When the GALA project started in 2010, the notion of using games as verification tests was slowly appearing in academia, but with scarce mentions, usually in the form of future work (Moreno- Ger, Burgos & Torrente, 2009). The use of background assessment techniques in general, usually in the form of stealth assessment (Shute et al. 2013) or embedded assessment (Shute and Ventura, 2009) also became an established trend only in the early years of the GALA project.
On the other hand, the Technology Enhanced Learning (TEL) area has also looked intently at the advances in Web Analytics and Business Intelligence, where big and detailed logs of the interactions of stakeholders are used to improve business processes or ecommerce profitability (Williams & Williams, 2003). This has resulted in the strong emergence of Learning Analytics (LA), where interaction logs in online Learning Management Systems are studied in order to identify trends and interaction patterns, with the objective of improving the learning processes, identifying struggling students and perhaps even predict student grades (del Blanco et al. 2013).
In GALA, we have followed these trends demonstrating that the potential at the crossroads of serious games and Learning Analytics is great: a single gameplay session can generate more data than a large cohort of students interacting with a web system for weeks, and the application of data mining techniques seems extraordinarily powerful. The notion is even more promising if we consider larger scopes, such as a course with large cohorts playing many different games, or the same games being played by different groups in a school, a region or a country. This will impact the deployment rate and uptake.
However, the technical challenges are enormous, including the need to streamline game-specific trace aggregation and visualization, tailor this to serious gaming, and address challenges concerting the detection of significant patterns. For this reason, in GALA we have focused on providing tools to overcome the technical barriers and pave the road for the next generation of LA-aware serious games. This approach is the rationale for the development of the GLEANER framework (see Serrano-Laguna et al. 2012, 2013, 2014, del Blanco et al. 2013).
GLEANER has provided the basis on which to build a future infrastructure to generate and collect data through different serious games, exploring different perspectives of how this data can be leveraged. The exploration has covered the different possible application scopes, the technical challenges involved and the different measurements that can be performed with objectives ranging from detecting gameplay issues to identifying poorly performing students, as well as how the aggregation of data at different scopes can help policymakers in making informed decisions. All these perspectives are detailed in the GALA D2.4 deliverable “Report for Learning Analytics for SGs”. And the open source GLEANER API is also available for download online: http://e-ucm.github.io/gleaner/
In addition, all these features have also been exemplified through different case studies that used different games and technologies to gather and analyze data. The main outcomes of these case studies and their repercussions in how LAs should be used are also described in the D2.4 “Report for Learning Analytics for SGs” deliverable, available after September 2014.
For the complete report or feedback, please email s.arnab@coventry.ac.uk or comment below with:
- i) Name ii) Affiliation iii) comments (Optional)
References
Moreno-Ger, P., D. Burgos, J. Torrente (2009). Digital Games in eLearning Environments: Current Uses and Emerging Trends. Simulation & Gaming 40 (5), 669-687.
Serrano-Laguna, A., Torrente, J., Moreno-Ger, P., Fernández-Manjón, B. (2012). Tracing a little for big Improvements: Application of Learning Analytics and Videogames for Student Assessment. In proceedings of VS-GAMES conference 2012, pp 203-209, October 29-31 2012, Genoa, Italy.
Serrano-Laguna, A., Torrente, J., Moreno-Ger, P., Fernández-Manjón, B. (2014). Application of Learning Analytics in Educational Videogames. Entertainment Computing, Elsevier (in press, early access available).
Serrano-Laguna, A., Fernández-Manjón, B. (2014). Applying learning analytics to simplify serious games deployment in the classroom. Proceedings of the 2014 IEEE Global Engineering Education Conference (EDUCON) Pages 872-877.
del Blanco, A., Serrano-Laguna, A., Freire, M., Martínez-Ortiz, I., Fernández-Manjón, B. (2013). E-Learning Standards and Learning Analytics. Can Data Collection Be Improved by Using Standard Data Models?. In Proceedings of the IEEE Engineering Education Conference (EDUCON), pp 1255-1261, Berlin, Germany, March 13-15.
Shute, V.J., Ventura, M., Bauer, M., and Zapata-Rivera, D. (2009) Melding the power of serious games and embedded assessment to monitor and foster learning: Flow and grow. In U. Ritterfeld, M. Cody, and P. Vorderer (Eds.), Serious Games: Mechanisms and Effects. Philadelphia, PA: Routledge. pp. 295-321.
Shute, V. J., & Ventura, M. (2013). Stealth assessment: Measuring and supporting learning in games. The John D. and Catherine T. MacArthur Foundation Reports on Digital Media and Learning. MIT Press.
Williams, S., & Williams, N. (2003). The Business Value of Business Intelligence. Intelligence, 8(310), 30–39.