Details
| Original language | English |
|---|---|
| Title of host publication | DIS 2019 |
| Subtitle of host publication | Proceedings of the 2019 ACM Designing Interactive Systems Conference |
| Pages | 1517-1529 |
| Number of pages | 13 |
| ISBN (electronic) | 9781450358507 |
| Publication status | Published - 18 Jun 2019 |
| Event | 2019 ACM Conference on Designing Interactive Systems, DIS 2019 - San Diego, United States Duration: 23 Jun 2019 → 28 Jun 2019 |
Abstract
Conversational interfaces (CIs) have the potential to empower a broader spectrum of users to independently conduct visual analysis. Yet, recent approaches do not fully consider the user's characteristics. In particular, the objective of matching the user's language has been understudied in visual analysis. In order to close this gap, we introduce an answer space motivated by Grice's cooperative principle for framing personalized communication in complex data situations. We conducted both an online survey (N = 76) to analyze communication preferences and a qualitative experiment (N = 10) to investigate personalized conversations with an existing CI. In order to match the user's language properly, our results suggest to consider additional user characteristics along with their knowledge level. While mismatching communication preferences triggers negative reactions, a preference-aligned communication evokes positive reactions. As our analysis confirms the importance of matching the user's language in visual analysis, we provide design implications for future CIs.
Keywords
- Answer space, Conversational design, Conversational interface, Cooperative principle, Personalization, Quantitative and qualitative analysis, Visual analysis
ASJC Scopus subject areas
- Computer Science(all)
- Computer Networks and Communications
- Computer Science(all)
- Human-Computer Interaction
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
DIS 2019: Proceedings of the 2019 ACM Designing Interactive Systems Conference. 2019. p. 1517-1529.
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Talk to me intelligibly
T2 - 2019 ACM Conference on Designing Interactive Systems, DIS 2019
AU - Kassel, Jan Frederik
AU - Rohs, Michael
N1 - Funding information: Any opinions, findings, and conclusions expressed in this paper do not necessarily reflect the views of the Volkswagen Group.
PY - 2019/6/18
Y1 - 2019/6/18
N2 - Conversational interfaces (CIs) have the potential to empower a broader spectrum of users to independently conduct visual analysis. Yet, recent approaches do not fully consider the user's characteristics. In particular, the objective of matching the user's language has been understudied in visual analysis. In order to close this gap, we introduce an answer space motivated by Grice's cooperative principle for framing personalized communication in complex data situations. We conducted both an online survey (N = 76) to analyze communication preferences and a qualitative experiment (N = 10) to investigate personalized conversations with an existing CI. In order to match the user's language properly, our results suggest to consider additional user characteristics along with their knowledge level. While mismatching communication preferences triggers negative reactions, a preference-aligned communication evokes positive reactions. As our analysis confirms the importance of matching the user's language in visual analysis, we provide design implications for future CIs.
AB - Conversational interfaces (CIs) have the potential to empower a broader spectrum of users to independently conduct visual analysis. Yet, recent approaches do not fully consider the user's characteristics. In particular, the objective of matching the user's language has been understudied in visual analysis. In order to close this gap, we introduce an answer space motivated by Grice's cooperative principle for framing personalized communication in complex data situations. We conducted both an online survey (N = 76) to analyze communication preferences and a qualitative experiment (N = 10) to investigate personalized conversations with an existing CI. In order to match the user's language properly, our results suggest to consider additional user characteristics along with their knowledge level. While mismatching communication preferences triggers negative reactions, a preference-aligned communication evokes positive reactions. As our analysis confirms the importance of matching the user's language in visual analysis, we provide design implications for future CIs.
KW - Answer space
KW - Conversational design
KW - Conversational interface
KW - Cooperative principle
KW - Personalization
KW - Quantitative and qualitative analysis
KW - Visual analysis
UR - http://www.scopus.com/inward/record.url?scp=85070612296&partnerID=8YFLogxK
U2 - 10.1145/3322276.3322282
DO - 10.1145/3322276.3322282
M3 - Conference contribution
AN - SCOPUS:85070612296
SP - 1517
EP - 1529
BT - DIS 2019
Y2 - 23 June 2019 through 28 June 2019
ER -