An official website of the United States government
Abstract In this study, we used Epistemic Network Analysis (ENA) to represent data generated by Natural Language Processing (NLP) analytics during an activity based on the Knowledge Integration (KI) framework. The activity features a web-based adaptive dialog about energy transfer in photosynthesis and cellular respiration. Students write an initial explanation, respond to two adaptive prompts in the dialog, and write a revised explanation. The NLP models score the KI level of the initial and revised explanations. They also detect the ideas in the explanations and the dialog responses. The dialog uses the detected ideas to prompt students to elaborate and refine their explanations. Participants were 196 8th-grade students at a public school in the Western United States. We used ENA to represent the idea networks at each KI score level for the revised explanations. We also used ENA to analyze the idea trajectories for the initial explanation, the two dialog responses, and the final explanation. Higher KI levels were associated with more links and increased frequency of mechanistic ideas in ENA representations. Representation of the trajectories suggests that the NLP adaptive dialog helped students who started with descriptive and macroscopic ideas to add more microscopic ideas. The dialog also helped students who started with partially linked ideas to keep linking the microscopic ideas to mechanistic ideas. We discuss implications for STEM teachers and researchers who are interested in how students build on their ideas to integrate their ideas.
more »
« less
Explaining Thermodynamics: Impact of an Adaptive Dialog Based on a Natural Language Processing Idea Detection Model
We explored how Natural Language Processing (NLP) adaptive dialogs that are designed following Knowledge Integration (KI) pedagogy elicit rich student ideas about thermodynamics and contribute to productive revision. We analyzed how 619 6-8th graders interacted with two rounds of adaptive dialog on an end-of-year inventory. The adaptive dialog significantly improved students’ KI levels. Their revised explanations are more integrated across all grades, genders, and prior thermodynamics experiences. The dialog elicited many additional ideas, including normative ideas and vague reasoning. In the first round, students refined their explanation to focus on their normative ideas. In the second round they began to elaborate their reasoning and add new normative ideas. Students added more mechanistic ideas about conductivity, equilibrium, and the distinction between how an object feels and its temperature after the dialog. Thus, adaptive dialogs are a promising tool for scaffolding science sense-making.
more »
« less
- Award ID(s):
- 2101669
- PAR ID:
- 10510557
- Editor(s):
- Blikstein, P; Van_Aalst, J; Kizito, R; Brennan, K
- Publisher / Repository:
- International Society of the Learning Sciences
- Date Published:
- Page Range / eLocation ID:
- 1306 to 1309
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Students benefit from dialogs about their explanations of complex scientific phenomena, and middle school science teachers cannot realistically provide all the guidance they need. We study ways to extend generative teacher–student dialogs to more students by using AI tools. We compare Responsive web-based dialogs to General web-based dialogs by evaluating the ideas students add and the quality of their revised explanations. We designed the General guidance to motivate and encourage students to revise their explanations, similar to how an experienced classroom teacher might instruct the class. We designed the Responsive guidance to emulate a student–teacher dialog, based on studies of experienced teachers guiding individual students. The analyses comparing the Responsive and the General condition are based on a randomized assignment of a total sample of 507 pre-college students. These students were taught by five different teachers in four schools. A significantly higher proportion of students added new accurate ideas in the Responsive condition compared to the General condition during the dialog. This research shows that by using NLP to identify ideas and assign guidance, students can broaden and refine their ideas. Responsive guidance, inspired by how experienced teachers guide individual students, is more valuable than General guidance.more » « less
-
Blikstein, P; Van_Aalst, J; Kizito, R; Brennan, K (Ed.)This study takes advantage of advances in Natural Language Processing (NLP) to build an idea detection model that can identify ideas grounded in students’ linguistic experiences. We designed adaptive, interactive dialogs for four explanation items using the NLP idea detection model and investigated whether they similarly support students from distinct language backgrounds. The curriculum, assessments, and scoring rubrics were informed by the Knowledge Integration (KI) pedagogy. We analyzed responses of 1,036 students of different language backgrounds taught by 10 teachers in five schools in the western United States. The adaptive dialog engages students from both monolingual English and multilingual backgrounds in incorporating additional relevant ideas into their explanations, resulting in a significant improvement in student responses from initial to revised explanations. The guidance supports students in both language groups to progress in integrating their scientific ideas.more » « less
-
This study explores how the interplay between data analysis and model design shifts 6th-grade students' understanding of diffusion from simple to sophisticated mechanistic reasoning and from non-canonical to canonical ideas about diffusion. Using mixed-methods qualitative analysis, we determine students' mechanistic reasoning and ideas about diffusion at five different points in a curricular sequence using a new tool for computational modeling called MoDa. With this data, we present a framework for the relationship between students' developing mechanistic reasoning and their canonical understanding, suggesting that they develop independently. Further, we illustrate how the computational modeling environment, MoDa, used in this study pushed students' mechanistic reasoning toward sophistication. Moreover, in allowing them to explore non-canonical mechanisms, MoDa supported their convergence on canonical scientific ideas about diffusion.more » « less
-
Uncertainty is an important concept in physics laboratory instruction. However, little work has examined how students reason about uncertainty beyond the introductory (intro) level. In this work we aimed to compare intro and beyond-intro students’ ideas about uncertainty. We administered a survey to students at 10 different universities with questions probing procedural reasoning about measurement, student-identified sources of uncertainty, and predictive reasoning about data distributions. We found that intro and beyond-intro students answered similarly on questions where intro students already exhibited expert-level reasoning, such as in comparing two data sets with the same mean but different spreads, identifying limitations in an experimental setup, and predicting how a data distribution would change if more data were collected. For other questions, beyond-intro students generally exhibited more expertlike reasoning than intro students, such as when determining whether two sets of data agree, identifying principles of measurement that contribute to spread, and predicting how a data distribution would change if better data were collected. Neither differences in institutions, student majors, lab courses taken, nor research experience were able to fully explain the variability between intro and beyond-intro student responses. These results call for further research to better understand how students’ ideas about uncertainty develop beyond the intro level.more » « less
