Hidden Semi-Markov Models to Segment Reading Phases from Eye Movements - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Journal of Eye Movement Research Year : 2022

Hidden Semi-Markov Models to Segment Reading Phases from Eye Movements

Modèles de semi-Markov cachés pour la segmentation de trajectoires oculométriques en phases de lecture

Abstract

Our objective is to analyze scanpaths acquired through participants achieving a reading task aiming at answering a binary question: Is the text related or not to some given target topic? We propose a data-driven method based on hidden semi-Markov chains to segment scanpaths into phases deduced from the model states, which are shown to represent different cognitive strategies: normal reading, fast reading, information search, and slow confirmation. These phases were confirmed using different external covariates, among which semantic information extracted from texts. Analyses highlighted some strong preference of specific participants for specific strategies and more globally, large individual variability in eye-movement characteristics, as accounted for by random effects. As a perspective, the possibility of improving reading models by accounting for possible heterogeneity sources during reading is discussed.
Fichier principal
Vignette du fichier
8415-Olivieretal-Article (1).pdf (793.6 Ko) Télécharger le fichier
Origin : Publication funded by an institution

Dates and versions

hal-03155843 , version 1 (09-03-2021)
hal-03155843 , version 2 (07-10-2022)

Identifiers

Cite

Brice Olivier, Anne Guérin-Dugué, Jean-Baptiste Durand. Hidden Semi-Markov Models to Segment Reading Phases from Eye Movements. Journal of Eye Movement Research, 2022, 15 (4), pp.5. ⟨10.16910/jemr.15.4.5⟩. ⟨hal-03155843v2⟩
192 View
259 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More