Article
To read the full-text of this research, you can request a copy directly from the authors.

Abstract

Most e-learning systems engage successively students in reading, writing and assessment activities. In the third phase, the teacher gives feedback on student comprehension, which is often processed a long time after the others, letting the students alone with their difficulties. Thus, there is room to devise automated assessment systems on course comprehension, based on NLP techniques such as latent semantic analysis (LSA). The aim of this paper is to present some systems devised to complete this aim, which implement LSA to model learners' comprehension and/or to compare reading material (e.g., course text) with learners' summaries about it, select reading materials and predict student processes from their summaries.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... Pensum est un outil d'aide à la synthèse de document(s), issu du projet européen Learning Technologies for Lifelong Learning (LtfLL, 7 e PCRD-STREP). Toutefois sa genèse commence en amont de ce projet [11]. Comme outil d'apprentissage autorégulé, il doit permettre à l'utilisateur-apprenant de décider de l'organisation de son travail et donc d'interrompre son activité quand il le souhaite. ...
Article
Full-text available
Professional Development is ill served by traditional ways of learning. It can profit from a Learning Networks approach, which emphasizes logistic, content and didactic flexibility. Learning Networks are online, social networks that have been de-signed and tooled to foster informal learning. Three European projects are discussed – idSpace, LTfLL, Handover -which have developed tools befitting networked learning. Each in its own way, the projects illustrate the benefits of a networked learning ap-proach. This goes for all three flexibilities but in particular for the need to be didactical-ly flexible. Finally, it is argued that formal education could profit from the tools dis-cussed.
Article
Full-text available
Much computer-assisted language learning (CALL) software engenders a mixture of reactions upon initial exposure. For teachers, this may obscure a more objective view of the benefits to the learner. This article considers ways in which a languages teacher or a languages department might evaluate language learning software on a pedagogical basis. It emphasises that the classroom teacher is already in possession of much of the knowledge to do this successfully. It illustrates what might be considered good practice in various areas. This is done by matching a learning and teaching approach as currently practised within the U.K. secondary school environment against features of various CALL software packages.
Conference Paper
Full-text available
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.
Article
Full-text available
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 rst 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 kalah with the student in such a way that the next con guration of the board is supposed to be the most appropriate with respect to the semantic structure of the domain and the previous student's moves.
Article
Full-text available
Can distance learning transform higher education, saving money and improving student learning? Modern technolo- gies allow instructors to design distance learning environ- ments with all the features of traditional courses and more. What findings from research on instruction can help course designers make effective choices? I argue that students who take an autonomous stance towards instruction tend to learn from most courses, and that course designers who take a scaffolded knowledge integration approach to course design can enable autonomous learning. To help designers create courses that transform passive students into autonomous learners, this article draws on recent re- search on instruction. I describe the scaffolded knowledge integration framework and use this framework to interpret current approaches to distance learning.
Article
Full-text available
The study reported here sought to obtain the clear articulation of asynchronous computer-mediated discourse needed for Carl Bereiter and Marlene Scardamalia’s knowledge-creation model. Distinctions were set up between three modes of discourse: knowledge sharing, knowledge construction, and knowledge creation. These were applied to the asynchronous online discourses of four groups of secondary school students (40 students in total) who studied aspects of an outbreak of Severe Acute Respiratory Syndrome (SARS) and related topics. The participants completed a pretest of relevant knowledge and a collaborative summary note in Knowledge Forum, in which they self-assessed their collective knowledge advances. A coding scheme was then developed and applied to the group discourses to obtain a possible explanation of the between-group differences in the performance of the summary notes and examine the discourses as examples of the three modes. The findings indicate that the group with the best summary note was involved in a threshold knowledge-creation discourse. Of the other groups, one engaged in a knowledge-sharing discourse and the discourses of other two groups were hybrids of all three modes. Several strategies for cultivating knowledge-creation discourse are proposed.
Article
Full-text available
This paper presents a general computational cognitive model of the way a summary is assessed by teachers. It is based on models of two subprocesses: determining the importance of sentences and guessing the cognitive rules that the student may have used. All models are based on Latent Semantic Analysis, a computational model of the representation of the meaning of words and sentences. Models' performances are compared with data from an experiment conducted with 278 middle school students. The general model was implemented in a learning environment designed for helping students to write summaries.
Article
Full-text available
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.
Article
This paper reviews written feedback from an information-processing perspective. The first section discusses the question of feedback as a reinforcer, and describes the feedback paradigm used as a conceptual guide for the following sections. In the second section we evaluate research on the form and content of feedback. In the last section, a model is developed that applies concepts from servocontrol theory to the feedback sequence. Finally, we report three experiments which support the major predictions of the control model.
Article
Designing metacognitive activities that focus on both cognitive and social development is a theoretical and practical challenge. This balanced approach to metacognition concerns itself with many aspects of student development, ranging from academic competence to knowledge about the self-as-learner. In this article, I examine two basic approaches to supporting metacognition: (a) strategy training and (b) creation of a supprotive social environment for metacognition. There are also two kinds of content that are taught using these two approaches: (a) knowledge about a specific domain and (b) knowledge about the self-as-learner. These approaches and contents have been used frequently in metacognitive interventions over the past two decades. Each offers unique contributions to metacognitive development. However, programs that address these approaches and contents simultaneously are rare. Maintaining the coordination, on one hand, between strategy training and creating social supports, and on the other hand, between knowledge about the subject domain and knowledge about the self-as-learner, is a challenge for most design efforts in metacognition. Future design issues include: (a) developing a system approach to promote coordination among these approaches and contents; and (b) finding ways to build knowledge about the self-as-learner.
Article
The automatic generation of summaries using cases (GARUCAS) environment was designed as an intelligent system to help one learn to summarize narrative texts by means of examples within a case-based reasoning (CBR) approach. Each example, modeled as a case, contains a conceptual representation of the initial textual state, the different steps of the summarization method, and the representation of the final textual state obtained. The CBR approach allows the environment to summarize new texts in order to produce new text summarization examples with respect to some predefined educational objectives. Within GARUCAS, this approach is used at two levels: an event level (EL) in order to identify essential elements of a story, and the clause level (CL) to make the summary more readable. The purpose of this article is to describe the GARUCAS environment and the model used to build story summarization examples and summarize new texts. This model is based on important psycholinguistic work concerning event and narrative structures and text revision rules. An experiment was conducted with 12 short stories. The GARUCAS environment can classify the stories according to their structure analogy and reuse the summarization method of the most similar text. Such an approach can be reused for any kind of texts or summary types. © 2003 Wiley Periodicals, Inc.
Conference Paper
The role of assessment and evaluation has recently changed in a way which will have fundamental consequences in applying information and communication technologies (ICTs) in the analysis of learning outcomes. Rather than helping teachers to get their students' final grades from an entirely automated assessment system, the idea is also to support students to reflect on their learning process as early as possible and point out the strong and weak aspects of it. This paradigmatic shift from teacher-centered assessment towards learner-centered process evaluation offers interesting challenges to educational technologists, especially in the area of essay evaluation. We present a system that evaluates the content of essays based on Latent Semantic Analysis (LSA). The system applies LSA to compare the conceptual similarity between the essays and selected text passages from the course material which cover the essay assignment-specific subject matter. As an introduction to the semi-automatic essay grading we describe how, in addition to grade assignment, we use LSA to provide the writer with more detailed feedback about the points covered in the essay.