From Learner Information Packages to Student Models: Which Continuum?

Author(s):  
Lahcen Oubahssi ◽  
Monique Grandbastien
Keyword(s):  
1994 ◽  
Vol 40 (3) ◽  
pp. 497-508 ◽  
Author(s):  
Menucha Birenbaum ◽  
Anthony E. Kelly ◽  
Kikumi K. Tatsuoka ◽  
Yaffa Gutvirtz
Keyword(s):  

Water ◽  
2020 ◽  
Vol 12 (4) ◽  
pp. 1040 ◽  
Author(s):  
Diane Lally ◽  
Cory Forbes

One of the keys to science and environmental literacy is systems thinking. Learning how to think about the interactions between systems, the far-reaching effects of a system, and the dynamic nature of systems are all critical outcomes of science learning. However, students need support to develop systems thinking skills in undergraduate geoscience classrooms. While systems thinking-focused instruction has the potential to benefit student learning, gaps exist in our understanding of students’ use of systems thinking to operationalize and model SHS, as well as their metacognitive evaluation of systems thinking. To address this need, we have designed, implemented, refined, and studied an introductory-level, interdisciplinary course focused on coupled human-water, or sociohydrologic, systems. Data for this study comes from three consecutive iterations of the course and involves student models and explanations for a socio-hydrologic issue (n = 163). To analyze this data, we counted themed features of the drawn models and applied an operationalization rubric to the written responses. Analyses of the written explanations reveal statistically-significant differences between underlying categories of systems thinking (F(5, 768) = 401.6, p < 0.05). Students were best able to operationalize their systems thinking about problem identification (M = 2.22, SD = 0.73) as compared to unintended consequences (M = 1.43, SD = 1.11). Student-generated systems thinking models revealed statistically significant differences between system components, patterns, and mechanisms, F(2, 132) = 3.06, p < 0.05. Students focused most strongly on system components (M = 13.54, SD = 7.15) as compared to related processes or mechanisms. Qualitative data demonstrated three types of model limitation including scope/scale, temporal, and specific components/mechanisms/patterns excluded. These findings have implications for supporting systems thinking in undergraduate geoscience classrooms, as well as insight into links between these two skills.


AI Magazine ◽  
2013 ◽  
Vol 34 (3) ◽  
pp. 13-26 ◽  
Author(s):  
Cristina Conati ◽  
Samad Kardan

The field of intelligent tutoring systems has successfully delivered techniques and applications to provide personalized coaching and feedback for problem solving in a variety of domains. The core of this personalized instruction is a student model; the ITS component in charge of assessing student traits and states relevant to tailor the tutorial interaction to specific student needs during problem solving. There are however, other educational activities that can help learners acquire the target skills and abilities at different stages of learning including, among others, exploring interactive simulations and playing educational games. This article describes research on creating student models that support personalization for these novel types of interactions, their unique challenges, and how AI and machine learning can help.


Sign in / Sign up

Export Citation Format

Share Document