A novel machine learning analysis of eye-tracking data reveals suboptimal visual information extraction from facial stimuli in individuals with autism

Magdalena Król , Michał Król


We propose a new method of quantifying the utility of visual information extracted from facial stimuli for emotion recognition. The stimuli are convolved with a Gaussian fixation distribution estimate, revealing more information in those facial regions the participant fixated on. Feeding this convolution to a machine-learning emotion recognition algorithm yields an error measure (between actual and predicted emotions) reflecting the quality of extracted information. We recorded the eye-movements of 21 participants with autism and 23 age-, sex- and IQ-matched typically developing participants performing three facial analysis tasks: free-viewing, emotion recognition, and brow-mouth width comparison. In the emotion recognition task, fixations of participants with autism were positioned on lower areas of the faces and were less focused on the eyes compared to the typically developing group. Additionally, the utility of information extracted by them in the emotion recognition task was lower. Thus, the emotion recognition deficit typical in autism can be at least partly traced to the earliest stage of face processing, i.e. to the extraction of visual information via eye-fixations.
Author Magdalena Król (Filia we Wrocławiu / II Wydział Psychologii we Wrocławiu)
Magdalena Król,,
- II Wydział Psychologii we Wrocławiu
, Michał Król
Michał Król,,
Journal seriesNeuropsychologia, ISSN 0028-3932, (N/A 100 pkt)
Issue year2019
Publication size in sheets0.5
Keywords in EnglishAutism spectrum disorder; Eye-tracking; Machine-learning; Face processing; Face emotion recognition
ASJC Classification2802 Behavioral Neuroscience; 2805 Cognitive Neuroscience; 3205 Experimental and Cognitive Psychology
URL https://doi.org/10.1016/j.neuropsychologia.2019.04.022
Languageen angielski
A novel machine_tekst.pdf 1.09 MB
Additional file
A novel machine_oswiadczenie_Krol.pdf 276.52 KB
Score (nominal)100
Score sourcejournalList
Publication indicators Scopus SNIP (Source Normalised Impact per Paper): 2016 = 1.12; WoS Impact Factor: 2017 = 2.888 (2) - 2017=3.325 (5)
Citation count*8 (2021-03-01)
Share Share

Get link to the record

* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.
Are you sure?