TY  - Type of reference 
TI  - Automatic classification of emotions using motion sensors and keystroke dynamics on smartphones 
AU  - Nicolas Simonazzi
 
AU  - Jean-Marc Salotti
 
AU  - Caroline Dubois
 
AU  - Philippe Le Goff 
AB  - We present the results of a study on a binary classification of emotions, based on data collected through motion sensors and keystrokes of a smartphone and a connected bracelet. To this end, we developed a mobile application to induce emotions through videos and record user interactions. A specific digital self-assessment system was developed based on the Geneva Emotion Wheel to help participants express their emotions. The sensor recordings were labelled according to participants’ statements and video conditions. A method is thus proposed to process the collected temporal data and automatically classify the valence of the declared emotions using machine learning techniques. We tested a general valence classification using all emotions from all individuals and a personalized classification using a subset of emotions from a single individual. The most promising result was obtained with a personalized model, for which we were able to obtain, on average across all participants, two-thirds of correct valence classification, using fused data from different modalities. 
DO  - 10.21494/ISTE.OP.2025.1328 
JF  - Cognitive Engineering 
KW  - Emotions classification, emotions detection, Geneva emotion wheel, smartphones usage, cognitics, cognitive engineering, Classification des émotions, détection des émotions, roue des émotions de Genève, usage des smartphones, cognitique, ingénierie cognitive,  
L1  - https://www.openscience.fr/IMG/pdf/iste_ingecog25v8n1_1.pdf 
LA  - en 
PB  - ISTE OpenScience 
DA  - 2025/07/21 
SN  - 2517-6978 
TT  - Classification automatique des émotions par exploitation du capteur de mouvement et de la dynamique de frappe sur smartphone 
UR  - https://www.openscience.fr/Automatic-classification-of-emotions-using-motion-sensors-and-keystroke 
IS  - Issue 1 
VL  - 8 
ER  -