Showing papers presented at "Artificial Intelligence in Education in 2001"

ELM-ART: An Adaptive Versatile System for Web-based Instruction

Abstract: This paper discusses the problems of developing versatile adaptive and intelligent learning systems that can be used in the context of practical Web-based education. We argue that versatility is an important feature of successful Web-based education systems. We introduce ELM-ART, an intelligent interactive educational system to support learning programming in LISP. ELM-ART provides all learning material online in the form of an adaptive interactive textbook. Using a combination of an overlay model and an episodic student model, ELM-ART provides adaptive navigation support, course sequencing, individualized diagnosis of student solutions, and example-based problem-solving support. Results of an empirical study show different effects of these techniques on different types of users during the first lessons of the programming course. ELM-ART demonstrates how some interactive and adaptive educational components can be implemented in WWW context and how multiple components can be naturally integrated together in a single system.

Supporting Social Interaction in an Intelligent Collaborative Learning System

Abstract: Students learning effectively in groups encourage each other to ask questions, explain and justify their opinions, articulate their reasoning, and elaborate and reflect upon their knowledge. The benefits of collaborative learning, however, are only achieved by active, well- functioning teams. This paper presents a model of collaborative learning designed to help an intelligent collaborative learning system identify and target group interaction problem areas. The model describes potential indicators of effective collaborative learning, and for each indicator, recommends strategies for improving peer interaction. This collaborative learning model drove the design and development of two tools that automate the coding, and aid the analysis of collaborative learning conversation and activity. Empirical evaluation of these tools confirm that effective learning teams are comprised of active participants who demand explanations and justification from their peers. The distribution of conversational skills used by members of a supportive group committed to their teammates' learning is compared to that of an unfocused, unsupportive group. The results suggest that structured, high-level knowledge of student conversation in context may be sufficient for automating the assessment of group interaction, furthering the possibility of an intelligent collaborative learning system that can support and enhance the group learning process.

ActiveMath: A Generic and Adaptive Web-Based Learning Environment

Abstract: ActiveMath is a generic web-based learning system that dynamically generates interactive (mathematical) courses adapted to the student's goals, preferences, capabilities, and knowledge. The content is represented in an semantic xml-based format. For each user, the appropriate content is retrieved from a knowledge base and the course is generated individually according to pedagogical rules. Then the course is presented to the user via a standard web- browser. One of the exceptional features of ActiveMath is its integration of stand-alone mathematical service systems. This offers the means for exploratory learning, realistically complex exercises as well as for learning proof methods. The article provides a comprehensive account of the current version of ActiveMath.

Simulating Human Tutor Dialog Moves in AutoTutor

Abstract: This purpose of this paper is to show how prevalent features of successful human tutoring interactions can be integrated into a pedagogical agent, AutoTutor. AutoTutor is a fully automated computer tutor that responds to learner input by simulating the dialog moves of effective, normal human tutors. AutoTutor’s delivery of dialog moves is organized within a 5step framework that is unique to normal human tutoring interactions. We assessed AutoTutor’s performance as an effective tutor and conversational partner during tutoring sessions with virtual students of varying ability levels. Results from three evaluation cycles indicate the following: (1) AutoTutor is capable of delivering pedagogically effective dialog moves that mimic the dialog move choices of human tutors, and (2) AutoTutor is a reasonably effective conversational partner.

Narrative Evolution: Learning from Students' Talk about Species Variation

Abstract: Learners do not always enjoy productive interactions with Multimedia Interactive Learning Environments. Their attention can be distracted away from the educational focus intended by designers and teachers through poor design and operational inadequacy. In this paper we describe a study of groups of learners using a multimedia CD-ROM research tool called Galapagos. This tool was developed to enable us to observe groups of learners interacting with different versions of the same multimedia content. These different versions implemented different forms of guidance for learners both within the presented narrative structure of the material and in the tools offered to learners to help them build the individual content elements into a coherent whole. Our empirical work was conducted with groups of learners within their educational establishment using the Galapagos CD-ROM as part of their studies for national examinations in Biology. Their sessions with Galapagos were recorded using video and audio and our analysis of their dialogue has enabled us to gain a greater understanding of the factors that contribute to productive, educationally focused learning interactions. Through the construction of different representations we have been able to co- ordinate information about interactivity between learners and system at the interface with interactivity between individual learners within the group around the system interface. Varying the quantity and quality of guidance impacts upon the trajectory learners construct through multimedia content; it also influences the manner in which they use the facilities provided by system designers to assist them in their construction of task answers.

