Learning Analytics and Serious Games: Trends and Considerations

© author(s) of these slides including research results from the KOM research network and TU Darmstadt; otherwise it is specified at the respective slide

4-Nov-14

Prof. Dr.-Ing. Ralf Steinmetz

KOM - Multimedia Communications Lab

ACM Multimedia 2014

Learning Analytics

and Serious Games:

Trends and Considerations

ACM Multimedia Serious Games Workshop Nov. 2014

Laila Shoukry, M.Sc.

KOM – Multimedia Communications Lab 2

Outline


What is Learning Analytics

http://edtechreview.in/event/87-webinar/835-can-learning-analytics-enable-personalized-learning

“Learning analytics is the measurement, collection,

analysis and reporting of data about learners and

their contexts, for purposes of understanding and

optimising learning and the environments in which

it occurs.” George Siemens 2011


Motivation

http://www.openequalfree.org/gamification-versus-game-based-learning-in-the-classroom/10082

Why Learning Analytics for Serious Games

• Evaluation of Serious Games

• Justifying expense in learning contexts

• Objective and cost-effective approach

• Evaluation with Serious Games

• Provide a big amount of gameplay data

• Interactive and engaging nature Stealth

Assessment

• Enable insight about learner attributes and

learning progress


Outline


Modelling for Learning Analytics in SG

https://www.linkedin.com/pulse/article/20140320222540-1265384-show-what-you-know-the-future-of-

competency-based-learning

• Competence-Based Knowledge Space Theory

(CbKST)

• Requires learning domains to be modelled as a prerequisite

competency structure

• Inferring knowledge states

• Narrative Game-Based Learning Objects (NGLOB)

• Additionally considers player type and narrative aspects

• Triple vector: Narrative Context, Gaming Context, Learning

Context

• Evidence-Centered Design (ECD)

• Competency Model, Evidence Model and Action Model

• Open Learner Model (OLM)

• Presenting to the learner an understandable visualization of

his current knowledge state

• Proven to improve learning outcomes


Outline


Choosing Data for Learning Analytics in SG

Depends on learning goals, setting, tasks, game

genre, mechanic and platform

• Intensive vs. Extensive Data

• Extensive Data: for Higher Quantity

• Intensive Data: for Higher Quality

• Single-Player vs. Multiplayer

• Multiplayer:

• additional social component

• Data fed into social network analysis to identify aspects

of collaborative learning

• Generic vs. Game-Specific Traces

• Generic:

• Identify strengths and weaknesses of learning games

• Compare different learning games

• Game-Specific:

• Designing games „with analytics in mind“

• More tailored to invidiual games

StoryPlay Learning Analytics Tool


Outline


Capturing Data for Learning Analytics in SG

Depends on data modalities and interactions

• Activity logs

• Widely employed

• Records interaction data in form of log files

• Multimodal Learning Analytics

• Includes biometric data and other multimodal

data for assessing motivation, fun and

collaboration aspects in learning settings

• Introduces its own challenges for aligning data

• Mobile and Ubiquitous Learning Analytics

• Data of mobile learners, suitable for mobile

games

• Interaction with mobile devices

• Considering contextual information


Outline


Aggregating Data for Learning Analytics in SG

Depends on data sources and sample size

• Extensive Data Aggregation accross

Users

• Log data joined into central database after

preprocessing using session identifiers

• Log files generated on all machines should

use same data format

• Need for standardized xml formats

• „Aggregation Model“: using semantic rules

to map game actions or states to meaningful

expressions under which similar events are

grouped

• Intensive Data Aggregation accross

Modalities

• Multimodal Data Synchronization needed for

observing behavior accross MM data

channels

• Some tools exist: Replayer, ChronoVis

ChronoViz.com


Outline


Analyzing Data for Learning Analytics in SG

Depends on learning context and application

• By instructor

• This step is not done by the system but instructor intervenes

according to visualized statistics

• Automatic Analysis

• For intelligent tutoring systems and adaptive Serious Games

• Measures to be derived:

• Gaming: general in-game performance, in-game learning, in-game

strategies, player type

• Learning: general traits and abilities of the learner, general knowledge,

situation-specific state, learning behaviors, learning outcomes

• Rules governing the interpretation of in-game sources of evidence

to infer competencies

• Algorithms applied during learning sessions to update competency

models

• Data Mining and Machine Learning approaches can be used for

identifying solution strategies, error patterns and player goals


Outline


Deploying Results for Learning Analytics in SG

Depends on learning context and

application

• Visualization

• visualizations of narrative structure,

player model and skill tree

• graphs, Hasse Diagrams, Heat Maps

• for games, a special need for real-time

operation, extensibility and

interoperability

• Adaptation

• macro-adaptivity: system responds by

choosing the appropriate next learning

object or narrative event

• micro-adaptivity: adjusting aspects

within a learning task like task diffculty or

feedback type


Popular Analytics Tools

Piwik Google Analytics

OpenSim Analytics for Virtual Worlds


Questions & Contact


References

• N. R. Aljohani and H. C. Davis. Learning analytics in mobile and ubiquitous learning environments. In 11th • World Conference on Mobile and Contextual Learning: mLearn 2012, Helsinki, Finland, 2012. • R. S. J. D. Baker and K. Yacef. The State of Educational Data Mining in 2009 : A Review and Future Visions. 1(1):3-16, 2009. • P. Blikstein. Multimodal learning analytics. Proceedings of the Third International Conference on • Learning Analytics and Knowledge - LAK '13, page 102, 2013. • S. Bull, Y. C. Y. Cui, a.T. McEvoy, E. Reid, and W. Y. W. Yang. Roles for mobile learner models. The 2nd IEEE International

Workshop on Wireless and Mobile Technologies in Education, 2004. Proceedings., pages 124-128, 2004. • S. Bull and J. Kay. Open learner models. In Advances in Intelligent Tutoring Systems, pages 301-322. Springer, 2010. • G. K. Chung and D. S. Kerr. A Primer on Data Logging to Support Extraction of Meaningful • Information from Educational Games: An Example from Save Patch. CRESST Report 814. National • Center for Research on Evaluation, Standards, and Student Testing (CRESST), page 27, 2012. • A. Cooper. Learning Analytics Interoperability – The Big Picture In Brief. Learning Analytics Community Exchange, 2014. • E. Duval. Attention Please!: Learning Analytics for Visualization and Recommendation. LAK '11, pages 9-17, New York, NY, USA,

2011. ACM. • A. Dyckho and D. Zielke. Design and Implementation of a Learning Analytics Toolkit for Teachers. Journal of . . . , 15:58-76, 2012. • G. Dyke, K. Lund, and J.-J. Girardot. Tatiana: An Environment to Support the CSCL Analysis Process. In Proceedings of the 9th

International Conference on Computer Supported Collaborative Learning – Volume 1, CSCL'09, pages 58{67. International Society of the Learning Sciences, 2009.

• B. M. Eun Young Ha Jonathan Rowe and J. Lester. Recognizing Player Goals in Open-Ended Digital Games with Markov Logic Networks. Plan, Activity and Intent Recognition: Theory and Practice, 2014.

• J.-C. Falmagne, D. Albert, C. Doble, D. Eppstein, and X. Hu. Knowledge Spaces: Applications in Education. Springer Science & Business, 2013.

• I. Garcia, A. Duran, and M. Castro. Comparing the eectiveness of evaluating practical capabilities through hands-on on-line exercises versus conventional methods. In Frontiers in Education Conference, 2008.

• FIE 2008. 38th Annual, pages F4H{18{F4H{22, Oct • 2008. • S. Goebel, M. Gutjahr, and S. Hardy. Evaluation of Serious Games. Serious Games and Virtual Worlds in Education, Professional

Development, and Healthcare, page 105, 2013.


References

• S. Goebel, V. Wendel, C. Ritter, and R. Steinmetz. Personalized, adaptive digital educational games using narrative game-based learning objects. pages 438-445. Springer, 2010.

• S. L. . B. H. Jan Plass. Assessment mechanics: design of learning activities that produce meaningful data.New York University, CREATE Lab, Apr. 2013.

• K. E. B. E. W. Joseph Grafsgaard Joseph Wiggins and J. Lester. Predicting Learning and Aect from Multimodal Data Streams in Task-Oriented Tutorial Dialogue. In Seventh International Conference on Educational Data Mining, 2014.

• D. S. Kerr and G. K. W. K. Chung. Using Cluster Analysis to Extend Usability Testing to Instructional Content. CRESST Report 816. National Center for Research on Evaluation, Standards, and Student Testing (CRESST), May 2012.

• M. D. Kickmeier-Rust and D. Albert. An Alien's Guide to Multi-Adaptive Educational Computer Games. Informing Science, 2012. • M. D. Kickmeier-Rust and D. Albert. Learning analytics to support the use of virtual worlds in the classroom. In Human-Computer

Interaction and Knowledge Discovery in Complex, Unstructured, Big Data, pages 358{365. Springer, 2013. • K. R. Koedinger, R. Baker, K. Cunningham, A. Skogsholm, B. Leber, and J. Stamper. A data repository for the EDM community: The

