Toward Automated Qualitative Analysis: Leveraging Large Language Models for Tutoring Dialogue Evaluation

Megan Gu, Chloe Qianhui Zhao, Claire Liu, Nikhil Patel, Jahnvi Shah, Jionghao Lin, Kenneth R. Koedinger. Toward Automated Qualitative Analysis: Leveraging Large Language Models for Tutoring Dialogue Evaluation. In Martin Hlosta, Ivan Moser, Amir Winer, Nitza Geri, Birte Heinemann, Sergej Görzen, Umesh Ramnarain, Christo van der Westhuizen, Mafor Penn, Alireza Gharahighehi, Rani Van Schoors, Paraskevi Topali, Jeroen Ooge, Brendan Flanagan, Owen H. T. Lu, Atsushi Shimada, Namrata Srivastava, Albert C. M. Yang, Hsiao-Ting Tseng, Fumiya Okubo, Eduardo Davalos Anaya, Hiroaki Ogata, Riordan Alfredo, Simon Buckingham Shum, Mutlu Cukurova, Yannis A. Dimitriadis, Charles Lang, Roberto Martínez Maldonado, Patricia Santos 0001, Olga Viberg, Andy Nguyen, Sanna Järvelä, Carolyn P. Rosé, Alyssa Wise, Michail Giannakos, Kshitij Sharma, Luna Huynh, Amanda Barany, Ryan Shaun Baker, Jionghao Lin, Andrew Katz, Maurice Boothe Jr., Xavier Ochoa 0001, David J. Gagnon, Luke Swanson, Erik Harpstead, editors, Joint Proceedings of LAK 2025 Workshops co-located with 15th International Conference on Learning Analytics and Knowledge (LAK 2025), Dublin, Ireland, March 3-4, 2025. Volume 3995 of CEUR Workshop Proceedings, pages 190-193, CEUR-WS.org, 2025. [doi]