Messages segmentation of asynchronous text-based discussion in social network analysis

Social network analysis (SNA) is often employed by teachers and researchers to analyze online asynchronous discussion in e-learning to serve various purposes regarding the communication structure of the group and other structural characteristics of the discussion forum. Usually, SNA determine the level of participation in online asynchronous discussion based on number of messages even though this message consist of only one word or one sentence. However, it is not fair for participants who send or post a message that consist of several sentences. The main idea to handle these problems is to segment the message into sentences unit, which will be more appropriate than their equivalent message. This paper discusses the difference between the SNA result using message and it equivalent sentences as unit interaction. The visual representation of the interaction in a map and graph are demonstrated and explained. It also describes the message segmentation procedure to break a message into sentences and examine whether sentence as a single unit of interaction can satisfy the assessment of participation level in SNA. The result shows that sentence unit able to determine the students´ participation in more objective way compared to messages in term of communication structures in online discussion.