Hi, I'm Aurélien

PhD candidate in computer science

Curiosity

2 minutes
May 16, 2020

Towards measuring states of epistemic curiosity through EEG and physiological signals

Abstract

Understanding the neurophysiological mechanisms underlying curiosity and therefore being able to identify the curiosity level of a person, would bring a very useful tool both to neuroscientists and psychologists, to understand curiosity deeper, as well as to designers of human-computer interaction, in order to trigger curiosity or to adapt an interaction to the curiosity levels of its users. A first step to uncovering the neural correlates of curiosity is to collect neurophysiological signals during states of curiosity, in order to develop signal processing and machine learning (ML) tools to recognize the curious states from the non-curious ones. Thus, we ran an experiment in which we used electroencephalography (EEG) to measure the brain activity of 27 participants as they were induced into states of curiosity, using trivia question and answer chains. Each participant participated in a single session of 4 runs (around 10 minutes each), resulting in a collect of 120 trials. We used two ML algorithms, i.e. Filter Bank Common Spatial Pattern (FBCSP) coupled with a Linear Discriminant Algorithm (LDA) [1], as well as a Filter Bank Tangent Space Classifier (FBTSC) [2], to classify the curious class EEG signals from the non-curious ones. Labels were defined based on both the participant’s choice to reveal the answer (“curious”) or not (“non-curious”) and the participant’s self-reported curiosity rating (1-7). Global results from the within-participant study with five-fold stratified cross-validation indicate that both algorithms obtained better performances in the 3-to-5s time windows, suggesting an optimal time window length of 4 seconds (63.09% classification accuracy for the FBTSC, 60.93% classification accuracy for the FBCSP+LDA) to go towards curiosity states estimation based on EEG signals.

Other members

Jessy Ceha, Smeety Pramij, Dan Dutartre, Edith Law, Pierre-Yves Oudeyer, Fabien Lotte

Collaborations

Publications