"Like Having a Really Bad PA": The Gulf between User Expectation and Experience of Conversational Agents
The DOI matches its Crossref record; 49 of the 51 references it cites were found in a registry or an index.
Abstract
The past four years have seen the rise of conversational agents (CAs) in everyday life. Apple, Microsoft, Amazon, Google and Facebook have all embedded proprietary CAs within their software and, increasingly, conversation is becoming a key mode of human-computer interaction. Whilst we have long been familiar with the notion of computers that speak, the investigative concern within HCI has been upon multimodality rather than dialogue alone, and there is no sense of how such interfaces are used in everyday life. This paper reports the findings of interviews with 14 users of CAs in an effort to understand the current interactional factors affecting everyday use. We find user expectations dramatically out of step with the operation of the systems, particularly in terms of known machine intelligence, system capability and goals. Using Norman's 'gulfs of execution and evaluation' [30] we consider the implications of these findings for the design of future systems.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“Whereas, we found that the challenges our participants experienced were more elementary.”
From Exploring How Older Adults Use a Smart Speaker–Based Voice Assistant in Their First Interactions: Qualitative Study (2021) · cites this paper as [32]
In the citing paper
“In addition, it could be more important for novice users to have an appropriate mental model and understand the system rather than an efficient user experience [32].”
From Exploring How Older Adults Use a Smart Speaker–Based Voice Assistant in Their First Interactions: Qualitative Study (2021) · cites this paper as [32]
In the citing paper
“human-AI mixed-initiative presents a generally valuable and underexplored interface paradigm.”
From Mixed-Initiative Creative Interfaces (2017) · cites this paper as [20]
In the citing paper
“Not only do these breakdowns significantly diminish user satisfaction and damage trust, they also decrease the likelihood of continued use [18, 44].”
From System and User Strategies to Repair Conversational Breakdowns of Spoken Dialogue Systems: A Scoping Review (2024) · cites this paper as [44]
In the citing paper
“This is because when voice assistants fail, such as by incorrectly answering a question, it derails user trust [27, 35].”
From A Mixed-Methods Approach to Understanding User Trust after Voice Assistant Failures (2023) · cites this paper as [35]
17 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
How Many Interviews Are Enough?: An Experiment with Data Saturation and Variability
Guest, G., Bunce, A., & Johnson, L. (2006) · Field Methods · doi:10.1177/1525822x05279903 · Cited by 20,808
(2010) · Sociology for Pharmacists · doi:10.4324/9780203381175_chapter_9 · Cited by 14,152
Norman, D. (2016) · Vahlen eBooks · doi:10.15358/9783800648108 · Cited by 6,374
Thematic networks: an analytic tool for qualitative research
Attride-Stirling, J. (2001) · Qualitative Research · doi:10.1177/146879410100100307 · Cited by 5,506 · cited 2×
“The thematic network is a ‘web-like coding structure’ [2; 385] that allows for a rich understanding of the conceptual interplay occurring within the narrative.”
Background(1997) · Choice Reviews Online · doi:10.5860/choice.34-3702 · Cited by 4,887
ELIZA—a computer program for the study of natural language communication between man and machine
Weizenbaum, J. (1966) · Communications of the ACM · doi:10.1145/365153.365168 · Cited by 4,452
ELIZA — a computer program for the study of natural language communication between man and machine
Weizenbaum, J. (1983) · Communications of the ACM · doi:10.1145/357980.357991 · Cited by 2,738
Licklider, J. C. R. (1960) · IRE Transactions on Human Factors in Electronics · doi:10.1109/thfe2.1960.4503259 · Cited by 1,938 · cited 1×
“When considering human-machine dialogue from an HCI perspective, some of the earliest work can be traced back to vision statements and position papers such as JCR Licklider (1960), ‘Man-machine symbiosis’ [25] and the early work of Richard Bolt [4].”
MethodEmbodied Conversational Agents
(2000) · The MIT Press eBooks · doi:10.7551/mitpress/2697.001.0001 · Cited by 1,799
Interaction Ritual: Essays on Face-to-face Behaviour
Goffman, E. (1972) · Medical Entomology and Zoology · Cited by 1,449
Research works printed but not linked: 14
- Boden Margaret A, 2007, Proceedings of Artificial Companions in Society: Perspectives on the Present and Future. Oxford Internet Institute.
