BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Early Prediction for Targeted Interventions in Educational Games
DTSTART:20210824T110000
DTEND:20210824T130000
DTSTAMP:20260415T075927Z
UID:c3e1263d8c39fd359de326b3d48b3cbc39034cd99fb35469d1447ba7
CATEGORIES:Conferences - Seminars
DESCRIPTION:Lucas Ramirez\nEDIC candidacy exam\nexam president: Prof. Pier
 re Dillenbourg\nthesis advisor: Prof. Tanja Käser\nco-examiner: Prof. Rob
 ert West\n\nAbstract\nThe open-nature and heterogeneity of open-ended\nlea
 rning environments (OELEs) makes processing their interaction\ndata partic
 ularly challenging. Learner modeling methods\ndeveloped for a specific OEL
 E often do not transfer to other\nOELEs easily\, if at all. This diminishe
 s the generalizability of\ndata processing techniques and reproducibility 
 of experimental\nresults. To tackle this issue\, we propose to define an i
 ntermediate\nrepresentation for student traces derived from interaction da
 ta\nthat could be used universally among a well-defined subset\nof OELEs. 
 Data processing algorithms could then leverage\nthis shared representation
  on interaction data originating from\ndifferent OELEs without methodologi
 cal changes. We hope our\ncontribution can lower the effort required to cr
 eate and evaluate\nnovel digital spaces and learner modeling techniques.\n
 \nBackground papers\n\n	Exploring networks of problem-solving interactions
  (https://dl.acm.org/doi/abs/10.1145/2723576.2723630)\n	Integrating Model-
 Driven and Data-Driven Techniques for Analyzing Learning Behaviors in Open
 -Ended Learning Environments (https://ieeexplore.ieee.org/abstract/documen
 t/7368935)\n	Mapping Python Programs to Vectors using Recursive Neural Enc
 odings (https://educationaldatamining.org/EDM2021/virtual/static/pdf/EDM21
 _paper_J499.pdf)\n
LOCATION:
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR