Teachable agents are pedagogical agents that employ the ‘learning-by-teaching’ strategy, which facilitates learning by encouraging students to construct explanations, reflect on misconceptions, and elaborate on what they know. Teachable agents present unique opportunities to maximize the benefits of a ‘learning-by-teaching’ experience. For example, teachable agents can provide socio-emotional support to learners, influencing learner self-efficacy and motivation, and increasing learning. Prior work has found that a teachable agent which engages learners socially through social dialogue and paraverbal adaptation on pitch can have positive effects on rapport and learning. In this work, we introduce Emma, a teachable robotic agent that can speak socially and adapt on both pitch and loudness. Based on the phenomenon of entrainment, multi-feature adaptation on tone and loudness has been found in human-human interactions to be highly correlated to learning and social engagement. In a study with 48 middle school participants, we performed a novel exploration of how multi-feature adaptation can influence learner rapport and learning as an independent social behavior and combined with social dialogue. We found significantly more rapport for Emma when the robot both adapted and spoke socially than when Emma only adapted and indications of a similar trend for learning. Additionally, it appears that an individual’s initial comfort level with robots may influence how they respond to such behavior, suggesting that for individuals who are more comfortable interacting with robots, social behavior may have a more positive influence.
more »
« less
Designing an Adaptive Dialogue to Promote Science Understanding
We used Natural Language Processing (NLP) to design an adaptive computer dialogue that engages students in a conversation to reflect on and revise their written explanations of a science dilemma. We study the accuracy of the NLP idea detection. We analyze how 98 12-13 year-olds interacted with the dialogue as a part of a Diagnostic Inventory. We study students’ initial and revised science explanations along with their logged responses to the dialogue. The dialogue led to a high rate of student revision compared to prior studies of adaptive guidance. The adaptive prompt encouraged students to reflect on prior experiences, to consider new variables, and to raise scientific questions. Students incorporated these new ideas when revising their initial explanations. We discuss how these adaptive dialogues can strengthen science instruction.
more »
« less
- Award ID(s):
- 2101669
- NSF-PAR ID:
- 10330141
- Date Published:
- Journal Name:
- Proceedings of the 16th International Conference of the Learning Sciences - ICLS 2022
- Page Range / eLocation ID:
- 1653-1656
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Teachable agents are pedagogical agents that employ the 'learning-by-teaching' strategy, which facilitates learning by encouraging students to construct explanations, reflect on misconceptions, and elaborate on what they know. Teachable agents present unique opportunities to maximize the benefits of a 'learning-by-teaching' experience. For example, teachable agents can provide socio-emotional support to learners, influencing learner self-efficacy and motivation, and increasing learning. Prior work has found that a teachable agent which engages learners socially through social dialogue and paraverbal adaptation on pitch can have positive effects on rapport and learning. In this work, we introduce Emma, a teachable robotic agent that can speak socially and adapt on both pitch and loudness. Based on the phenomenon of entrainment, multi-feature adaptation on tone and loudness has been found in human-human interactions to be highly correlated to learning and social engagement. In a study with 48 middle school participants, we performed a novel exploration of how multi-feature adaptation can influence learner rapport and learning as an independent social behavior and combined with social dialogue. We found significantly more rapport for Emma when the robot both adapted and spoke socially than when Emma only adapted and indications of a similar trend for learning. Additionally, it appears that an individual’s initial comfort level with robots may influence how they respond to such behavior, suggesting that for individuals who are more comfortable interacting with robots, social behavior may have a more positive influence.more » « less
-
null (Ed.)This NSF EAGER research paper investigates how undergraduate STEM and engineering students’ learning trajectories evolve over time, from 1st to senior year, along a novice to expert spectrum. We borrow the idea of “learning trajectories” from mathematics education that can paint the evolution of students’ knowledge and skills over time over a set of learning experiences. Curricula for undergraduate engineering programs can reflect an intended pathway of knowledge construction within a discipline. We intend our study of individual students within undergraduate STEM and engineering programs can highlight how this may happen in situ and how it may be similar or might differ from a given, prescribed programs of study among disciplines. We use a theoretical framework based in adaptive expertise and design thinking adaptive expertise to develop a design learning continuum further. Envisioned routes through disciplinary undergraduate curricula and student conceptions of their design process are explored through qualitative, semi-structured interviews with undergraduate 1st year and senior year students across STEM, engineering and non-STEM field such as computer science, mechanical engineering, general engineering, mathematics, science, English, and art. We also conduct similar interviews with faculty in these fields who are responsible and knowledgeable for undergraduate programs about their perceived benefits for the structure of their program’s curriculum. Additional information is collected from noticing the organizational and pedagogical structures of the relative undergraduate curriculum. Initial findings/outcomes suggest that traditions to knowledge construction both differ across disciplinary approaches and have similarities across non-obvious disciplinary relationships. Faculty have a firm understanding of how one class chains from one to another; students have less of a field of view for how mindful chunks of knowledge combine together.more » « less
-
Examining the effect of automated assessments and feedback on students’ written science explanationsWriting scientific explanations is a core practice in science. However, students find it difficult to write coherent scientific explanations. Additionally, teachers find it challenging to provide real-time feedback on students’ essays. In this study, we discuss how PyrEval, an NLP technology, was used to automatically assess students’ essays and provide feedback. We found that students explained more key ideas in their essays after the automated assessment and feedback. However, there were issues with the automated assessments as well as students’ understanding of the feedback and revising their essays.more » « less
-
The way high school chemistry curricula are structured has the potential to convey consequential messages about knowledge and knowing to students and teachers. If a curriculum is built around practicing skills and recalling facts to reach “correct” answers, it is unlikely class activities will be seen (by students or the teacher) as opportunities to figure out causes for phenomena. Our team of teachers and researchers is working to understand how enactment of transformed curricular materials can support high school chemistry students in making sense of perplexing, relatable phenomena. Given this goal, we were surprised to see that co-developers who enacted our materials overwhelmingly emphasized the importance of acquiring true facts/skills when writing weekly reflections. Recognition that teachers’ expressed aims did not align with our stated goal of “supporting molecular-level sensemaking” led us to examine whether the tacit epistemological commitments reflected by our materials were, in fact, consistent with a course focused on figuring out phenomena. We described several aspects of each lesson in our two-semester curriculum including: the role of phenomena in lesson activities, the extent to which lessons were 3-dimensional, the role of student ideas in class dialogue, and who established coherence between lessons. Triangulation of these lesson features enabled us to infer messages about valued knowledge products and processes materials had the potential to send. We observed that our materials commonly encouraged students to mimic the structure of science practices for the purpose of being evaluated by the teacher. That is, students were asked to “go through the motions” of explaining, modeling etc. but had little agency regarding the sorts of models and explanations they found productive in their class community. This study serves to illustrate the importance of surfacing the tacit epistemological commitments that guide curriculum development. Additionally, it extends existing scholarship on epistemological messaging by considering curricular materials as a potentially consequential sources of messages.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
