Exploring Induced Pedagogical Strategies through a Markov Decision Process Framework: Lessons Learned

Autor/inn/en	Shen, Shitian; Mostafavi, Behrooz; Barnes, Tiffany; Chi, Min
Titel	Exploring Induced Pedagogical Strategies through a Markov Decision Process Framework: Lessons Learned
Quelle	In: Journal of Educational Data Mining, 10 (2018) 3, S.27-68 (42 Seiten) PDF als Volltext Verfügbarkeit
Sprache	englisch
Dokumenttyp	gedruckt; online; Zeitschriftenaufsatz
ISSN	2157-2100
Schlagwörter	Teaching Methods; Markov Processes; Decision Making; Rewards; Correlation; Intelligent Tutoring Systems; Student Behavior; Academic Achievement; Guidelines; Reinforcement; Problem Solving; Mathematics Instruction; Equations (Mathematics); Course Descriptions; Data Analysis; Pretests Posttests; Mathematics Tests; North Carolina + Suchen Sie Ihr Suchwort? Teaching method; Lehrmethode; Unterrichtsmethode; Markowscher Prozess; Decision-making; Entscheidungsfindung; Reward; Belohnung; Korrelation; Intelligentes Tutorsystem; Student behaviour; Schülerverhalten; Schulleistung; Richtlinien; Positive Verstärkung; Problemlösen; Mathematics lessons; Mathematikunterricht; Equations; Mathematics; Gleichungslehre; Kursstrukturplan; Auswertung
Abstract	An important goal in the design and development of Intelligent Tutoring Systems (ITSs) is to have a system that adaptively reacts to students' behavior in the short term and effectively improves their learning performance in the long term. Inducing effective pedagogical strategies that accomplish this goal is an essential challenge. To address this challenge, we explore three aspects of a Markov Decision Process (MDP) framework through four experiments. The three aspects are: 1) "reward function," detecting the impact of immediate and delayed reward on effectiveness of the policies; 2) "state representation," exploring ECR-based, correlation-based, and ensemble feature selection approaches for representing the MDP state space; and 3)"policy execution," investigating the effectiveness of stochastic and deterministic policy executions on learning. The most important result of this work is that there exists an aptitude-treatment interaction (ATI) effect in our experiments: the policies have significantly different impacts on the particular types of students as opposed to the entire population. We refer the students who are sensitive to the policies as the Responsive group. All our following results are based on the Responsive group. First, we find that an immediate reward can facilitate a more effective induced policy than a delayed reward. Second, The MDP policies induced based on low correlation-based and ensemble feature selection approaches are more effective than a Random yet reasonable policy. Third, no significant improvement was found using stochastic policy execution due to a ceiling effect. (As Provided).
Anmerkungen	International Working Group on Educational Data Mining. e-mail: jedm.editor@gmail.com; Web site: http://jedm.educationaldatamining.org/index.php/JEDM
Erfasst von	ERIC (Education Resources Information Center), Washington, DC
Update	2020/1/01