Jo Wilder Dataset

Overview

Just as there are many ways to learn there are many ways to assess learning. Game-based learning is different in that it allows students to engage with educational content in a dynamic way that traditional classroom experiences do not typically provide.

Current research indicates that game-based learning could be effective in supporting learning outcomes, however the limited amount of game-based learning datasets makes it difficult to extend this research. Developing models that make real-time predictions about student performance on game objectives will support and enable educational game developers who are working to create more effective learning experiences for students.
image3
The Jo Wilder dataset available here via the Lab’s Learning Exchange is derived from the 2023 Jo Wilder Kaggle Competition to predict student performance from game play. It includes assets from one of the largest open datasets of game logs available. More than 2,050 teams participated in the competition. The Jo Wilder dataset represents a free and openly-accessible launch point for those interested in researching and/or developing new models around game-based learning and assessment.
image2
Jo Wilder and the Capitol Case, a free online point & click game designed by Field Day Lab, aligns with newly-revised 3-5th grade Wisconsin state standards for social studies. Sections of the game assess players’ story comprehension and analysis of clues to create the competition’s performance measures.

Jo Wilder Dataset © 2024 by The Learning Agency Lab is licensed under CC BY 4.0. To view a copy of this license, visit https://creativecommons.org/licenses/by/4.0/

Potential Uses

Those who access the Exchange’s Jo Wilder dataset can conceivably: