At the end of the last year, an Educational Data Mining competition called NAEP Data Mining Competition 2019 was held. This competition aimed to understand which behaviours are effective or ineffective in performing online assessments and to determine how quickly these behaviours can be detected.
Cristina Villa-Torrano, a PhD candidate in the GSIC-EMIC Research Group, together with the rest of the group, participated in this competition. To solve this challenge, the proposal was based on modeling the evolution of student behaviour throughout the online assessment, considering different characteristics such as the sequence of activities performed and the order in which they were carried out. The proposed classifier was based on the LSTM neural network architecture, as it is capable of capturing evolutionary patterns over time.
The NAEP Data Mining Competition 2019 had 89 individual and team participants. The final scoreboard was announced in April and Cristina Villa-Torrano, along with the GSIC-EMIC Research Group, obtained the 6th position.