PSLC DataShop. Handbook of educational data mining, pages 43-55, 2010. • J. Konert, K. Richter, F. Mehm, S. G•obel, R. Bruder, and R. Steinmetz. Pedale - a peer education diagnostic and learning

environment. Journal of Educational Technology & Society, 2012. • K. Korossy. Modeling knowledge as competence and performance. Knowledge spaces: Theories, empirical research, and

applications, pages 103{132, 1999. • J. Lester, B. Mott, J. Rowe, and J. Sabourin. {learner modeling to predict real-time aect in serious games. Design Recommendations

for Intelligent Tutoring Systems, page 201, 2013. • S. M. Letourneau. Intensive data at CREATE -Research approaches & future directions. In Simulations and Games Learning

Analytics and Data Mining Workshop, 2013. • R. Levy. Dynamic Bayesian Network Modeling of Game Based Diagnostic Assessments. CRESST Report, 2014. • C. Martin, O. Galibert, M. Michel, F. Mougin, and V. Stanford. NIST Smart Flow System User's guide. • M. Minovic and M. Milovanovic. Real-time learning analytics in educational games. pages 245{251. ACM, • 2013. • R. J. Mislevy, R. G. Almond, and J. F. Lukas. A brief introduction to evidence-centered design. cse report 632. US Department of

Education, 2004. • A. Mitrovic and B. Martin. Evaluating the eect of open student models on self-assessment. International Journal of Articial

Intelligence in Education, 17(2):121-144, 2007. • A. Morrison, P. Tennent, and M. Chalmers. Coordinated visualisation of video and system log data. In Coordinated and Multiple

Views in Exploratory Visualization, 2006. Proceedings. International Conference on, pages 91-102. IEEE,2006.


References

• K. Nurmela, E. Lehtinen, and T. Palonen. Evaluating CSCL log les by social network analysis. In Proceedings of the 1999 conference on Computer support for collaborative learning, page 54. International Society of the Learning Sciences, 1999.

• H. Ogata, M. Li, B. Hou, N. Uosaki, M. M. El-Bishouty, and Y. Yano. SCROLL: Supporting to share and reuse ubiquitous learning log in the context of language learning. Research & Practice in Technology Enhanced Learning, 6(2), 2011.

• S. Oviatt, A. Cohen, and N. Weibel. Multimodal learning analytics: Description of math data corpus for icmi grand challenge workshop. In Proceedings of the 15th ACM on International conference on multimodal interaction, pages 563{568. ACM, 2013.

• J. L. Plass, B. D. Homer, C. K. Kinzer, Y. K. Chang, J. Frye, W. Kaczetow, K. Isbister, and K. Perlin. Metrics in Simulations and Games for Learning. In Game Analytics, pages 697{729. Springer, 2013.

• M. Prensky. Computer games and learning: Digital game-based learning. Handbook of computer game studies, 18:97-122, 2005.

• C. Reuter, F. Mehm, S. G•obel, and R. Steinmetz. Evaluation of Adaptive Serious Games using Playtraces and Aggregated Play Data. Proceedings of the 7th European Conference on Game Based Learning (ECGBL) 2013, (October):504{511, 2013.

• A. Serrano, E. J. Marchiori, A. del Blanco, J. Torrente, and B. Fernandez-Manjon. A framework to improve evaluation in educational games. In Global Engineering Education Conference (EDUCON), 2012 IEEE, pages 1-8. IEEE, 2012.

• A. Serrano-Laguna, J. Torrente, P. Moreno-Ger, and B. Fernandez-Manjon. Application of learning analytics in educational videogames. Entertainment Computing, 2014.

• V. J. Shute, M. Ventura, M. Bauer, and D. Zapata-Rivera. Melding the power of serious games and embedded assessment to monitor and foster learning. Serious games: Mechanisms and eects,

• pages 295-321, 2009. • G. Siemens and R. S. J. Baker. Learning Analytics and Educational Data Mining : Towards Communication and Collaboration.

2010. • K. K. Tatsuoka. Architecture of knowledge structures and cognitive diagnosis: A statistical pattern recognition and classication

approach. Cognitively diagnostic assessment, pages 327-359, 1995. • T. P. Vendlinski, G. C. Delacruz, R. E. Buschang, G. Chung, and E. L. Baker. Developing high-quality assessments that align

with instructional video games (CRESST Report 774). . National Center for Research on Evaluation, Standards, and Student Testing, 2010.

• A. V. Wallop. Althea Vail Wallop CS 229 Final Project Report Learning to Predict Disengagement in Educational iPad Application. pages 1-5, 2010.

• J.-D. Zapata-Rivera and J. E. Greer. Interacting with inspectable bayesian student models. International Journal of Articial Intelligence in Education, 14(2):127-163, 2004.


Websites

http://www.zoodles.com http://www.google.com/analytics http://piwik.org/ http://secondlife.com/ http://opensimulator.org/

Learning Analytics and Serious Games: Trends and Considerations

Technology

Transcript of Learning Analytics and Serious Games: Trends and Considerations