Predicting Student Learning from Conversational Cues

• Published in: Intelligent Tutoring Systems pp. 220 - 229
• Main Authors: Adamson, David, Bharadwaj, Akash, Singh, Ashudeep, Ashe, Colin, Yaron, David, Rosé, Carolyn P.
• Format: Book Chapter
• Language: English
• Published: Cham Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: Computer-Supported Collaborative Learning; Discourse Analysis; Educational Data Mining
• ISBN: 331907220X; 9783319072203
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-319-07221-0_26

In the work here presented, we apply textual and sequential methods to assess the outcomes of an unconstrained multiparty dialogue. In the context of chat transcripts from a collaborative learning scenario, we demonstrate that while low-level textual features can indeed predict student success, models derived from sequential discourse act labels are also predictive, both on their own and as a supplement to textual feature sets. Further, we find that evidence from the initial stages of a collaborative activity is just as effective as using the whole.