The document discusses the integration of game learning analytics (GLA) in serious games to enhance their efficacy and improve educational outcomes. It highlights the current challenges, such as limited user validation and the complexities involved in systematically applying GLA, particularly in mainstream education. The establishment of the experience API for serious games (xAPI-sg) aims to standardize data collection and analysis to facilitate better insights into student engagement and learning outcomes.

1. Systematizing Game Learning Analytics
for Improving Serious Games Lifecycle
Baltasar Fernandez-Manjon
balta@fdi.ucm.es , @BaltaFM
e-UCM Research Group , www.e-ucm.es
Educación Digital y Juegos Serios
Cátedra Telefónica-Complutense

2. Serious Games
• Any use of digital games with purposes other than
entertainment (Michael & Chen, 2006)
• Applied successfully in many domains (medicine,
business) with different purposes (knowledge,
awareness, behavioural change)
• But still is a low adoption of Serious Games in
mainstream education
• More evidence-support about SG efficacy is
needed
Clark Abt, 1970

3. https://ig.ft.com/uber-game/
https://getbadnews.com/
https://www.re-mission2.org/
https://www.play2prevent.org/
http://burymemylove.arte.tv/

4. Do serious games actually work?
- Very few SG have a formal evaluation (e.g., pre-post)
- Usually tested with a very limited number of users
- Formal evaluation could be as expensive as creating the
game (or even more expensive)
- Evaluation is not yet considered as a strong requirement
- Difficult to deploy games in the classroom
- Teachers have very little info about what is happening when a
game is being used
- what the student has learned from playing the game?

5. Serious Games for bullying & cyberbullying
A. Calvo-Morata, C. Alonso-Fernández, M. Freire-Morán, I. Martínez-Ortiz and B. Fernández-Manjón, Serious games to prevent and
detect bullying and cyberbullying: a systematic serious games and literature review in Computers & Education, 8 July 2020

6. Serious Games for bullying & cyberbullying
• Only 14/32 games with user validation
• Validation: average < 300 users per game
• Very few collect user interactions
• Various target groups
• They address the problem in a variety of ways
• 20 Bullying, 7 Cyberbullying, 5 Both problems, work on
empathy, raise awareness, show prevention strategies,
safe internet use, report harassment, identify problem,
change behavior, develop emotional/social skills
• No open games
• Lack of free access to the game resources and its code
A. Calvo-Morata, C. Alonso-Fernández, M. Freire-Morán, I. Martínez-Ortiz and B. Fernández-Manjón, Serious games to prevent and
detect bullying and cyberbullying: a systematic serious games and literature review in Computers & Education, 8 July 2020

7. Most common methodology are pre-post questionaries in experiments:
Formal validation of serious games
Is there a significant
difference between
pre-questionary and
post-questionary
results?
Pre and post questionaries should
have been previously validated

8. Learning analytics & Game Analytics
• Learning analytics: Improving education based
on analysis of actual data
• Data driven
• From only theory-driven to evidence-based
• Game Analytics: Application of analytics to
game development and research (Telemetry)
• Game metrics
• Interpretable measures of data related to games
• Player behavior
• Mainly used with “commercial purposes”
• monetization, churn, user funnels

9. Game Learning Analytics
breaking the game black box
model to obtain information
while students play.
Manuel Freire, Ángel Serrano-Laguna, Borja Manero, Iván Martínez-Ortiz, Pablo Moreno-Ger, Baltasar Fernández-Manjón (2016): Game
Learning Analytics: Learning Analytics for Serious Games. In Learning, Design, and Technology (pp. 1–29). Cham: Springer International
Publishing. http://doi.org/10.1007/978-3-319-17727-4_21-1.
•GLA is learning analytics applied to serious games
• collect, analyze and visualize data from learners’ interactions
with SGs
Game Learning Analytics (GLA)

10. Uses of Game Learning Analytics in Serious
Games Lifecycle
• Game testing – game analytics
• Player focus – user experience
• Average playing time, completion rate
• Game deployment and student evaluation
• Real-time information for supporting the teacher
• Knowing what is happening when the game is deployed
in the class
• “Stealth” student evaluation (Valerie Shute)
• Formal Game evaluation – game effectivity
• From pre-post questionaries to evaluation based on
game learning analytics??
GLA

