"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 801–900 of 1,007
Emotion and Intention Detection in a Large Language Model
Castro, E., Calvo, H., & Kolesnikova, O. (2025) · Mathematics · doi:10.3390/math13233768 · Cited by 4
From prompt to persona: a literature review on LLMs as single cognitive agents
Tissaoui, A. (2025) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-025-05029-4 · Cited by 5
Generative AI-driven employment recommendations for individuals with disabilities
Werner, S., Ajzenstadt, M., & Winer, A. (2026) · AI & Society · doi:10.1007/s00146-025-02840-7 · Cited by 4
From Counsel to Code: Implications of AI Dependency for Authentic Human Bonds – A Systematic Review
Kamener, K. (2025) · Premier Journal of Artificial Intelligence · doi:10.70389/pjai.100020 · Cited by 3
From User Operations to Agentic Automation: Toward Intent-Oriented Software in the LLM Era
Xie, T., Ran, D.-Z., Cao, Y. J., Meng-Zhou, W. U., Guo, Y.-Z., & Yang, W. (2026) · Journal of Computer Science and Technology · doi:10.1007/s11390-026-6182-0 · Cited by 3
From access to agency: empowering older adults for critical AI use
Choi, S., Rojas‐Alvarez, A., & Salinas, J. J. (2026) · The Gerontologist · doi:10.1093/geront/gnag092 · Cited by 3
Ferrario, A., Vinay, R., Casserini, M., & Facchini, A. (2026) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3805689.3812324 · Cited by 4
“On the one hand, authors defend a positive framing, arguing that the anthropomorphisation of LLM-based CAs may support users’ autonomy and well-being, leading to positive effects such as increased engagement and inclusion, supporting identity formation and trauma recovery [9, 47, 54].”
Intelligence et artifice: Le Magicien d’Oz ou la simulation de l’interaction humain-machine
Alévêque, G. (2019) · Techniques & culture · doi:10.4000/tc.12017 · Cited by 3
Analysing the Use of Voice Assistants in Domestic Settings Through the Lens of Activity Theory
Maier, E., & Reimer, U. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-35602-5_26 · Cited by 3
Usability Analysis of Smart Speakers from a Learnability Perspective for Novel Users
Doi, T., & Nishikawa, Y. (2024) · Applied System Innovation · doi:10.3390/asi7030036 · Cited by 3
Comparing Perceptions of Static and Adaptive Proactive Speech Agents
Edwards, J., Doyle, P. R., Branigan, H. P., & Cowan, B. R. (2024) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3640794.3665548 · Cited by 5
“Likewise, participants’ partner models of the proactive agent were statistically significantly weaker than their partner models of the static agent or their pretest control partner model of speech agents in general, as measured by the PMQ, so H3 was rejected.”
BackgroundMethodInfluentialShared storytelling with a virtual learning companion: prospects in child-AI collaboration
Ong, E., Jesus, C. R. D., Gilig, L. K., & Ong, D. T. (2024) · Research and Practice in Technology Enhanced Learning · doi:10.58459/rptel.2025.20031 · Cited by 3
“…interfaces functioning as digital home assistants such as Siri and Amazon Echo has sparked research interest in investigating how families communicate with computers using these technologies (Beneteau et al., 2019; Cowan et al., 2017; Luger & Sellen, 2016; Sciuto et al., 2018; Ureta et al., 2020).”
BackgroundDo, H. J., Brachman, M., Dugan, C., Johnson, J. M., Lauer, J., Rai, P., & Pan, Q. (2024) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3686902 · Cited by 3
“Therefore, users have to learn how to write inputs that the system can reliably process and find it difficult to form accurate mental models about system capabilities [66, 71].”
