CoChat

Identifying and Avoiding Confusion in Dialogue with People with Alzheimer's Disease

Open access
Chinaei, Hamidreza, Currie, Leila Chan, Danks, Andrew, Lin, Hubert, Mehta, Tejas, Rudzicz, Frank · 2017 · Computational Linguistics

The DOI matches its Crossref record; 65 of the 66 references it cites were found in a registry or an index.

Abstract

Alzheimer's disease (AD) is an increasingly prevalent cognitive disorder in which memory, language, and executive function deteriorate, usually in that order. There is a growing need to support individuals with AD and other forms of dementia in their daily lives, and our goal is to do so through speech-based interaction. Given that 33% of conversations with people with middle-stage AD involve a breakdown in communication, it is vital that automated dialogue systems be able to identify those breakdowns and, if possible, avoid them. In this article, we discuss several linguistic features that are verbal indicators of confusion in AD (including vocabulary richness, parse tree structures, and acoustic cues) and apply several machine learning algorithms to identify dialogue-relevant confusion from speech with up to 82% accuracy. We also learn dialogue strategies to avoid confusion in the first place, which is accomplished using a partially observable Markov decision process and which obtains accuracies (up to 96.1%) that are significantly higher than several baselines. This work represents a major step towards automated dialogue systems for individuals with dementia.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1162/coli_a_00290

Cites

65 of 65 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 The standardized Cookie Theft picture (Goodglass and Kaplan 1983).
Figure 1 The standardized Cookie Theft picture (Goodglass and Kaplan 1983).CC-BY-NC-ND · From the PDF
Figure 2 Accuracy, sensitivity, and specificity of TIB detection with logistic regression on Control and Dementia data (processed with 3NN-Imputation and SMOTE).
Figure 2 Accuracy, sensitivity, and specificity of TIB detection with logistic regression on Control and Dementia data (processed with 3NN-Imputation and SMOTE).CC-BY-NC-ND · From the PDF
Figure 3 Accuracy, sensitivity, and specificity of TIB detection with MDN (100 hidden units, 6,000 max training cycles) on Control and Dementia data (processed with 3NN-Imputation and SMOTE).
Figure 3 Accuracy, sensitivity, and specificity of TIB detection with MDN (100 hidden units, 6,000 max training cycles) on Control and Dementia data (processed with 3NN-Imputation and SMOTE).CC-BY-NC-ND · From the PDF
Image 4
CC-BY-NC-ND · From the PDF
Image 5
CC-BY-NC-ND · From the PDF
Figure 4 Accuracy, sensitivity, and specificity of TIB detection with MDN (scaled number of hidden units, 6,000 max training cycles) on Control and Dementia data (processed with 3NN-Imputation and SMOTE).
Figure 4 Accuracy, sensitivity, and specificity of TIB detection with MDN (scaled number of hidden units, 6,000 max training cycles) on Control and Dementia data (processed with 3NN-Imputation and SMOTE).CC-BY-NC-ND · From the PDF
Image 7
CC-BY-NC-ND · From the PDF
Image 8
CC-BY-NC-ND · From the PDF
Figure 5 MDN(scaling hidden units, 6,000 max training cycles) on combined data (processed with 3NN-Imputation and SMOTE). Values corresponding to 10, 20,... features are shown. Peak accuracy of 81.70% at 20 features, peak sensitivity of 63.88% at 20 features, and peak specificity of 90.51% at 20 features.
Figure 5 MDN(scaling hidden units, 6,000 max training cycles) on combined data (processed with 3NN-Imputation and SMOTE). Values corresponding to 10, 20,... features are shown. Peak accuracy of 81.70% at 20 features, peak sensitivity of 63.88% at 20 features, and peak specificity of 90.51% at 20 features.CC-BY-NC-ND · From the PDF
Figure 6
Figure 6 CC-BY-NC-ND · From the PDF
Figure 7 Accuracy of n -way classification, using TIB-clusters and the no-TIB class, for each of Dementia, Control, and combined data sets using each of the regression and MDN models.
Figure 7 Accuracy of n -way classification, using TIB-clusters and the no-TIB class, for each of Dementia, Control, and combined data sets using each of the regression and MDN models.CC-BY-NC-ND · From the PDF
Figure 8 Mean number of dialogue turns in learned POMDP policies, and the baseline policies.
Figure 8 Mean number of dialogue turns in learned POMDP policies, and the baseline policies.CC-BY-NC-ND · From the PDF
Figure 9 Mean number of accumulated rewards in learned POMDP policies, and the baseline policies.
Figure 9 Mean number of accumulated rewards in learned POMDP policies, and the baseline policies.CC-BY-NC-ND · From the PDF

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 65 references

Research works printed but not linked: 2

  1. Choi, J. and K.E. Kim. 2011. Inverse reinforcement learning in partially observable environments. Journal of Machine Learning Research, 12:691–730.
  2. 10.1353/lan.1977.0041 · doi:10.1353/lan.1977.0041 · Paper page

Cited by

See all 30

Metadata

Authors
Chinaei, H., Currie, L. C., Danks, A., Lin, H., Mehta, T., & Rudzicz, F.
Affiliations
University of Toronto (CA)
Venue
Computational Linguistics
Publisher
MIT Press
Published
2017-06
Volume
43
Issue
2
Pages
377-406
ISSN
  • 0891-2017 (ISSN-L)
  • 1530-9312
OpenAlex
W2602799059
Cited by
30
References
66
Citations by year
2026: 2 · 2025: 3 · 2024: 2 · 2023: 1 · 2022: 2 · 2021: 4 · 2020: 8 · 2019: 7 · 2018: 1
FWCI
2.61
Type
journal article
Language
en
Open access
Licence
cc-by-nc-nd
Locations
  • Computational Linguistics (publishedVersion, cc-by-nc-nd)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
Funders
  • University of Pittsburgh
  • Carnegie Mellon University
  • AGE-WELL
  • Alzheimer Society
  • National Institutes of Health (AG005133, AG005133 and AG003705)
  • Natural Sciences and Engineering Research Council of Canada (RGPIN 435874)
  • National Institute on Deafness and Other Communication Disorders (DC008524, R01DC008524)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
  • Health Sciences › Medicine › Psychiatry and Mental health › Dementia and Cognitive Impairment Research
  • Social Sciences › Arts and Humanities › Language and Linguistics › Language, Discourse, Communication Strategies
Keywords
Alzheimer's disease, dementia, communication breakdown, confusion detection, speech-based interaction, dialogue strategies, lexical diversity, acoustic cues, partially observable Markov decision processes, conversational support

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Identifying and Avoiding Confusion in Dialogue with People with Alzheimer's Disease. https://app.cochat.ai/papers/10.1162/coli_a_00290
The paper
Chinaei, H., Currie, L. C., Danks, A., Lin, H., Mehta, T., & Rudzicz, F. (2017). Identifying and Avoiding Confusion in Dialogue with People with Alzheimer's Disease. Computational Linguistics. https://doi.org/10.1162/coli_a_00290

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.