11. From Formal Game Validation to Game Learning
Analytics
PRE POST
Experimental
group
Real-time
analysis
Off-line
analysis
User control
Session control
Game efficacy
User acceptance
Design validation

12. Minimun Game Requirements for GLA
• Most of games are black boxes.
• No access to what is going on during game play
• We need access to game “guts”
• User interactions
• Changes of the game state or game variables
• Or the game must communicate with the outside world
• Using some logging framework
• What is the meaning of the that data?
• Ethics: adequate experimental design and setting
• Are users informed?
• Anonymization of data could be required
• Fair data exploitation for all stakeholders?

13. Game Learning Analytics (GLA) or Informagic?
• Informagic
• False expectations of gaining full insight on the game
educational experience based only on very shallow game
interaction data
• Set more realistic expectations about learning analytics with
serious games
• Requirements
• Outcomes
• Uses
• Cost/Complexity
Perez-Colado, I. J., Alonso-Fernández, C., Freire-Moran, M., Martinez-Ortiz, I., & Fernández-Manjón, B. (2018). Game
Learning Analytics is not informagic! In IEEE Global Engineering Education Conference (EDUCON).

14. Game Learning Analytics

15. Game Learning Analytics
What data is to be
collected from the game
and how it relates to
learning goals
Which specific statements (e.g.
in xAPI format) are to be
tracked from the game
containing that information
How the statements collected
are to be analyzed and what
information is to be reported
and/or visualized

17. Results: RQ1 GLA purposes
➔ Main focus: assess learning &
predict performance
➔ Games are indeed useful for
purposes beyond entertainment
➔ Interest now in analyzing
interaction data to measure
impact on players and relation to
players’ in-game behaviors

18. Results: RQ2 data science techniques
➔ Linear models and cluster
techniques commonly applied
➔ Classical techniques
➔ More powerful techniques (e.g.
neural networks) not broadly
applied yet
➔ Need of xAI
➔ Explainable AI
➔ Human understable decissions

19. Results: RQ3 main stakeholders
➔ Purposes that cover interests of
many stakeholders
➔ Many research done on this area
➔ Students/Learners indirect
recipients of all results

20. Results: RQ4 conclusions and results
Results on assessment & student profiling:
➔ GLA data can accurately predict games’ impact
➔ Performance is related to players’ characteristics
Results on SG design:
➔ GLA data can validate SG design
➔ Assessment can & should be integrated in SG design
➔ Importance of SG characteristics
➔ Identified challenges when designing SG
➔ Proposed frameworks to simplify design

21. Results: Additional information
Serious games used:
➔ Main focus to teach
➔ Main domain maths and science-related topics
Participants in the validations studies:
➔ Small sample sizes used (<100)
➔ Primary & secondary education
Interaction data:
➔ Completion times, actions & scores commonly tracked
➔ Format not reported

22. Requirements to Systematize GLA in SG
• Applying GLA to serious games is complex, error-prone, and fragile
• Any small glitch can cause the whole process to fail
• GLA is still a complex process that is not affordable for most of the small
game producers or to game research teams
• Systematize GLA in SG require better models, standards and tools
• Game Learning Analytics Models
• Standard formats for collecting GLA data
• Tools that simplify the GLA implementation
• Authoring
• Tracking
• Analysis
• Orchestation / Management

23. GLA framework

24. Experience API for Serious Games: xAPI-SG Profile
Experience API (xAPI) is a new de facto standard that
enables the capture of data about human performance and
its context. Now it is becoming an IEEE standard
The e-UCM Research Group in collaboration with ADL
created the Experience API for Serious Games Profile (xAPI-
SG), a xAPI profile for the specific domain of Serious Games.
The xAPI-SG Profile defines a set of verbs, activity types and
extensions, that allows tracking of all in-game interactions
as xAPI traces (e.g. level started or completed) https://xapi.e-ucm.es/vocab/seriousgames
Ángel Serrano-Laguna, Iván Martínez-Ortiz, Jason Haag, Damon Regan, Andy Johnson, Baltasar Fernández-Manjón (2017):
Applying standards to systematize learning analytics in serious games. Computer Standards & Interfaces 50 (2017) 116–123,

