Limongelli-Research-Activity

Recent Research Activity
Artificial Intelligence Methodologies and technologies for e-learning. The research mainly focuses on Intelligent Adaptive Learning Environments, User Modeling and User-Adapted Interaction, and collaborative learning environments. In particular, LS-Plan, a framework for personalization and adaptation in e-learning, is a prototype proposed for automatic sequencing of e-learning courses. Adaptation is meant, with respect to the knowledge possessed by the learner and her learning styles, both evaluated prior of the course and maintained during course fruition. LS-Plan has been integrated into Moodle Learning Management System. Present work focuses on the following topics:
Retrieval of didactic materials. In particular, she has been developed social-based approach for retrieving and sequencing didactic materials from the web and from Learning Objects Repositories. Community of practice for sharing material and experiences among teachers. The first step has been the study of Community of Practice (CoPs) she has presented a first study of a Community of Practice of teachers, involved in Vocational Education and Training (VET), aiming at learning the use of Web 2.0 tools and applications to support the learning process of their pupils. The experiment involved the use of a CoP providing an educational program on Web2.0 Technologies for education for Vocational Education and Training teachers. The CoP was designed based on the foundational Wenger’s concepts of domain, community and practice. In particular, we present a study of some social aspects of the CoP dynamics, basing our study on some evaluation metrics coming from the Social Network Analysis research area, i.e., using metrics such as betweenness, centrality, and closeness, in order to elicit useful relationships information. Social collaboration tools, to support the process of course construction. Such a process comprises several distinct steps, from concept mapping, through selection of suitable learning material, to the final stages of delivery in a Learning Management System. The support we foresee should exploit the knowledge of the entire teaching community, in which the teacher acts, to help her/him in doing the job described above. By “knowledge”, we mean basically a representation of the ways of usage of learning materials, by the teachers in the community for their courses. To start on a solid footing, here we address the topic of modeling the teacher. The model we define aims to give teachers a personalized support, encompassing consideration for their own pedagogy, teaching styles, and teaching experience during course creation. Recommendation systems to support the operations of retrieving, analyzing, and importing LOs from a set of standard Learning Objects Repositories. In particular, a recommendation system has been designed to support the teacher in the phases of (i) retrieval of LOs, through a keyword-based search mechanism applied to the selected repositories. (ii) analysis of the returned LOs, whose information is enriched by a concept of relevance metric, based on both the results of the searching operation and the data related to the previous use of the LOs in the courses managed by the Learning Management System. (iii) LO importation into the course under construction. Automatic extraction and recommendation of learning material from Wikipedia. With its 5,006,202 articles, 49 millions of registered people and on average 800 new articles per day, Wikipedia provides a knowledge base for teachers and instructional designers to build didactic materials. It is a matter of facts that teachers consult this encyclopedia to arrange, integrate or enrich their courses. Moreover, with the exponential growth of the Internet, didactic materials are freely available and usable by teachers, instructional designers and students from Learning Objects Repositories such as Merlot or Ariadne and others. On the other hand, the designing and delivering of a new course is a crucial task for teachers that have to face two main problems: building, or retrieving, and sequencing learning materials. Retrieving learning materials requires a great effort and waste of time, while sequencing learning materials requires an accurate didactic project. We are developing a sequencing engine of learning materials, embedded inside the “Wiki Course Builder” system, a system capable to retrieve and sequence Wikipedia web pages based on a teacher model based on the Grasha teaching styles and on a social didactic approach. In particular, the main goal of the system is to support teachers building on-the-fly courses, i.e., building courses quickly, by means of few clicks of the mouse. An important feature of the system is represented by its capability to allow teachers to interact with the recommended learning path through a graph-based graphic interface where teachers can directly modify the proposed learning path adding or deleting WikipeDia pages. Extracting information for establishing didactic dependencies between Wikipedia pages. We have proposed and experimented a light-weight formalization of the LO, and how it can be “represented” by a set of WikiPedia Pages (“topics”); then we show how such set of topics, together with a set of hypotheses we defined in regard, can help deciding on the dependence relationship holding between two LOs. In this endeavor, we exploit the classification in categories available for the WikiPedia topics, and obtain interesting results for our framework, in terms of precision and recall of the dependence relationships.

List of publications from the DBL Bibliography Server

List of publications and citations from Google Scholar

Created