Computational Modeling of the Effects of the Science Writing Heuristic on Student Critical Thinking in Science Using Machine Learning

Abstract

This study is intended to provide an example of computational modeling (CM) experiment using machine learning algorithms. Specific outcomes modeled in this study are the predicted influences associated with the Science Writing Heuristic (SWH) and associated with the completion of question items for the Cornell Critical Thinking Test. The Student Task and Cognition Model in this study uses cognitive data from a large-scale randomized control study. Results of the computational model experiment provide for the possibility to increase student success via targeted cognitive retraining of specific cognitive attributes via the SWH. This study also illustrates that computational modeling using machine learning algorithms (MLA) is a significant resource for testing educational interventions, informs specific hypotheses, and assists in the design and development of future research designs in science education research.

The application of AI technologies in STEM education: a systematic review from 2011 to 2021

“…Artificial Intelligence in Education (AIEd), as an interdisciplinary field, emphasizes applying AI to assist instructor's instructional process, empower student's learning process, and promote the transformation of educational system (Chen et al, 2020;Holmes et al, 2019;Hwang et al, 2020;Ouyang & Jiao, 2021). First, AIEd has potential to enhance instructional design and pedagogical development in the teaching processes, such as accessing students' performance automatically (Wang et al, 2011;Zampirolli et al, 2021), monitoring and tracking students' learning (Berland et al, 2015;Ji & Han, 2019), and predicting at-risk students (Hellings & Haelermans, 2020;Lamb et al, 2021). Second, AIEd is beneficial for improving student-centered learning, such as providing adaptive tutoring (Kose & Arslan, 2017; Myneni et al, 2013), recommending personalized learning resources (Ledesma & García, 2017;Zhang et al, 2020), and diagnosing students' learning gaps (Liu et al, 2017).…”

A Coordinated and Optimized Mechanism of Artificial Intelligence for Student Management by College Counselors Based on Big Data

“…The aim is to cultivate the emerging vitality and endogenous momentum of the innovative development of collaborative ideological and political work in colleges and universities and promote the development of socialist education with Chinese characteristics in the new era. Finally, under the technological push represented by big data, we scientifically investigated and assessed the growth trend of collaborative education of ideological and political activity in colleges and universities [ 16 ]. Due to the limitation of data saving and processing ability, under the scientific data analysis method, the sampling method of data is to take part of sample data in the full set of data and infer the overall characteristics of the full set of data through the analysis of the sample data.…”

Physics language and language use in physics—What do we know and how AI might enhance language-related research and instruction

“…Increasing clarity and elaboration also raises reading comprehension for science texts [125]. Evidence from intervention studies suggests that language-sensitive learning materials can help students in their development of conceptual understanding [126]. For example, the Science Writing Heuristic engages students in immersive argumentative writing (producing language), and evidently supports argumentative skills, metacognition, and other important outcomes [126][127][128].…”