Multimodal Learning Analytics and Predictive Student Modeling for Game-Based Learning

Autor/in	Emerson, Andrew John
Titel	Multimodal Learning Analytics and Predictive Student Modeling for Game-Based Learning
Quelle	(2021), (165 Seiten) PDF als Volltext Verfügbarkeit Ph.D. Dissertation, North Carolina State University
Sprache	englisch
Dokumenttyp	gedruckt; online; Monographie
ISBN	979-8-3796-4984-5
Schlagwörter	Hochschulschrift; Dissertation; Learning Analytics; Prediction; Game Based Learning; Student Behavior; Outcomes of Education; Individualized Instruction; Biology; Science Instruction; Nonverbal Communication; Eye Movements + Suchen Sie Ihr Suchwort? Thesis; Dissertations; Academic thesis; Vorhersage; Student behaviour; Schülerverhalten; Lernleistung; Schulerfolg; Individualisierender Unterricht; Biologie; Teaching of science; Science education; Natural sciences Lessons; Naturwissenschaftlicher Unterricht; Non-verbal communication; Nonverbale Kommunikation; Augenbewegung
Abstract	A distinctive feature of game-based learning environments is their capacity to create learning experiences that are both effective and engaging. Recent advances in sensor technologies (e.g., facial expression analysis and gaze tracking) and natural language processing have introduced the opportunity to leverage multimodal data streams for learning analytics. Learning analytics informed by multimodal data captured during students' interactions with game-based learning environments hold significant promise for developing a deeper understanding of game-based learning, designing game-based learning environments to detect unproductive student behaviors, and informing adaptive scaffolding to support game-based learning. Further, learning analytics frameworks that can accurately predict student learning outcomes early in students' interactions hold considerable promise for enabling environments to adapt to individual student needs. This dissertation investigates a multimodal, multi-task predictive student modeling framework for informing individualized learning in game-based learning environments. The framework is evaluated on two corpora of game-based learning interactions from two distinct student populations who interacted with two versions of CRYSTAL ISLAND, a game-based learning environment for microbiology education. The framework leverages available multimodal data channels from the corpora to simultaneously predict student post-test performance and interest. In CRYSTAL ISLAND -- SENSOR-BASED, student facial expressions, eye gaze, and gameplay behaviors are used to predict these outcomes at early points during interactions, and in CRYSTAL ISLAND -- REFLECTION, textual representations of student reflections and gameplay are used. In addition to inducing models for each corpus individually, this dissertation investigates the ability to leverage information from one corpus to improve models based on another (i.e., transfer learning through the use of pre-trained models). This dissertation reports on research on multimodal learning analytics, multi-task machine learning, and early prediction. Previous work has shown that multimodal models of student posttest performance and interest outperform unimodal models. Additionally, predictive models that incorporate multi-task learning have achieved improved accuracy compared to single-task models when predicting student performance on post-tests. Preliminary work has also demonstrated the efficacy of early prediction approaches for forecasting student performance. The dissertation research extends these approaches by combining them into a unified framework that makes predictions early during game-based learning. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.] (As Provided).
Anmerkungen	ProQuest LLC. 789 East Eisenhower Parkway, P.O. Box 1346, Ann Arbor, MI 48106. Tel: 800-521-0600; Web site: http://www.proquest.com/en-US/products/dissertations/individuals.shtml
Erfasst von	ERIC (Education Resources Information Center), Washington, DC
Update	2024/1/01