2025 ASEE Annual Conference & Exposition

This Work in Progress paper presents the development of MATLAB code based on data science techniques and game learning analytics (GLA) for a novel gaming tool designed to enhance faculty development in engineering regarding Diversity, Equity, and Inclusion (DEI) training. This work is part of a larger NSF funded DEI project called [removed for blind review]. The aim of this paper is to articulate our process of adding additional context to game data and creating a data analysis method to assign meaning to the game data.

Past research has shown the widespread applications of data science techniques for analyzing gaming data. Because of the interactive nature of game environments, there is often rich data that can be collected. Gaming data can be used to both provide information about the impact of the game and to validate the game design, ensuring it adequately meets learning objectives. GLA techniques specifically aim to provide insight about the educational processes that occur during gaming. However, there are no standardized procedures for creating or replicating existing GLA techniques for different applications. Therefore, this paper describes how we created a code to clean, organize, and visualize the data generated from our game.

We developed a gaming platform as an innovative tool to help engineering faculty explore DEI concepts in a safe, interactive environment. The gaming platform encourages users to reflect on how their personal values and beliefs influence their professional actions including interactions with students and colleagues with marginalized identities. Our game features scenarios where players must choose from several possible decisions, each informed by differing values and beliefs related to DEI issues. Data collected from gameplay includes the user’s choices in response to various scenarios; their decision-making speed; and the players’ final scores in each of the three scoring categories: student academic achievement, department inclusiveness, and personal reputation. To assign additional meaning to the gameplay data, we added scores to each scenario response based on established scales pertaining to different aspects of DEI. Data analysis will provide insight into participants’ experiences and interpretations of the DEI concepts presented. Overall, it aims to assess changes in faculty beliefs about DEI after game participation.

To ensure meaningful insights from the raw data, we are developing a system for data cleaning and analysis using MATLAB. This tool organizes, cleans, and creates visualizations of the data collected during the game, helping identify trends and relationships. This analysis is instrumental in ultimately contributing to the enhancement of faculty DEI training. Furthermore, this method of data analysis is generalizable to other similar projects, allowing for broader applications in faculty development and training. We hope to present this Work in Progress paper as a Lightning Talk at the 2025 ASEE Annual Conference.