A Multi-Agent System of Semantic Analysis and Filtering of Modeled Traces to Calculate Interaction Indicators Favoring Collaboration in LMS

This research work presents a traces engineering method for 1/interactive traces visualization and 2/computation of indicators helping to enhance collaboration in Learning Management Systems (LMS). The aims is to extend the LMS features by incorporating the intelligence of the multi-agents approach, semantic Web technologies and cloud computing services in order to intelligently support collaborative learning. The proposed system is implemented as a LMS based on a cloud architecture and integrating a multi-agents based-system for traces collection and content analysis and filtering. Data collected are modeled, stored, transformed, analyzed and filtered in order to visualize traces and calculate interaction indicators helping tutors to make optimal decisions supporting collaboration. The proposed approach is implemented through a representative prototype. The paper presents the graphical interface of the tool with some examples of computation of indicators of a social nature.