Learning Analytics applied to simulations and videogames

39
LEARNING ANALYTICS APPLIED TO SIMULATIONS AND VIDEOGAMES

Transcript of Learning Analytics applied to simulations and videogames

LEARNING ANALYTICS APPLIED TO

SIMULATIONS AND VIDEOGAMES

EDUCATIONAL DATA MINING

● Educational institutions have interesting information about students

● Students are generating a lot of new data– e-learning systems (LMS, MOOCs)

– Interactions with complex resources (simulations)

We need tools to understand these data and optimize learning processes

LEARNING ANALYTICS

ACADEMIC ANALYTICS

EDUCATIONAL DATA MINING

STAKEHOLDERS AND OBJECTIVES

● For learners/students– Personalized e-learning, receive recommendations for

paths/activities, auto-assessment

● For instructors/teachers– Get feedback about instruction, detect students at risk, predict

students performance

● For course developers/researchers– Evaluate and maintain courseware

● For organizations/administrators– Develop the best way to organize institutional resources

Romero, C., & Ventura, S. Educational Data Mining: A Review of the State of the Art, 40 IEEE Transactions on Systems Man and Cybernetics Part C Applications and Reviews 601–618 (2010). IEEE. doi:10.1109/TSMCC.2010.2053532

IN

● Learning Analytics– Using simulations and videogames

● Objectives– Assess students learning process analyzing their

interactions with simulations

– Give feedback to teachers● Real time: while students play with the simulation● Post-experience: after students are done with the

simulation

GLEANER VIDEOS

WHAT WE LEARNED

● Phase indicator: progress● Score and badges: performance● Detecting errors: students blocked

… and that going back to the instructor computer to check the dashboard was not optimal

A GAME IS FORMED BY...

● Zones: a virtual area in which the player can enter or exit

● Variables: a variable with a meaningful weight inside the game

● Choices: a set of options offered to the player, usually with different consequences

● Quests: the current goal of the player, the next thing he needs to accomplish to advance in the game

GAME MODEL

● A zones graph: representing the map of the game

● A list of variables: containing all meaningful variables in the game

● A list of choices: all choices players can face during gameplay

● A list of quests: containing all the quests players can complete inside the game.

Player action Event Target Value

Gameplay started start Empty Empty

Gameplay ended end Empty Empty

Entered in a zone. Implicitily, exits any previous zone

zone Empty Zone identifier

Variable value updated var Variable name

New variable value

Quest started quest_started Quest id Empty

Quest finished quest_finished Quest id Quest result

Selected an option in a choice

choice Choice id Option id

TRACES

PLAYER GAMEPLAY STATE

"time": time // Time since the gameplay started"zone": "zoneId" // Current zone Id, "zones": { // Number of visits to each zone

"zone1": counter, "zone2": counter, ...

}, "vars": { // Current value of the variables

"var1": value, "var2": value, ...

}, "quests_finished": ["quest1", "quest2", ...], "quests_started": ["quest3", "quest4", ...],"choices": { // Counter of options selected in each choice

"choice1": { "option1": counter

} }

ASESSMENT MODEL

● Score– Overall performance of the player

● Progress – General progress in the game. How long until the

player is done with the simulation

● Alerts – Gameplay state in an undesired condition

– Might need instructor intervention

EXAMPLE: SUPER MARIO BROS.

GAME MODEL

TRACES

GAMEPLAY STATE

ASESSMENT MODEL

ASESSMENT MODEL IN GLEANER

CLASSROOM SUMMARY

PLAYERS LIST

INDIVIDUAL PLAYER VIEW

WHAT WE HAVE

● Simulations, traces and assessment models● Framework to track and assess simulations in

real time

NEXT

● Building assessment models automatically– Using extra data in the simulation model

● All data stored in GLEANER is in a non-standard format...– xAPI

● For interactions data, so others can perform analysis● For assessment results, so it can be shared with a

LMS, LRS...

THANKS!