Exploring the Affordances of Sequence Mining in Educational Games
Name
3434780.3436562.pdf
Size
1.5 MB
Format
Adobe PDF
Checksum (MD5)
daabb211e0fa9963079a861870475172
Author(s)
Gomez, Manuel J.
Ruip?rez-Valiente, Jos? A.
Martinez, Pedro A.
Kim, Yoon Jeon
Date Issued
October 21, 2020
Publisher
ACM|Eighth International Conference on Technological Ecosystems for Enhancing Multiculturality
Citation
Games have become one of the most popular mediums across cultures and ages and the use of educational games is growing. There is ample evidence that supports the benefits of using games for learning and assessment. However, we do not usually find games incorporated into educational environments. One of the main problems that teachers face is to actually know how students are interacting with the game as they cannot analyze properly the effect of the activity on the students. To improve this issue, we can use the data generated by the interaction of students with such educational games to analyze the sequences and errors by transforming raw data into meaningful sequences that are interpretable and actionable for teachers. In this study we use a data collection from our game Shadowspect and implement learning analytics with process and sequence mining techniques to generate two metrics that aim to help teachers make proper assessment and better understand the process.
Version
Final published version
Abstract
Games have become one of the most popular mediums across cultures and ages and the use of educational games is growing. There is ample evidence that supports the benefits of using games for learning and assessment. However, we do not usually find games incorporated into educational environments. One of the main problems that teachers face is to actually know how students are interacting with the game as they cannot analyze properly the effect of the activity on the students. To improve this issue, we can use the data generated by the interaction of students with such educational games to analyze the sequences and errors by transforming raw data into meaningful sequences that are interpretable and actionable for teachers. In this study we use a data collection from our game Shadowspect and implement learning analytics with process and sequence mining techniques to generate two metrics that aim to help teachers make proper assessment and better understand the process.
Description
TEEM’20, October 21–23, 2020, Salamanca, Spain
MIT Department
Massachusetts Institute of Technology. Program in Comparative Media Studies/Writing
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/3434780.3436562