Nagai, N., Miyamoto, T., & Katagami, D. (2025) · Applied Sciences · doi:10.3390/app15073897 · Cited by 4
NexOz - A Wizard of Oz Approach to Facilitate the Integration of AI in Interactive Systems
Menten, R., Ruiz, G. A. R., & Vanacken, D. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-91760-8_8 · Cited by 3
Gao, E., Zhong, H., Yuan, R., Guo, J., & Chen, Z. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-93733-0_21 · Cited by 6
A Smart Mirror to Your Health: Personalized Virtual Coaching for Active and Healthy Ageing
Santofimia, M. J., del Toro, X., Peño, C. B., Dorado, J., & Colantonio, S. (2025) · Intelligent systems reference library · doi:10.1007/978-3-031-84158-3_10 · Cited by 3
Villa, L., Hervás, R., Cabañero, L., Fontecha, J., López, G., & Favela, J. (2025) · Behaviour and Information Technology · doi:10.1080/0144929x.2025.2546976 · Cited by 3
“The interaction starts with users uttering a wake word followed by an inquiry, and only then the agent responds to the user, so conversations are highly constrained, task-oriented, and impersonal (Clark et al. 2019; Doyle et al. 2019; Luger and Sellen 2016).”
Rojc, M., Kačič, Z., & Mlakar, I. (2018) · InTech eBooks · doi:10.5772/intechopen.75599 · Cited by 3
“One of the key challenges in the modern human-machine interaction (HMI) is the generation of more natural, more personalized, and more human-like human-machine interaction [1].”
BackgroundComparing Wizard of Oz & Observational Studies for Conversational IR Evaluation
Elsweiler, D., Frummet, A., & Harvey, M. (2020) · Datenbank-Spektrum · doi:10.1007/s13222-020-00333-z · Cited by 3
“Another challenge is that, although considerable progress has been made in recent years, many of the technologies that would be required to fulfil the vision of true conversational search, such as accurate speech recognition or dialogue modelling, do not yet work sufficiently [4].”
BackgroundLiao, Q., Zhang, S., Wang, M., Li, J., Wang, X., & Deng, X. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-49062-1_14 · Cited by 4
Waters, J., Rodas, M. O., Orden, K. V., & Hricko, M. (2020) · IEEE International Conference on Human-Machine Systems (ICHMS) · doi:10.1109/ichms49158.2020.9209542 · Cited by 4
“[5 ] Military training and operations can be more efficient and effective if operators and intelligent agents understand their roles at any moment in the dynamic interaction required to accomplish a mission.”
BackgroundAn intimate virtual counselor for a better user experience
Potdevin, D., Sabouret, N., & Clavel, C. (2020) · ACM International Conference on Intelligent Virtual Agents (IVA) · doi:10.1145/3383652.3423859 · Cited by 3
Exploring User Experience of Automatic Documentation Tools
Wu, S., Zhou, Y., & Wang, X. (2021) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3411763.3451606 · Cited by 5
“Users often have overly high expectations towards smart or intelligent tools [24], which can eventually hurt the user experience.”
BackgroundObstacle Judgment Model of In-vehicle Voice Interaction System Based on Eye-tracking
Yan, X., Hou, W., & Xu, X. (2021) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd49262.2021.9437635 · Cited by 4
“Since 1990, through interviews and observation, researchers found that people are required to do additional work to understand the reasons for malfunctions and attempt to repair control failures in voice assistants [14] [15].”
Background“Can You Search for Me?”: Understanding and Improving User‐System Dialogues for Complex Search Tasks
Ghosh, S. (2021) · Proceedings of the Association for Information Science and Technology · doi:10.1002/pra2.446 · Cited by 3
“Findings from prior research (Sa & Yuan, 2020; Turunen et al., 2012; Luger & Sellen, 2016) have highlighted that conversation systems are task-based and incapable of performing complex or exploratory search tasks.”
Methodvan der Zandt, L., van der Stappen, E., & van Turnhout, K. (2021) · Electronic workshops in computing · doi:10.14236/ewic/hci2021.33 · Cited by 3
“This notion became mainstream in the field of study to conversational agents since the 2016 publication by Luger and Sellen (2016), which mentions a ‘gulf of evaluation’ for conversational agents.”
BackgroundResultDo smart speaker skills support diverse audiences?
