DementiaBank-Emotion: A Multi-Rater Emotion Annotation Corpus for Alzheimer's Disease Speech (Version 1.0)

2026-02-04

AI Summary

This study addresses the lack of multi-annotator emotional speech corpora specifically designed for individuals with Alzheimer’s disease (AD), a gap that has hindered advances in clinical emotion recognition. We present the first such corpus, comprising 1,492 utterances from 108 speakers, manually annotated according to Ekman’s six basic emotions plus neutrality. Acoustic features—including fundamental frequency (F0) and loudness—were analyzed alongside statistical modeling. Results reveal that AD patients exhibit a significantly higher proportion of non-neutral emotional expressions (16.9%) compared to healthy controls (5.7%). While their emotion–prosody mapping is partially preserved—with loudness effectively differentiating emotion categories—their ability to modulate F0 in expressing sadness is markedly impaired. This corpus provides a critical resource and novel empirical evidence for computational approaches to clinical emotion assessment in AD.

Technology Category

• Cognitive Modeling & Cognitive Systems: Affective Computing
• Humans and AI: Emotional Intelligence
• Natural Language Processing: Speech

Application Category

• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization

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.

Problem

• Alzheimer's disease
• emotion annotation
• speech emotion
• DementiaBank
• clinical corpus

Innovation

• emotion annotation
• Alzheimer's disease
• prosody
• multi-rater corpus
• acoustic analysis