DementiaBank-Emotion: A Multi-Rater Emotion Annotation Corpus for Alzheimer's Disease Speech (Version 1.0)
Abstract
We present DementiaBank-Emotion, the first multi-rater emotion annotation corpus for Alzheimer's disease (AD) speech. Annotating 1,492 utterances from 108 speakers for Ekman's six basic emotions and neutral, we find that AD patients express significantly more non-neutral emotions (16.9%) than healthy controls (5.7%; p < .001). Exploratory acoustic analysis suggests a possible dissociation: control speakers showed substantial F0 modulation for sadness (Delta = -3.45 semitones from baseline), whereas AD speakers showed minimal change (Delta = +0.11 semitones; interaction p = .023), though this finding is based on limited samples (sadness: n=5 control, n=15 AD) and requires replication. Within AD speech, loudness differentiates emotion categories, indicating partially preserved emotion-prosody mappings. We release the corpus, annotation guidelines, and calibration workshop materials to support research on emotion recognition in clinical populations.
Keywords
Cite
@article{arxiv.2602.04247,
title = {DementiaBank-Emotion: A Multi-Rater Emotion Annotation Corpus for Alzheimer's Disease Speech (Version 1.0)},
author = {Cheonkam Jeong and Jessica Liao and Audrey Lu and Yutong Song and Christopher Rashidian and Donna Krogh and Erik Krogh and Mahkameh Rasouli and Jung-Ah Lee and Nikil Dutt and Lisa M Gibbs and David Sultzer and Julie Rousseau and Jocelyn Ludlow and Margaret Galvez and Alexander Nuth and Chet Khay and Sabine Brunswicker and Adeline Nyamathi},
journal= {arXiv preprint arXiv:2602.04247},
year = {2026}
}
Comments
Accepted at HeaLING Workshop @ EACL 2026. 9 pages, 3 figures, 8 tables