We provide intuitive, objective and reliable metrics for evaluating the participants of a discussion based on a basic set of roles. This method can be applied to any temporally ordered discussion transcript. We show that it is possible to partially automate the evaluation process by defining numerical attributes which can be extracted automatically from the content of discussion transcripts. We demonstrate its application to chat groups using the microblogging application Twitter.
The analysis finally produces a score-sheet for each chat:
These score-sheets can be used to compare participants to each other on different scales and can be used to get a brief profile of them:
Based on this profile (and other considerations), rewards could be given to the participants performing well.
Back to Home