Creating persona skeletons from imbalanced datasets - A case study using U.S. Older Adults' health data

Haining Zhu, Hongjian Wang, John Carroll

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Incorporating health personas for older adults into design processes can help designers accurately represent older adults by evoking empathy, facilitating consideration of health issues and needs, and reducing stereotype reliance. Toward this goal, we create a two-level quantitative methodology for constructing persona skeletons from imbalanced datasets. We demonstrate our methodology by constructing a set of 4 care-management personas for U.S. older adults via filtering and analyzing demographic, behavior risk factor, and chronic health conditions from 170,704 randomly sampled older adults in a national survey with imbalanced coverage (i.e. between unconditional & conditional questions). We obtain 4 cluster centers for unconditional questions through K-means and iteratively dropping irrelevant features. Within each cluster, we analyze selected respondents for conditional questions. We synthesize results into persona narratives and provide a weighting scheme to quantitatively measure each persona's significance. We contribute a robust persona construction methodology, here applied towards representing older adults.

Original languageEnglish (US)
Title of host publicationDIS 2019 - Proceedings of the 2019 ACM Designing Interactive Systems Conference
PublisherAssociation for Computing Machinery, Inc
Pages61-70
Number of pages10
ISBN (Electronic)9781450358507
DOIs
StatePublished - Jun 18 2019
Event2019 ACM Conference on Designing Interactive Systems, DIS 2019 - San Diego, United States
Duration: Jun 23 2019Jun 28 2019

Publication series

NameDIS 2019 - Proceedings of the 2019 ACM Designing Interactive Systems Conference

Conference

Conference2019 ACM Conference on Designing Interactive Systems, DIS 2019
CountryUnited States
CitySan Diego
Period6/23/196/28/19

Fingerprint

Health

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Human-Computer Interaction

Cite this

Zhu, H., Wang, H., & Carroll, J. (2019). Creating persona skeletons from imbalanced datasets - A case study using U.S. Older Adults' health data. In DIS 2019 - Proceedings of the 2019 ACM Designing Interactive Systems Conference (pp. 61-70). (DIS 2019 - Proceedings of the 2019 ACM Designing Interactive Systems Conference). Association for Computing Machinery, Inc. https://doi.org/10.1145/3322276.3322285
Zhu, Haining ; Wang, Hongjian ; Carroll, John. / Creating persona skeletons from imbalanced datasets - A case study using U.S. Older Adults' health data. DIS 2019 - Proceedings of the 2019 ACM Designing Interactive Systems Conference. Association for Computing Machinery, Inc, 2019. pp. 61-70 (DIS 2019 - Proceedings of the 2019 ACM Designing Interactive Systems Conference).
@inproceedings{87486d9cbf774276bee02eab481b166f,
title = "Creating persona skeletons from imbalanced datasets - A case study using U.S. Older Adults' health data",
abstract = "Incorporating health personas for older adults into design processes can help designers accurately represent older adults by evoking empathy, facilitating consideration of health issues and needs, and reducing stereotype reliance. Toward this goal, we create a two-level quantitative methodology for constructing persona skeletons from imbalanced datasets. We demonstrate our methodology by constructing a set of 4 care-management personas for U.S. older adults via filtering and analyzing demographic, behavior risk factor, and chronic health conditions from 170,704 randomly sampled older adults in a national survey with imbalanced coverage (i.e. between unconditional & conditional questions). We obtain 4 cluster centers for unconditional questions through K-means and iteratively dropping irrelevant features. Within each cluster, we analyze selected respondents for conditional questions. We synthesize results into persona narratives and provide a weighting scheme to quantitatively measure each persona's significance. We contribute a robust persona construction methodology, here applied towards representing older adults.",
author = "Haining Zhu and Hongjian Wang and John Carroll",
year = "2019",
month = "6",
day = "18",
doi = "10.1145/3322276.3322285",
language = "English (US)",
series = "DIS 2019 - Proceedings of the 2019 ACM Designing Interactive Systems Conference",
publisher = "Association for Computing Machinery, Inc",
pages = "61--70",
booktitle = "DIS 2019 - Proceedings of the 2019 ACM Designing Interactive Systems Conference",

