David Kotz papers for project 'cogvox'

Privacy Concerns of Older Adults Using Voice Assistant Systems

Fri, 26 Aug 2022 00:00:00

Hillary B. Spangler, Tiffany M. Driesse, David H. Lynch, Xiaohui Liang, Robert M. Roth, David Kotz, Karen Fortuna, and John A. Batsis. Privacy Concerns of Older Adults Using Voice Assistant Systems. Journal of the American Geriatrics Society, volume 70, number 12, pages 3643–3647. Wiley, August 26, 2022. doi:10.1111/jgs.18009.

Abstract:

Voice assistant systems (VAS) are software platforms that complete various tasks using voice commands. It is necessary to understand the juxtaposition of younger and older adults' VAS privacy concerns as younger adults may have different concerns impacting VAS acceptance. Therefore, we examined the differences in VAS related privacy concerns across the lifespan.

Evaluating Voice-Assistant Commands for Dementia Detection

Tue, 01 Mar 2022 00:00:00

Xiaohui Liang, John A. Batsis, Youxiang Zhu, Tiffany M. Driesse, Robert M. Roth, David Kotz, and Brian MacWhinney. Evaluating Voice-Assistant Commands for Dementia Detection. Computer Speech and Language, volume 72, article 101297, 13 pages. Elsevier, March 2022. doi:10.1016/j.csl.2021.101297. Special Issue on Speech Based Evaluation of Neurological Diseases.

Abstract:

Early detection of cognitive decline involved in Alzheimer’s Disease and Related Dementias (ADRD) in older adults living alone is essential for developing, planning, and initiating interventions and support systems to improve users’ everyday function and quality of life. In this paper, we explore the voice commands using a Voice-Assistant System (VAS), i.e., Amazon Alexa, from 40 older adults who were either Healthy Control (HC) participants or Mild Cognitive Impairment (MCI) participants, age 65 or older. We evaluated the data collected from voice commands, cognitive assessments, and interviews and surveys using a structured protocol. We extracted 163 unique command-relevant features from each participant’s use of the VAS. We then built machine-learning models including 1-layer/2-layer neural networks, support vector machines, decision tree, and random forest, for classification and comparison with standard cognitive assessment scores, e.g., Montreal Cognitive Assessment (MoCA). Our classification models using fusion features achieved an accuracy of 68%, and our regression model resulted in a Root-Mean-Square Error (RMSE) score of 3.53. Our Decision Tree (DT) and Random Forest (RF) models using selected features achieved higher classification accuracy 80%–90%. Finally, we analyzed the contribution of each feature set to the model output, thus revealing the commands and features most useful in inferring the participants’ cognitive status. We found that features of overall performance, features of music-related commands, features of call-related commands, and features from Automatic Speech Recognition (ASR) were the top-four feature sets most impactful on inference accuracy. The results from this controlled study demonstrate the promise of future home-based cognitive assessments using Voice-Assistant Systems.

Privacy Concerns Among Older Adults Using Voice Assistant Systems

Wed, 01 Dec 2021 00:00:00

Hillary Spangler, Tiffany Driesse, Robert Roth, Xiaohui Liang, David Kotz, and John Batsis. Privacy Concerns Among Older Adults Using Voice Assistant Systems. Innovation in Aging, volume 5, number 1, page 265. Oxford University Press, December 2021. doi:10.1093/geroni/igab046.1023.

Abstract:

Voice Assistant Systems (VAS) are software platforms that complete various tasks using voice commands (e.g., Amazon Alexa), with increasing usage by older adults. It is unknown whether older adults have significant privacy concerns with VAS. 55 participants were evaluated from ambulatory practice sites for a study on VAS detection of early cognitive decline. The mean age was 73.3±5.6 years, 58% female, 93% white, and 53% had mild cognitive impairment. Privacy concerns were assessed via Likert-based surveys. Participants believed data was used with consent (71%) and stored properly (67%); however, 71% wanted new privacy regulations, 43% were comfortable with daily activity monitoring, and 85% thought the data needs to be highly protected. Qualitative themes included “listening-in”, “tracking”, and unwanted sharing of information. Findings suggest that older adults do not have significant privacy concerns for VAS use, but requested additional regulations. Future research can compare VAS privacy concerns between age groups.