Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 50 of the 50 references it cites were found in a registry or an index; 5 of the 53 sources its claims cite were checked for support.

Usability assessment of interaction management support in LOUISE, an ECA-based user interface for elders with cognitive impairment

Open access

Abstract

BACKGROUND: Embodied conversational agents (ECA) are possible enablers of assistive technologies, in particular for older adults with cognitive impairment. Yet, dedicated interaction management techniques addressing the specificities of this public are needed. OBJECTIVES: We assess whether the interaction management framework of the LOUISE (Lovely User Interface for Servicing Elders) ECA has the potential to overcome the user interface constraints linked to cognitive impairment. METHODS: LOUISE supports key target-specific features: personalization; attention management; context reminders; image and video displays; a conversation manager for task-oriented interactions; and the foundations for a domain-specific XML-based language for task-oriented assistive scenarios. LOUISE’s usability and acceptance were evaluated at the Broca geriatric hospital in Paris. with a group of 14 older adults with either mild cognitive impairment (MCI) or Alzheimer’s disease (AD) through four simple but realistic assistive scenarios: drinking, taking medicine, measuring blood pressure and choosing the lunch menu. RESULTS: Most of our participants were able to interact with the ECA, succeeded in completing the proposed tasks and enjoyed our design. CONCLUSION: The field usability evaluation of LOUISE’s interaction management framework suggests that this suite of interaction techniques can be effective in enabling interfaces for users with MCI or AD.

Overview

CoChat Summary

TL;DR

LOUISE, an ECA-based interface with attention management, context reminders, and XML-scripted task dialogs, was evaluated with 14 older adults with MCI or Alzheimer’s disease in four assistive scenarios at a geriatric hospital. Most participants could interact and complete tasks and rated it positively, but speech recognition and attention-estimation errors limited usability, especially for more impaired users.

Key findings

  • 13/14 participants were able to interact with LOUISE; the one who could not had the most severe impairment (male, age 73, MMSE 8/30) and seemed intimidated by the character. All 9 participants with MCI successfully accomplished the pill task, while only one participant with Alzheimer’s disease (female, age 83, MMSE 26) completed the blood pressure task without help.
  • In annotated data for 9 participants, there were 258 valid answers, 56 invalid answers (16.3%), 30 no answers (8.7%), 31 cases of no reaction to an answer (9.9%), 59 speech recognition errors with a 20.8% word error rate (range 6.9–33.3%), and 23 attention-estimation errors.
  • Questionnaire ratings from 13 participants on a 1–4 scale were positive: pleasantness mean 3.38, appearance 3.31, clarity of speech 3.54, ease of instruction following 3.38, and pace of conversation 3.46. However, 5 participants (all with MCI) complained the system was too slow.
  • General ECA questions showed varied preferences: 7/13 wanted personalization of embodiment; 7 selected TV and 7 selected tablet as display; 5/13 would accept a camera at home; and 8/13 wanted activation by the user only.

Methods

  • LOUISE was implemented as an ECA system using Kinect-based behavior analysis, attention estimation, speech-turn detection, automatic speech recognition, a finite-state-machine interaction manager, an XML scenario language (AISML), and a BML/SmartBody behavior realizer with image and video display.
  • The usability study was conducted at the Broca geriatric hospital in Paris with 14 participants over 65 diagnosed with cognitive impairment: 9 with MCI and 5 with Alzheimer’s disease, 11 females and 3 males, aged 71–89 (mean 78.8, SD 5.8), with MMSE scores 8–30 (mean 23.8, SD 4.9). Four scenarios were used: drinking water, taking medicine, measuring blood pressure, and choosing a lunch menu; each participant did 3 scenarios in a fixed order.
  • Data included video recordings for 11 participants annotated with Noldus Observer XT 11.5 plus application logs, with quantitative results reported for 9 participants, and post-test 4-level questionnaires (13 participants) plus semi-structured interviews; analysis was descriptive.

