Search for: All records

This paper introduces a novel approach for learning natural language descriptions of scenery in Minecraft. We apply techniques from Computer Vision and Natural Language Processing to create an AI framework called MineObserver for assessing the accuracy of learner-generated descriptions of science-related images. The ultimate purpose of the system is to automatically assess the accuracy of learner observations, written in natural language, made during science learning activities that take place in Minecraft. Eventually, MineObserver will be used as part of a pedagogical agent framework for providing in-game support for learning. Preliminary results are mixed, but promising with approximately 62% of images in our test set being properly classified by our image captioning approach. Broadly, our work suggests that computer vision techniques work as expected in Minecraft and can serve as a basis for assessing learner observations. 

Our work investigates interest triggering, a necessary component of sustaining and developing long-term interest in STEM. We gathered interview data from middle school aged learners (N = 7) at a science-focused Minecraft summer camp over a period of one week. We first identified STEM interest triggering episodes, then categorized each episode based on codes developed previously by Renninger and Bachrach (2016). Our initial findings show differences in the frequency of interest triggering episodes across individuals and suggest that personal relevance and the use of Minecraft played prominent roles.