- Davis Martin, Engines of Logic: Mathematicians and the Origin of the Computer
- Glass James R., 1999, Challenges for Spoken Dialogue Systems. In the proceedings of IEEE Workshop on Automatic Speech Recognition and Understanding. (ASRU), CO, USA
- 10.5555/1941863 · doi:10.5555/1941863
- Heuwinkel Kerstin, Your Virtual Butler: The Making-of. Robert Trappl (ed)
- Robnett Licklider Joseph Carl, 1960, HFE-1,(March
- Moore Roger, Spoken Language Processing: Where do we go from Here? In Your Virtual Butler: The Making-of. Robert Trappl (ed)
- Payr Sabine, Your Virtual Butler: The Making-of. Robert Trappl (ed)
- Preece Jenny, 2015, Interaction Design: Beyond Huma- Computer Interaction
- Pulman Stephen, Proceedings of the 2010 Workshop on Companionable Dialogue Systems. Assoc. for Computational Linguistics
- Trappl Robert, From Jeeves Jeannie to Siri, and Then? In Your Virtual Butler: The Making-of. Robert Trappl (ed)
- Vassallo Giorgio, Semantic Computing. Sheu, Yu, Ramamoorthy, Joshi & Zadeh.(eds)
- 10.5555/1870559.1870562 · doi:10.5555/1870559.1870562
- Wilks Yorick, 2010, Amsterdam: John Benjamins.
Cited by
Items 1,001–1,007 of 1,007
Engagement of Parents with the Aurora Child Health Chatbot: A Conversation Log Analysis Study
Liebeatrau, D., Densmore, M., & Nunes, F. (2025) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2025.2492805 · Cited by 2
“…design revealed that a rule-based and domain-specific architecture might restrict its ability to engage in fluid dialogues, aligning with broader research indicating that such constraints often lead to user dissatisfaction (Brandtzaeg & Følstad, 2017; Janssen et al., 2021; Luger & Sellen, 2016).”
How to Convey Resilience: Towards a Taxonomy for Conversational Agent Breakdown Recovery Strategies
Feng, S. (2025) · Lecture notes in information systems and organisation · doi:10.1007/978-3-031-80119-8_18 · Cited by 1
Short-Term Effects of Stepwise Feedback on Driver Readiness on Urban Roads
Jiang, L., Yoshihara, Y., Karatas, N., Kanamori, H., Harada, A., Noda, S., Kawachi, T., Hamada, K., & Tanaka, T. (2025) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv64158.2025.11097655 · Cited by 1
“Low acceptance levels may result in users refusing to rely on such systems [12].”
Chen, C., & He, J. (2025) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2025.2526584 · Cited by 1
“Nonetheless, anthropomorphic dialogues can also have negative impacts if they fail to meet users’ actual mental expectations, potentially compromising user experiences if not addressed (Luger & Sellen, 2016; Zamora, 2017).”
Jaskowska, B. (2025) · Zagadnienia Informacji Naukowej - Studia Informacyjne · doi:10.36702/zin2024.02.01 · Cited by 1
Alqithami, S. (2025) · arXiv · doi:10.48550/arxiv.2512.12856
“…users expect agents to remember preferences that matter for the task while gracefully letting go of stale, incidental, or sensitive details (Luger and Sellen, 2016; Clark, Pantidi, Cooney, Doyle, Garaialde, Edwards, Spillane, Gilmartin, Murad, Munteanu, Wade and Cowan, 2019; Brandtzaeg and…”
(2019) · AICS
Metadata
- Authors
- Luger, E., & Sellen, A.
- Affiliations
- Microsoft Research (United Kingdom) (GB)
- Venue
- Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems
- Publisher
- ACM
- Published
- 2016-05-07
- Pages
- 5286-5297
- OpenAlex
- W2405187948
- Semantic Scholar
- 814e62bb4f0ec6facd640fbd3e3fcbd189716d20
- Cited by
- 1,176
- References
- 51
- Citations by year
- 2026: 164 · 2025: 175 · 2024: 119 · 2023: 116 · 2022: 107 · 2021: 148 · 2020: 141 · 2019: 126 · 2018: 54 · 2017: 25 · 2016: 1
- FWCI
- 37.00
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- CHI Conference on Human Factors in Computing Systems (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Social Sciences › Business, Management and Accounting › Marketing › AI in Service Interactions
- Physical Sciences › Computer Science › Human-Computer Interaction › Innovative Human-Technology Interaction
- Keywords
- chatbots, voice assistants, everyday use, user expectations, human-computer interaction, multimodality, system capabilities, interface design
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
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.