Predicting Learner’s Project Performance with Dialogue Features in Online Q&A Discussions

Jaebong Yoo, Jihie Kim

Although many college courses adopt online tools such as Q&A online discussions, there is no easy way to evaluate their impact on learning. In this paper, we investigate a predictive relation between characteristics of discussion contributions and student performance. For the modeling dynamics of conversational dialogue, speech acts (Q&A dialog roles that participants play) and emotional features covered by LIWC (Linguistic Inquiry and Word Count) were used. These dialogue information is used for correlation and regression analyses for predicting the performance of learners (173 student groups). Our current results indicate that the number of answers provided to others, the degree of positive emotion expressions, and how early students exchange information before the deadline correlate with project grades. This finding confirms the argument that in assessing student online activities, we need to capture how they interact, not just what they produce.

The final publication is available at Springer via https://doi.org/10.1007/978-3-642-30950-2_74.