A Context-Based Information Agent for Supporting Education on the Web

In this paper, we present an attempt to support education on the Web. We take advantage of information that can be taken directly during a learning session in order to update domain knowledge. A new technique to structure domain knowledge is presented. We represent domain knowledge as a hierarchy of concepts. Each concept consists of some dominant meanings, and each of those is linked with some chunks (segments of information) to define it. Based on this structure, we define a context-based information agent that can monitor conversations among a community of on-line learners, interpret the learners' inputs, and then assess the current context of the session. It is able to build a new query to get updated information from the Web. Then, it can filter the results, organizing, and presenting information useful to the learners in their current activities. We claim that specifying the context of a search better can significantly improve search results. An important task, therefore, is to assess the context based on dominant meaning space. That is a new set based measure to evaluate the closeness between queries and documents. Our experiments show that the proposed method greatly improves retrieval effectiveness, in terms of average overall accuracy.