Limitations

  • Stated by the authors: this was a small exploratory usability study; only 9 participants contributed to the quantitative table because of video/cloud speech-recognition configuration issues; ASR performance was poor (word error rate >20%) and the system sometimes reacted to its own speech; Kinect range and placement caused attention-estimation errors; the system lacked activity recognition and did not perform well for task guidance with Alzheimer’s disease; the cloud-based ASR was not evaluated with patients; and larger validation is needed.
  • Stated or evident: the study was single-site and hospital-based, had no control group, was mostly female, and used descriptive rather than inferential statistics; the authors also note possible white-coat effects and that some questionnaire responses did not match observed difficulties.
  • Evident from the text: scenario order was fixed and not counterbalanced; some scenarios were not completed by all participants (the water scenario was often cut short because participants said they were not thirsty; one blood pressure scenario was not done because a participant could not move her only arm; one pill scenario was interrupted because the attention estimator was failing).

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.3233/tad-180189

Cites

50 of 50 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Verification

Claims the paper makes

4 Valid · 6 Not valid · 28 Not checked · 59 Own results and interpretations

37 more claims

Create a free account to see all 97 claims and to verify the 1 reference still open.

See all claims — free account
  • Probably not a substantial claim. 29
  • It may state two separate claims as one. 34
  • The quote only partly states this claim. 1

Create a free account to see these claims.

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.

Each contradiction between two passages listed here was confirmed by an independent check.

4 of 4

Citations

Cites

Show all 48 references

Research works printed but not linked: 9

  1. Zancanaro M, 2013, Contrasting responses of older users, 70
  2. FagelS HilbertA MorM MayerC. The Virtual Counselor Automated Character Animation for Ambient Assisted Living. In: Proceedings of 6th International Conference on Advances in Computer-Human Interactions (ACHI’13). IARIA; 2013. p. 184-187.
  3. Czarnuch S, 2012, Alzheimer’s & Dementia., 8, P446
  4. Peters C, 2014, ACM Transactions on Accessible Computing (TACCESS)., 5, 10
  5. Pollack ME, 2005, AI Magazine., 26, 9
  6. BenkaouarW VaufreydazD. Multi-sensors engagement detection with a robot companion in a home environment. In: Workshop on Assistance and Service robotics in a human environment at IEEE International Conference on Intelligent Robots and System (IROS2012); 2012. p. 45-52. from: http//hal.inria.fr/hal-00735150/.
  7. Pejsa T, 2015, ACM Transactions on Interactive Intelligent Systems (TiiS)., 5, 3
  8. Macefield R, 2009, J Usability Studies., 5, 34
  9. CarlettiG. Linguistic anthropology PhD thesis; 2018 (to appear).

Cited by

See all 33

Metadata

Authors
Wargnier, P., Benveniste, S., Jouvelot, P., & Rigaud, A.-S.
Affiliations
  • Université Paris Sciences et Lettres (FR)
  • Hôpital Broca (FR)
Corresponding author
Jouvelot, Pierre
Venue
Technology and Disability
Published
2018-08
Volume
30
Issue
3
Pages
105-126
ISSN
  • 1055-4181 (ISSN-L)
  • 1878-643X
OpenAlex
W2903466273
Cited by
32
References
48
Citations by year
2026: 1 · 2025: 3 · 2024: 5 · 2023: 5 · 2022: 4 · 2021: 4 · 2020: 10
FWCI
4.74
Type
journal article
Language
en
Licence
  • other-oa
  • journals.sagepub.com/page/policies/text-and-data-mining-license (tdm)
Locations
  • Technology and Disability (publishedVersion)
  • HAL (submittedVersion, other-oa)
Topics
  • Social Sciences › Psychology › Social Psychology › Social Robot Interaction and HRI
  • Health Sciences › Medicine › Geriatrics and Gerontology › Technology Use by Older Adults
  • Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
Keywords
embodied conversational agents, interaction management, usability evaluation, older adults with cognitive impairment, mild cognitive impairment, Alzheimer's disease, assistive technology, user interface design, personalization, attention management, task-based interaction, Louise

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.

The claim verdicts this report counts are experimental: their accuracy is not yet measured.

A language model drew the claims from the paper on 2026-10-29, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-29 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Cited sources are checked with a language model’s help (gpt-6-sol).

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: Usability assessment of interaction management support in LOUISE, an ECA-based user interface for elders with cognitive impairment. https://app.cochat.ai/papers/10.3233/tad-180189
The paper
Wargnier, P., Benveniste, S., Jouvelot, P., & Rigaud, A.-S. (2018). Usability assessment of interaction management support in LOUISE, an ECA-based user interface for elders with cognitive impairment. Technology and Disability. https://doi.org/10.3233/tad-180189

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.