Predictive Student Modeling in Game-Based Learning Environments with Word Embedding Representations of Reflection
- PDF / 1,007,511 Bytes
- 23 Pages / 439.37 x 666.142 pts Page_size
- 67 Downloads / 214 Views
Predictive Student Modeling in Game-Based Learning Environments with Word Embedding Representations of Reflection Michael Geden 1 & Andrew Emerson 1 Roger Azevedo 2 & James Lester 1
& Dan
Carpenter 1 & Jonathan Rowe 1 &
Accepted: 23 September 2020/ # International Artificial Intelligence in Education Society 2020
Abstract Game-based learning environments are designed to provide effective and engaging learning experiences for students. Predictive student models use trace data extracted from students’ in-game learning behaviors to unobtrusively generate early assessments of student knowledge and skills, equipping game-based learning environments with the capacity to anticipate student outcomes and proactively deliver adaptive scaffolding or notify instructors. Reflection is a key component of self-regulated learning, and it is critical in effective learning. However, there is currently limited work exploring the utility of reflection for inducing accurate predictive student models. This article presents a predictive student modeling framework that leverages natural language responses to in-game reflection prompts to predict student learning outcomes in a game-based learning environment for middle school microbiology, CRYSTAL ISLAND. With data from a pair of classroom studies involving 118 middle school students, we investigate the accuracy of early prediction models that utilize features extracted from student trace data combined with word embedding-based representations (i.e., GloVe, ELMo) of student reflection responses. We evaluate the accuracy of the predictive models over time using data from incremental segments of each student’s interaction with the game-based learning environment, and we compare against models that omit student reflection features. Results reveal that models encoding students’ natural language reflections with ELMo word embeddings yield significantly improved accuracy compared to other representations, with the greatest accuracy demonstrated by an ensemble of predictive models. We discuss the implications of these results for the design of game-based learning environments. Keywords Student modeling . Early prediction . Game-based learning environments . Self-
regulated learning . Reflection
* Andrew Emerson [email protected] Extended author information available on the last page of the article
International Journal of Artificial Intelligence in Education
Introduction Game-based learning holds considerable potential for student engagement, learning, and motivation (de Freitas 2018; Plass et al. 2020; Qian and Clark 2016). Because game-based learning environments can create learning experiences that are effective and engaging, they have shown success across a diverse range of subject matter (Brezovszky et al. 2019; Pesare et al. 2016; Tsatsou et al. 2019). Game-based learning environments can provide students with adaptive support in the form of personalized hints and feedback as well as tailored curricular sequencing. Delivering adaptive support requires access to a student model to e
Data Loading...