Shafei, H. A., & Tan, C. C. (2022) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2022.101716 · Cited by 4
Interacting with the News Through Voice User Interfaces
Nordberg, O. E., & Guribye, F. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-25581-6_2 · Cited by 3
Yoo, Y., Jung, J., Kang, C., Kim, H., & Jun, S. (2024) · Archives of Design Research · doi:10.15187/adr.2024.02.37.1.123 · Cited by 3
Toward Faceted Skill Recommendation in Intelligent Personal Assistants
Kalirai, M., Williams, A. C., & Kuzminykh, A. (2024) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3640543.3645201 · Cited by 4
“Most IPA commands often conflict with the familiar and natural phrasing used in everyday human-to-human conversations [44, 61], and remembering these commands imposes a considerable cognitive burden—often resulting in users using only the skills (and associated commands) they remember [44, 61, 64].”
BackgroundRe-evaluating the Command-and-Control Paradigm in Conversational Search Interactions
Trippas, J. R., Gallagher, L., & Mackenzie, J. (2024) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3627673.3679588 · Cited by 7
“Conversational assistants, exemplified by well-known systems like Siri, Alexa, and Google Assistant, work predominantly on a command-and-control paradigm, where user inputs are typically explicit queries or commands [25, 39, 58].”
Baumann, M., Markus, A., Pfister, J., Carolus, A., Hotho, A., & Wienrich, C. (2025) · Computers in Human Behavior Reports · doi:10.1016/j.chbr.2025.100610 · Cited by 3
Assessing Effectiveness and Interpretability of Light Behaviors in Smart Speakers
Kunchay, S., & Abdullah, S. (2021) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3469595.3469610 · Cited by 5
“The aforementioned work demonstrates that users often require visual confirmation before performing sensitive, important, and impactful tasks [22] such as sending texts and making calls.”
BackgroundTransparency in Language Generation: Levels of AutomationPreprint
Edwards, J., Perrone, A., & Doyle, P. R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.06295 · Cited by 4
“Subsequent failure to meet these expectations can lead to frustration, limited use and even abandonment of CUIs [8].”
BackgroundA proposed methodology for investigating chatbot effects in peer review
Lin, M. P.-C. (2020) · Summit (Simon Fraser University) · Cited by 12
Kaushik, A. (2021) · Dublin City University Open Access Institutional Repository (Dublin City University) · Cited by 4
Degachi, C., Freire, S. K., Niforatos, E., & Kortuem, G. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2506.03807 · Cited by 4
“Moreover, we also see much concern about system inconsistency, as well as feelings of distrust and disappointment that may form barriers to effective genCA search utilization and adoption, as observed in voice assistants [44, 47].”
InfluentialChang, R.-C., Natalie, R., Xu, W., Yap, J. Z. F., & Guo, A. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.03651 · Cited by 3
“Users could also fine-tune models with personal data (e.g., images of their belongings) [41, 67] for more personalized experiences.”
InfluentialBeyond the Hype: Mapping Uncertainty and Gratification in AI Assistant UsePreprint
Joy, K., Ammari, T., & Sheehan, A. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2506.09220 · Cited by 3
“User autonomy is especially critical [21], aligning with long-standing debates between user-controlled systems and agent-based automation [8, 52, 63].”
Verbraucherinformatik: Grundlagen und Anwendungsfelder der digitalen Konsumgesellschaft
Boden, A., Stevens, G., Recki, L., Bossauer, P., & Schreiber, D. (2024) · Springer eBooks · doi:10.1007/978-3-662-68706-2 · Cited by 2
Sistemas conversacionales: entre la privacidad y la funcionalidad de las interacciones
Valdivia, A. K. C. (2023) · Jurídicas · doi:10.17151/jurid.2023.20.2.12 · Cited by 2
Unpacking the Interface: The Impact of Design Choices on Users' Relationship with Raaji
Khan, K. L., & Azhar, F. (2024) · ACM International Conference on Design of Communication (SIGDOC) · doi:10.1145/3641237.3691662 · Cited by 3
Morsello, B., & Bonomo, C. (2024) · Journal of Gender Studies · doi:10.1080/09589236.2024.2431589 · Cited by 2
“This indicates that people increasingly interact by voice with a growing number of smart devices, and conversation is becoming an essential mode of human – computer interaction (Luger & Sellen, 2016).”
