Are All Who Wander Lost? An Exploratory Analysis of Learner Traversals of Minecraft Worlds
In this paper, we analyze in-game data and out-of-game assessment data from 15 Grade 6 boys from the Philippines who were completing a learning task with the What-If Hypothetical Implementations using Minecraft (WHIMC) to determine how distance traveled and area covered relate to assessment outcomes. We also determine the extent of overlap of areas covered by computing the Jaccard Index and Maximum Similarity Index (MSI). We find no significant correlation between assessment scores and overall distance, area, or MSI. However, when we break the data down into five-minute intervals, we find a significant negative correlation between assessment scores and distance traveled and area covered during certain time periods. These findings suggest that wandering off early in game play may be indicative of low learning outcomes later on. The absence of a significant relationship between MSI and assessment scores suggests the absence of a canonical traversal in an open-ended environment.
Esclamado, M.A., & Rodrigo, M.M.T. (2022). Are All Who Wander Lost? An Exploratory Analysis of Learner Traversals of Minecraft Worlds. In M.M. Rodrigo, N. Matsuda, A.I. Cristea, & V. Dimitrova (Eds.), Artificial Intelligence in Education. Posters and Late Breaking Results, Workshops and Tutorials, Industry and Innovation Tracks, Practitioners’ and Doctoral Consortium. AIED 2022. Lecture Notes in Computer Science, Vol. 13356. Springer. https://doi.org/10.1007/978-3-031-11647-6_48