An intelligent semantic agent for e-learning message communication

This paper presents an English chat room system in which students discuss course contents and ask questions to and receive from teachers and other students. A novel mechanism is also proposed that does not require that supervisors constantly remain online to handle queries. The mechanism contains an agent that detects syntax errors in sentences written by the online users and also checks the semantics of each sentence. Learners may make a semantic level mistake imply that they do not understanding the course topic or particular issue. The agent can thus offer recommendations to the user and analyze the data of the learner corpus. When users query the system or others, this system will attempt to find the answers from the knowledge ontology or learner corpus that is stored in the records of previous user comments. If sufficient numbers of QA pairs can be obtained, the FAQ can be provided for the learners.