25. xAPI-SG Profile
The xAPI-SG Profile is the result of the implementation of an interactions
model for Serious Games in xAPI.
The types of interactions that can be performed in a Serious Game, and are
included in the profile, can be grouped based on the type of interactions and
game objects that the interaction is performed over.
The following slides present some of these common interactions and game
objects related with them, with example xAPI-SG statements.
● completables
● accessibles
● alternatives
● GameObjects

26. xAPI-SG: Completables
A completable is something a player can start, progress and complete in a
game, maybe several times.
● Verbs: initialized, progressed, completed
● Types: game, session, level, quest, stage, combat, storynode, race, completable
John Smith progressed on Level 1 0.5
https://xapi.e-ucm.es/vocab/seriousgames

28. Java
xApi Tracker
Unity
xApi Tracker
C#
xApi Tracker
xAPI Game trackers as open code
https://github.com/e-ucm

29. SIMVA: SG Simple Validator
• Simva tool aims to simplify all the aspects of the validation
• Before the experiments:
• Managing users & surveys
• Providing anonymous identifiers to users
• During the experiments:
• Pre-questionnaire – Game analytics – Post-questionnaire
• Collecting and storing questionnaires (surveys) and traces data (xAPI-SG)
• Relating different data from users (GLA, questionnaires)
• After the experiments:
• Simplifying downloading and analysis of all data collected
Ivan Perez-Colado, Antonio Calvo-Morata, Cristina Alonso-Fernández, Manuel Freire, Iván Martínez-Ortiz, Baltasar Fernández-Manjón (2019): Simva:
Simplifying the scientific validation of serious games. 19th IEEE International Conference on Advanced Learning Technologies (ICALT), 15-18 July 2019,
Maceió-AL, Brazil.

30. Unified Cloud
Storage
Analytics and
Control
Survey
management
Data Science
tools
User & Group
management
Gameplay
Management
SIMVA orchestrates all the processes

32. T-mon: Monitoring xAPI-SG traces in Python
Experience API Profile
for Serious Games
(xAPI-SG)
T-mon (Traces
monitor)
xAPI-SG Processor
Jupyter Notebooks
Default set of
analysis and
visualizations
https://github.com/e-ucm/xapi-sg-processor

33. Default analysis and visualizations
Serious game completion
initialized and
completed traces
with object-type
serious-game
Serious game progress
initialized, progressed and
completed traces
with object-type
serious-game,
result.progress and
timestamp
Choices in alternatives
selected traces with
object-type alternative,
result.response and
result.success
Completable progress
progressed traces in any
completable object type,
with result.progress

34. Default analysis and visualizations
Interactions
interacted traces with
any object type;
bar chart per item, and
each bar per player
Completable results (scores)
completed trace of any
completable with result.score
Completable results (max and min times)
difference in timestamp
of initialized and
completed traces of
each completable
Interactions (heatmap)
interacted traces
grouped by item
(object)
and player

35. GLA Methodology
1. Game validation phase:
○ validate the serious game against actual results (post-test)
○ Collect all the game analytics data to improve the game
2. Use GLA interaction data to predict knowledge after playing.
○ create prediction models taking as input the interaction data
3. Game deployment phase:
○ students play and are automatically assessed based on their interactions (used
as input for prediction models)
○ pre-post are no longer required
Cristina Alonso-Fernández, Ana Rus Cano, Antonio Calvo-Morata, Manuel Freire, Iván Martínez-Ortiz, Baltasar Fernández-Manjón (2019): Lessons
learned applying learning analytics to assess serious games. Computers in Human Behavior, Volume 99, October 2019, Pages 301-309

