The Ateneo Laboratory for the Learning Sciences cordially invites you to attend the talk titled “Are All Who Wander Lost? An Exploratory Analysis of Learner Traversals of Minecraft Worlds” by Maricel Esclamado on Tuesday, 05 April 2022 at 4:00 PM.
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 the area covered during certain time periods. These findings suggest that wandering off early in gameplay 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.
About the Speaker
Maricel A. Esclamado is a graduate student currently taking Ph.D. in Computer Science at Ateneo de Manila University. She has been working on the data analysis for the WHIMC project in Ateneo Laboratory for the Learning Sciences (ALLS) since September 2021. She is also an Associate Professor at the University of Science and Technology of Southern Philippines.
Welcome to Technology-Enhanced Learning: How technology is changing the way we learn, a series that features brief summaries of scientific research and innovation in the area of computer-based learning. In this series, respected researchers and academics from across the world will be invited to talk about their current projects, the impact these projects have on teachers and learners, and the questions that are still open for investigation.
We look forward to sharing insightful conversations with you!
Technology-Enhanced Learning is a joint production of the Ateneo Laboratory for the Learning Sciences (ALLS) and the Asia Pacific Society for Computers in Education (APSCE).
Say hello to the ALLS YouTube channel! We’ll be posting software recommendations, research summaries, and more! We hope to see you there!
Many thanks to Dr. Jen Agapito and Mr. Neithan Casano for their production work! Thank you as well to our talented cast (ahem) of faculty and researchers who lent their voices and expertise to this undertaking!
The last couple of years have seen an explosion of interest in algorithmic bias in education, matching greater societal awareness of the problem of algorithmic bias in general, and problems of discrimination and social justice more broadly.
However, most of the work on algorithmic bias in education (and algorithmic bias in general) has focused on easily identified and well-known demographic categories. A recent review by Baker and Hawn (2021) finds that in the relatively rarer cases when researchers have looked for algorithmic bias in terms of other categories, they often find evidence for its existence. This suggests that other unknown categories may be impacting algorithmic effectiveness. Furthermore, algorithmic bias often is posed in terms of single categories, ignoring the possibility that bias may emerge at the intersection of categories as well.
This special issue seeks to promote research and practice that investigates and attempts to resolve less-studied algorithmic biases in education. Work on biases going beyond widely-studied demographic categories is welcome; this includes work that spans both widely-studied and non-widely-studied categories. Work on intersectional biases is also welcome. We welcome theoretical papers, conceptual and position papers, empirical papers, methodological papers, and papers of practice.
Sample topics may include:
Empirical research on whether algorithmic bias investigating less-studied categories is present in a specific application
Including but not limited to work involving indigenous populations, sub-categories of widely-studied demographic categories, learners with specific disabilities, neurodiversity, military-connected children, migrant workers and their families, non-binary and transgender learners, religious minorities, refugees, rural learners, learners in small or remote cities or communities, non-WEIRD countries, speakers of less common dialects or non-prestige dialects, second-language speakers, and international students or students of specific national backgrounds
Empirical research on intersectional algorithmic biases
Empirical work to address and resolve less-studied algorithmic bias and intersectional algorithmic biases
Mathematical work and methodology related to studying less-studied and/or intersectional algorithmic biases, including but not limited to power analyses and sample size calculations
Conceptual, theoretical, and position pieces related to journal special issue themes
Work around data systems and methods that enable research on less-studied groups
Case studies around efforts to reduce algorithmic bias (of the type this special issue focuses on) in practice
Submission and Inquiries
Please see the submission information. We welcome manuscripts of any length and welcome dual-publication both in English and other languages.
When you submit your paper, please note that it is for this special issue in your cover letter.
All submissions will go through the journal’s usual peer review process.
Important Dates
Email inquiry of interest for submitting to special issues or abstract: Any date before August 1, 2022 (optional)
Paper submission: September 1, 2022
All articles will be published online as soon as fully accepted, and as part of a special issue when all submissions have completed their processes
Guest Editors
Nigel Bosch University of Illinois Urbana-Champaign, pnb@illinois.edu
Ibrahim Dahlstrom-Hakki TERC, idahlstromhakki@terc.edu
Ryan S. Baker University of Pennsylvania, rybaker@upenn.edu
Ryan Baker and Ulrich Boser released a report on High-Leverage Opportunities for Learning Engineering. In it, they discuss “the potential of learning engineering to bring theory and practice of learning forward, including both key areas where learning engineering can bring benefits, and key steps towards making those benefits a reality.”
If you are interested in learning engineering and are looking for ideas for a thesis or indeed an entire research practice, this is a great starting point.