}

Zhu, H, Wang, H & Carroll, J 2019, Creating persona skeletons from imbalanced datasets - A case study using U.S. Older Adults' health data. in DIS 2019 - Proceedings of the 2019 ACM Designing Interactive Systems Conference. DIS 2019 - Proceedings of the 2019 ACM Designing Interactive Systems Conference, Association for Computing Machinery, Inc, pp. 61-70, 2019 ACM Conference on Designing Interactive Systems, DIS 2019, San Diego, United States, 6/23/19. https://doi.org/10.1145/3322276.3322285

Creating persona skeletons from imbalanced datasets - A case study using U.S. Older Adults' health data. / Zhu, Haining; Wang, Hongjian; Carroll, John.

DIS 2019 - Proceedings of the 2019 ACM Designing Interactive Systems Conference. Association for Computing Machinery, Inc, 2019. p. 61-70 (DIS 2019 - Proceedings of the 2019 ACM Designing Interactive Systems Conference).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Creating persona skeletons from imbalanced datasets - A case study using U.S. Older Adults' health data

AU - Zhu, Haining

AU - Wang, Hongjian

AU - Carroll, John

PY - 2019/6/18

Y1 - 2019/6/18

N2 - Incorporating health personas for older adults into design processes can help designers accurately represent older adults by evoking empathy, facilitating consideration of health issues and needs, and reducing stereotype reliance. Toward this goal, we create a two-level quantitative methodology for constructing persona skeletons from imbalanced datasets. We demonstrate our methodology by constructing a set of 4 care-management personas for U.S. older adults via filtering and analyzing demographic, behavior risk factor, and chronic health conditions from 170,704 randomly sampled older adults in a national survey with imbalanced coverage (i.e. between unconditional & conditional questions). We obtain 4 cluster centers for unconditional questions through K-means and iteratively dropping irrelevant features. Within each cluster, we analyze selected respondents for conditional questions. We synthesize results into persona narratives and provide a weighting scheme to quantitatively measure each persona's significance. We contribute a robust persona construction methodology, here applied towards representing older adults.

AB - Incorporating health personas for older adults into design processes can help designers accurately represent older adults by evoking empathy, facilitating consideration of health issues and needs, and reducing stereotype reliance. Toward this goal, we create a two-level quantitative methodology for constructing persona skeletons from imbalanced datasets. We demonstrate our methodology by constructing a set of 4 care-management personas for U.S. older adults via filtering and analyzing demographic, behavior risk factor, and chronic health conditions from 170,704 randomly sampled older adults in a national survey with imbalanced coverage (i.e. between unconditional & conditional questions). We obtain 4 cluster centers for unconditional questions through K-means and iteratively dropping irrelevant features. Within each cluster, we analyze selected respondents for conditional questions. We synthesize results into persona narratives and provide a weighting scheme to quantitatively measure each persona's significance. We contribute a robust persona construction methodology, here applied towards representing older adults.

UR - http://www.scopus.com/inward/record.url?scp=85070641838&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070641838&partnerID=8YFLogxK

U2 - 10.1145/3322276.3322285

DO - 10.1145/3322276.3322285

M3 - Conference contribution

AN - SCOPUS:85070641838

T3 - DIS 2019 - Proceedings of the 2019 ACM Designing Interactive Systems Conference

SP - 61

EP - 70

BT - DIS 2019 - Proceedings of the 2019 ACM Designing Interactive Systems Conference

PB - Association for Computing Machinery, Inc

ER -

Zhu H, Wang H, Carroll J. Creating persona skeletons from imbalanced datasets - A case study using U.S. Older Adults' health data. In DIS 2019 - Proceedings of the 2019 ACM Designing Interactive Systems Conference. Association for Computing Machinery, Inc. 2019. p. 61-70. (DIS 2019 - Proceedings of the 2019 ACM Designing Interactive Systems Conference). https://doi.org/10.1145/3322276.3322285