36. The game: First Aid Game
Game to teach first aid techniques
to 12-16 years old players
Three initial situations:
● chest pain
● unconsciousness
● choking
Game previously validated with
pre-post and control group:
Video-game instruction in basic life support
maneuvers. Marchiori EJ, Ferrer G, Fernandez-Manjon
B, Povar Marco J, Suberviola Gonźalez JF, Gimenez
Valverde A. (2012)

37. Pre-post questionnaires + GLA data
N = 227 students from a high school in Madrid (Spain)
Each student completed:
● pre-test: 15 questions assessing previous knowledge
about first aid techniques
● gameplay: of First Aid Game
● post-test: 15 questions assessing knowledge about
first aid techniques after playing
Collection of both results in pre-post test and GLA
interaction data from the game (following xAPI-SG Profile).
Cristina Alonso-Fernández, Iván Martínez-Ortiz, Rafael Caballero, Manuel Freire, Baltasar Fernández-Manjón (2020): Predicting students’ knowledge after
playing a serious game based on learning analytics data: A case study. Journal of Computer Assisted Learning, vol. 36, no. 3, pp. 350-358, June 2020.

38. New uses of games based on GLA
- Avoiding pre-test: Games for evaluation
- Avoiding post-test: Games for teaching and measure of learning
With or without pre-test.

39. Cyberbullying: Conectado game

40. Serious Game → prevent Bullying and
Cyberbullying
● Increase awareness and empathy
● Youngsters (12 to 17 years old)
● Use at the school as a tool for teachers
Conectado:
● Point & Click game
● Player in the role of victim
● Choices and minigames that you can not win
● Free and open code video game

41. 1300
12

42. Significant increase in the ciberbullying
awareness Wilcoxon paired test, p<0.001
5.72
6.38
Antonio Calvo-Morata, Dan-Cristian Rotaru, Cristina Alonso-Fernández, Manuel Freire, Iván Martínez-Ortiz, Baltasar Fernández-Manjón (2018):
Validation of a Cyberbullying Serious Game Using Game Analytics. IEEE Transactions on Learning Technologies (early access)

43. Our xAPI tool-based approach for GLA
uAdventure authoring
tool
● Narrative and GPS games
● Easy to use by non-experts
● GLA out-of-the-box
● Extensions for custom GLA
e-UCM xAPI tracker
● Compatible with xAPI for
serious games
● High-level interface to create
traces
● Local and online modes
Simva management tool
● Integrated with uA
● Automatically collects traces
in xAPI format (simple LRS)
● Manages experiments and
users
● Integrates GLA and pre-post
questionnaires
TxMon analysis tool
● Analyzes xAPI traces
● Default visualizations
● xAPI for SGs as LAM
● Can connect with Simva

44. This set of tools provide an
interoperable sandbox system for
supporting the xAPI GLA lifecycle:
● Simplifies SG creation
● Reduces technical knowledge for
setting up and collecting analytics
● Simplifies experiment management
● And provide default analytics so:
○ Students can see how they did
○ Teachers can monitor and
evaluate
○ Developers and teachers can
review and improve their games
Interoperable ecosystem for complete GLA lifecycle

45. Conclusions
• Game Learning Analytics has a great potential for improving SGs
• Evidence based serious games
• Games as assessments (better “Stealth” student evaluation)
• Games as powerful research environments
• Still complex to implement GLA in SG
• Increases the (already high) cost of the games
• Requires expertise not always present in game developers, SME or research
groups
• Real time GLA is still complex and fragile (e.g. deployment is schools)
• New standards specifications (e.g. xAPI) and open software tools could
greatly simplify GLA implementation and adoption
• Ethics should drive the GLA process
45

46. Thanks!
Contact: balta@fdi.ucm.es @baltafm
This work has been partially funded by Regional Government of Madrid (eMadrid S2018/TCS4307, co-funded by the European
Structural Funds FSE and FEDER), by the Ministry of Education (TIN2017-89238-R, PID2020-119620RB-I00), by MIT-La Caixa (MISTI
program, LCF/PR/MIT19/5184001) and by Telefonica-Complutense Chair on Digital Education and Serious Games.
Our publications: https://www.e-ucm.es/publications/all/
Our open code: https://github.com/e-ucm/