Recommendation of complementary material during chat discussions

Abstract

In the context of Internet, there are many tools that allow sharing knowledge. Examples of these tools are Web chats. However it is possible to use Web chats in a more effective way. In this sense, this paper presents a system that analyzes the themes discussed in a chat room and then recommends information sources according to the context of the discussion. In order to produce recommendations, the system considers users’ profiles to complement the knowledge of each individual, reaching what Vygotsky called zone of proximal development. Another important feature is related to the fact that, after the chat discussion session, it is possible to generate statistical analyses. These analyses allow evaluating the discussion (e.g. how many different subjects were discussed, discussion deviate) and thus the knowledge of the whole community and of each member (e.g. about what subject a participant is talking). The system uses text mining techniques to identify the themes discussed in the chat room.