Semantic Analysis, a tool which is used to represent the meaning of words as vectors in a high-dimensional space. By comparing an essay and the text of a given course on a semantic basis, our system can measure how well the essay matches the text. Various assessments are presented to the student regarding the topic, the outline and the coherence of the essay. Our experiments yield promising results.

A Computational Model for Simulating Text Comprehension

In the present article, we outline the architecture of a computer program for simulating the process by which humans comprehend texts. The program is based on psycholinguistic theories about human memory and text comprehension processes, such as the construction-integration model (Kintsch, 1998), the latent semantic analysis theory of knowledge representation (Landauer & Dumais, 1997), and the predication algorithms (Kintsch, 2001; Lemaire & Bianco, 2003), and it is intended to help psycholinguists investigate the way humans comprehend texts.

Latent Semantic Analysis for User Modeling

Latent semantic analysis (LSA) is a tool for extracting semantic information from texts as well as a model of language learning based on the exposure to texts. We rely on LSA to represent the student model in a tutoring system. Domain examples and student productions are represented in a high-dimensional semantic space, automatically built from a statistical analysis of the co-occurrences of their lexemes. We also designed tutoring strategies to automatically detect lexeme misunderstandings and to select among the various examples of a domain the one which is best to expose the student to. Two systems are presented: the first one successively presents texts to be read by the student, selecting the next one according to the comprehension of the prior ones by the student. The second plays a board game (kalah) with the student in such a way that the next configuration of the board is supposed to be the most appropriate with respect to the semantic structure of the domain and the previous students moves.

MDLChunker: A MDL-Based Cognitive Model of Inductive Learning

This paper presents a computational model of the way humans inductively identify and aggregate concepts from the low-level stimuli they are exposed to. Based on the idea that humans tend to select the simplest structures, it implements a dynamic hierarchical chunking mechanism in which the decision whether to create a new chunk is based on an information-theoretic criterion, the Minimum Description Length (MDL) principle. We present theoretical justifications for this approach together with results of an experiment in which participants, exposed to meaningless symbols, have been implicitly encouraged to create high-level concepts by grouping them. Results show that the designed model, called hereafter MDLChunker, makes precise quantitative predictions both on the kind of chunks created by the participants and also on the moment at which these creations occur. They suggest that the simplicity principle used to design MDLChunker is particularly efficient to model chunking mechanisms. The main interest of this model over existing ones is that it does not require any adjustable parameter.

Is Attentional Refreshing in Working Memory Sequential? A Computational Modeling Approach

Short-term memorization of items while performing a concurrent distracting task requires maintenance processes. The time-based resource-sharing model of working memory (Barrouillet et al. in Psychol Rev 118:175–192, 2011) and its computational version TBRS* (Oberauer and Lewandowsky in Psychon Bull Rev 18:10–45, 2011) proposed that items are refreshed when attention is not captured by the distracting activity. However, these models are unable to account for human performance on the last items when temporal constraints are substantial. The present study presents an analytic approach and computational simulations showing that the sequentiality of the domain-general attentional refreshing mechanism is responsible for the discrepancy between humans and model. It is suggested that the focus of attention could be flexible. The implementation of a computational model based on this solution provides a much better fit to human data. Outcomes are discussed in reference to contemporary works on the phonological loop as well as in reference to other computational models of short-term memory.

Using Production to Assess Learning: An ILE That Fosters Self-Regulated Learning

Current systems aiming at engaging students in Self-Regulated Learning processes are often prompt-based and domain-dependent. Such metacognitive prompts are either difficult to interpret for novices or ignored by experts. Although domain-dependence per se cannot be considered as a drawback, it is often due to a rigid structure which prevents from moving to another domain. We detail here Apex, a two-loop system which provides texts to be learned through summarization. In the first loop, called Reading, the student formulates a query and is provided with texts related to this query. Then the student judges whether each text presented could be summarized. In the second loop, called Writing, the student writes out a summary of the texts, then gets an assessment from the system. In order to automatically perform various comprehension-centered tasks (i.e., texts that match queries, assessment of summaries), our system uses LSA (Latent Semantic Analysis), a tool devised for the semantic comparison of texts.

Decision-making in information seeking on texts: an eye-fixation-related potentials investigation

Reading on a web page is known to be not linear and people need to make fast decisions about whether they have to stop or not reading. In such context, reading, and decision-making processes are intertwined and this experiment attempts to separate them through electrophysiological patterns provided by the Eye-Fixation-Related Potentials technique (EFRPs). We conducted an experiment in which EFRPs were recorded while participants read blocks of text that were semantically highly related, moderately related, and unrelated to a given goal. Participants had to decide as fast as possible whether the text was related or not to the semantic goal given at a prior stage. Decision making (stopping information search) may occur when the paragraph is highly related to the goal (positive decision) or when it is unrelated to the goal (negative decision). EFRPs were analyzed on and around typical eye fixations: either on words belonging to the goal (target), subjected to a high rate of positive decisions, or on low frequency unrelated words (incongruent), subjected to a high rate of negative decisions. In both cases, we found EFRPs specific patterns (amplitude peaking between 51 to 120 ms after fixation onset) spreading out on the next words following the goal word and the second fixation after an incongruent word, in parietal and occipital areas. We interpreted these results as delayed late components (P3b and N400), reflecting the decision to stop information searching. Indeed, we show a clear spill-over effect showing that the effect on word N spread out on word N + 1 and N + 2.

Inducing High-Level Behaviors from Problem-Solving Traces Using Machine-Learning Tools

Many researchers consider interactive learning environments to be interesting solutions for overcoming the limits of classical one-to-many teaching methods. However, these environments should incorporate accurate representations of student knowledge to provide relevant guidance. In a problem-solving environment, one way to build and update this student model is model tracing, or using a detailed representation of cognitive skills to precisely follow what the student is doing. Some model-tracing tutors such as PAT (Personal Algebra Tutor) contain rules that the system can use to solve the problem and assess the students solution.

An analysis of reading skill development using E-Z Reader

Previously reported simulations using the E-Z Reader model of eye-movement control suggest that the patterns of eye movements observed with children versus adult readers reflect differences in lexical processing proficiency. However, these simulations fail to specify precisely what aspect(s) of lexical processing (e.g., orthographic processing) account for the concurrent changes in eye movements and reading skill. To examine this issue, the E-Z Reader model was first used to simulate the aggregate eye-movement data from 15 adults and 75 children to replicate the finding that gross differences in reading skill can be accounted for by differences in lexical processing proficiency. The model was then used to simulate the eye-movement data of individual children so that the best-fitting lexical processing parameters could be correlated to measures of orthographic knowledge, phonological processing skill, sentence comprehension, and general intelligence. These analyses suggest that orthographic knowledge accounts for variance in the eye-movement measures that is observed with between-individual differences in reading skill. The theoretical implications of this conclusion will be discussed in relation to computational models of reading and our understanding of reading skill development.