Papers › Emotion-Recognition Using Smart Watch Sensor Data: Mixed-Design Study
Emotion-Recognition Using Smart Watch Sensor Data: Mixed-Design Study
Juan C. Quiroz, Elena Geangu, Min Hooi Yong
The archive published only this paper's code-link row. Authors, date and abstract are from arXiv's metadata (CC0), read from the Kaggle arXiv metadata snapshot of 2026-09-12 where its title matched the archive's; the title is the archive's.
This study investigates the use of movement sensor data from a smart watch to infer an individual's emotional state. We present our findings on a user study with 50 participants. The experimental design is a mixed-design study; within-subjects (emotions; happy, sad, neutral) and between-subjects (stimulus type: audio-visual "movie clips", audio "music clips"). Each participant experienced both emotions in a single stimulus type. All participants walked 250m while wearing a smart watch on one wrist and a heart rate monitor strap on their chest. They also had to answer a short questionnaire (20 items; PANAS) before and after experiencing each emotion. The heart rate monitor served as supplementary information to our data. We performed time-series analysis on the data from the smart watch and a t-test on the questionnaire items to measure the change in emotional state. The heart rate data was analyzed using one-way ANOVA. We extracted features from the time-series using sliding windows and used the features to train and validate classifiers that determined an individual's emotion. Participants reported feeling less negative affect after watching sad videos or after listening to the sad music, P < .006. For the task of emotion recognition using classifiers, our results show that the personal models outperformed personal baselines, and achieved median accuracies higher than 78% for all conditions of the design study for the binary classification of happiness vs sadness. Our findings show that we are able to detect the changes in emotional state with data obtained from the smartwatch as well as behavioral responses.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections