An intelligent semantic agent for supervising chat rooms in e-learning system

This paper presents an English chat room system in which students can discuss course by interacting with teachers and students. First, the novel mechanism provides learning angel agent and semantic agent that acts as supervisors constantly online to handle queries. Next, the mechanism also provides a QA subsystem that acts as assistant. The learning angel can detect syntax errors written by the online users. The semantic agent can check the semantic of each sentence. Sometimes learners may make semantic level mistakes. This implies that they don´t understand the course topic. The semantic agent can thus give some correction suggestions to users and analyze the data in the learner corpus. Moreover, when users query the system, the system attempts to find the answer from the knowledge ontology or learner corpus. Besides, if sufficient number of QA pairs has been accumulated, the FAQ can act as a powerful learning tool for the learners.