Early prediction of student knowledge in game‐based learning with distributed representations of assessment questions

Abstract

Game-based learning environments hold significant promise for facilitating learning experiences that are both effective and engaging. To support individualised learning and support proactive scaffolding when students are struggling, game-based learning environments should be able to accurately predict student knowledge at early points in students' gameplay. Student knowledge is traditionally assessed prior to and after each student interacts with the learning environment with conventional methods, such as multiple choice content knowledge assessments. While previous student modelling approaches have leveraged machine learning to automatically infer students' knowledge, there is limited work that incorporates the fine-grained content from each question in these types of tests into student models that predict student performance at early junctures in gameplay episodes. This work investigates a predictive student modelling approach that leverages the natural language text of the post-gameplay content knowledge questions and the text of the possible answer choices for early prediction of fine-grained individual student performance in game-based learning environments. With data from a study involving 66 undergraduate students from a large public university interacting with a game-based learning environment for microbiology, Crystal Island, we investigate the accuracy and early prediction capacity of student models that use

Learning analytics and assessment: Emerging research trends, promises and future opportunities

“…For instance, Bulut et al (2022) found that data gathered in online formative assessment activities, for example, scores and time features, can predict student performance in midterm and final exams. Emerson et al (2022) combined student log data collected in a game-based learning environment and the content from the post-test assessment questions, and developed an early prediction model of student achievements on a post-test. The authors showed that this approach can improve the performance and generalisability of prediction models, including the models that predict achievements of new students.…”

“…In the first group of studies, the authors harnessed learning analytics to support the assessment of course content comprehension. Bulut et al (2022) and Emerson et al (2022) demonstrated that combining learner trace‐data and data from formative assessments can be a viable approach to predicting learning performance of university students. For instance, Bulut et al (2022) found that data gathered in online formative assessment activities, for example, scores and time features, can predict student performance in midterm and final exams.…”

Generative Agents to support students learning progress

“…Malinova and Rahneva (Malinova & Rahneva, 2017) and Botelho et al (Botelho et al, 2023) proposed methods for automated question generation in English and mathematics respectively. Emerson et al (Emerson et al, 2022) introduced the use of fine-grained content for student performance prediction during tests. Transformer-based models for reading comprehension test generation were studied by Bulut and Yildirim-Erbasli (Bulut & Yildirim-Erbasli, 2022) and Runge et al (Runge et al, 2022).…”