Supervisor: pantelis papadopoulos
Collaborative conversational agents (CCAs) based on artificial intelligent (AI) can analyze student dialogue and intervene as teacher would to make the dialogue more productive. The intervention strategy (what to say, when to talk, who to address, etc.) is based on Michaels and O’Connor’s Academically Productive Talk framework (2015) according to which an intervention can make a student dialogue more productive when it serves one of the following four goals:
- Goal 1—“Help individual students share their own thoughts”
- Goal 2—“Help students orient to and listen carefully to one another”
- Goal 3—“Help students deepen their reasoning”
- Goal 4—“Help students engage with others' reasoning”
While this model is widely used, it is still not clear what is the relationship of the four goals within a dialogue and whether there are patterns in their appearance. For example, it is logical to expect that there is a progress from G1 to G4 (i.e., students cannot end up discussing and building upon each other’s contributions unless they have shared their thoughts, reasoning, and have listen to each other).
At the same time, when students collaborate on a given problem, their dialogue goes through phases (e.g., problem-solving phases or problem identification, idea generation, idea evaluation, and solution). Therefore, it is interesting to analyze how the four goals appear within a dialogue in a collaborative problem-solving activity.
The internship will focus on analyzing dialogue characteristics, identifying moments where the four goals are met, and exploring whether there are patterns that could further improve our knowledge on student dialogues and improve the design of CCAs.
METHOD
The internship will use both qualitative and quantitative methods. Already recorded dialogues will be analyzed using Atlas.ti, while the validation of coding, the identification of patterns, and a comparison of dialogues with different characteristics will be based on inferential statistical analysis.
REFERENCES
Michaels, S., & O'Connor, C. (2015). Conceptualizing talk moves as tools: Professional development approaches for academically productive discussions. In L. B. Resnick, C. Asterhan, & S. N. Clarke (Eds.), Socializing intelligence through talk and dialogue (pp. 347–362). American Educational Research Association. https://doi.org/10.3102/978-0-935302-43-1_27
de Araujo, A., Papadopoulos, P. M., McKenney, S., & de Jong, T. (2024). A learning analytics-based collaborative conversational agent to foster productive dialogues in inquiry learning, Journal of Computer Assisted Learning. https://doi.org/10.1111/jcal.13007
Tegos, S., Demetriadis, S., Papadopoulos, P. M., Weinberger, A. (2016). Conversational Agents for Academically Productive Talk: A Comparison of Directed and Undirected Agent Interventions. International Journal of Computer-Supported Collaborative Learning, 11(4), 417-440. https://doi.org/10.1007/s11412-016-9246-2