Effective feedback on L2 pronunciation in ASR-based CALL

Abstract: Computer Assisted Language Learning (CALL) has now established itself as a prolific area whose advantages are well-known to educators. Yet, many authors lament the lack of a reliable integrated conceptual framework linking technology advances and second language acquisition research within which effective materials can be designed [1],[2]. The CALL world has recently witnessed a flourishing of software applications among which Automatic Speech Recognition (ASR) is gaining growing importance. The reasons for this popularity lie in the opportunities this technology offers for practising oral skills and addressing pronunciation problems, two areas that are hard to improve within traditional class-based settings. ASR-based CALL systems appear to be particularly suited for pronunciation teaching as they allow evaluation of the learner’s speech and provide appropriate, individual feedback in real-time. However, given the lack of guidelines for CALL design, most courseware products often do not provide adequate guidance to the learner [3],[4]. Moreover, owing to the limitations in the state-of-the-art technology, all ASR systems will at times generate errors [4]. The main objective of our research is to study how the frequency and seriousness of feedback errors affect learning. The domain in which we work is the acquisition of pronunciation in Dutch as L2 by adults with different language backgrounds. In our study we will use a Dutch language multimedia course, Nieuwe Buren, to which we will add a speech recognition module previously developed at our department, which is able to recognize and score disfluent non-native speech [5]. Automatic pronunciation evaluation and feedback will focus on segmental and supra-segmental aspects. The system’s functionality will be first tested on a group of experts and subsequently on two experimental groups of different proficiency levels. After three months the pronunciation performance of these groups will be compared to that of two control groups who used the original version of Nieuwe Buren without immediate feedback. This will allow us to establish whether automatic immediate feedback does indeed lead to global improvement in L2 pronunciation. A more detailed analysis of individual results within the experimental groups will then provide insight into the specific effects of different feedback errors generated by the system and their impact on learning. Students and teachers will be finally required to complete a questionnaire meant to establish the feedback system userfriendliness, comprehensibility and adequacy (the control group will, by contrast, report on learning without real-time feedback). The experiment and the tests will be subsequently repeated using an improved version of the system which also takes into account newly emerged needs. In this paper, we first provide an overview of the literature on second language pronunciation teaching and learning in order to derive some general guidelines for effective teaching. Second, we present an appraisal of available CALL systems for L2 pronunciation training with a view to identifying pros and cons. Finally, we describe the choices made for our research on the effects of erroneous automatic feedback on pronunciation.

A concept-based approach to support learning in a Web-based support environment

Abstract: Intelligent information handling support is crucial for the efficiency of web-based learning. This paper presents an approach to information handling, which implies conceptual support for both learners and instructors engaged in openlearning and teaching tasks in a web-based course support environment. The proposed approach combines two powerful techniques to support web-based course learning information retrieval and concept mapping. It involves conceptualisation of the subject domain and representation of the domain structure in an ontological way by a concept map, which is used for knowledge classification and indexing and allows for efficient information search. In addition, it includes strong visual presentation and graphical navigation of the subject domain and information search results and supports adaptive matching of the presentation to particular learners. AIMS an intelligent tool for task-based information handling support in web-based learning/training/work environments demonstrates the main ideas of this approach. AIMS can help a learner adaptively in information retrieving and information visualisation by using a learner model. AIMS has been used in several pilot experiments focused on evaluating system’s functionality and user interface. In this paper we discuss the important aspects of the proposed approach as implemented in AIMS from a learner’s perspective – how do they help the learner in performing learning tasks in a web-based course environment.