The Ethical Aspects of Chatbots and Beyond
Ahmad, N. (2025) · Advances in medical technologies and clinical practice book series · doi:10.4018/979-8-3693-3112-5.ch010 · Cited by 2
Valente, P., Magalhães, J., & Nóbrega, R. (2025) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3708557.3716360 · Cited by 3
Integrating Proactive Conversational Agents in Hybrid User Interfaces: A Task-Based Analysis
Valente, P. (2025) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3708557.3716145 · Cited by 2
“Recent advances in CAs have highlighted both their potential and limitations in supporting user tasks [9, 13].”
Ferland, L., Owan, R., Kunkel, Z., Qu, H., Gini, M. L., & Koutstaal, W. (2025) · ACM Transactions on Interactive Intelligent Systems · doi:10.1145/3725738 · Cited by 3
“Past evidence suggests that more “human-like” behaviors can lead users to believe CAs are more capable than they actually are, which in turn leads to disappointment, frustration, and potential abandonment of the technology [18, 62, 102].”
Teaching Things To Think: Bootstrapping Local Reasoning for Smart(er) Devices
King, E., Yu, H., Vartak, S., Jacob, J., Lee, S., & Julien, C. (2025) · IEEE International Conference on Pervasive Computing and Communications · doi:10.1109/percom64205.2025.00027 · Cited by 3
“NLU struggles with loosely-constrained commands, which contributes to high user friction and dissatisfaction [37]–[39].”
Voice-Activated AI and The Evolution of Communication Etiquette
GÜVENDİ, N. E. (2025) · Intermedia International e-journal · doi:10.56133/intermedia.1614189 · Cited by 2
Hornbæk, K., Kristensson, P. O., & Oulasvirta, A. (2025) · Oxford University Press eBooks · doi:10.1093/oso/9780192864543.003.0018 · Cited by 2
A Depth Camera-Based Pointing Control System for Appliance Interaction
Lin, Z., Chen, C., & Hsieh, Y. (2025) · International Conference on Computer Communication and the Internet (ICCCI) · doi:10.1109/iccci65070.2025.11158373 · Cited by 2
Conversational Web Browsing: Where Do Existing DesignGuidelines Fall Short?
Piro, L., Verma, H., & Matera, M. (2025) · Biannual Conference of the Italian SIGCHI Chapter (CHItaly) · doi:10.1145/3750069.3750161 · Cited by 2
Design Thinking and AI: Facilitating HCAI Solutions
Böckle, M., Mohme, U., & Bick, M. (2025) · Springer eBooks · doi:10.1007/978-981-97-8440-0_73-1 · Cited by 2
Neuhaus, R., Laschke, M., Ringfort-Felner, R., & Hassenzahl, M. (2025) · International Academic Mindtrek Conference (Mindtrek) · doi:10.1145/3757980.3758001 · Cited by 2
Determinants of customer acceptance of frontline service robots in a retail context
Chaysang, A., Patterson, P., Kimpakorn, N., & Chaisuwan, C. (2025) · Journal of Services Marketing · doi:10.1108/jsm-02-2025-0109 · Cited by 4
Donato, B. D., Romeo, M., & Aylett, M. P. (2025) · Audio Mostly Conference (AM) · doi:10.1145/3771594.3771608 · Cited by 2
EmSim: AI-Driven VR Simulation for De-Escalation Training in Law Enforcement
Wang, D., Liang, K., Song, W., Zheng, Q., Sheikh, Z., Whiting, J., Lu, V., Yao, M., & Cao, C. G. L. (2026) · IEEE International Conference on Artificial Intelligence and eXtended and Virtual Reality (AIxVR) · doi:10.1109/aixvr67263.2026.00014 · Cited by 2
“This observation supports broader HCI research suggesting that mild AI imperfections can enhance authenticity and trust in human-AI interaction, especially when the goal is to simulate real human variability [26], [27].”
Li, L., Herath, S., & Grumbach, C. (2026) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3772363.3798678 · Cited by 2
“However, evidence from HCI and human–AI collaboration also cautions that fluent, continuous agent feedback can exacerbate over-reliance and reduce reflective engagement and divergent thinking, especially when systems remain overly agreeable throughout the innovation process [3, 28].”
Conversational Successes and Breakdowns in Everyday Smart Glasses Use
Zhu, X., Liu, X., Harteveld, C., Desai, S., & McGivney, E. (2026) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3772363.3798378 · Cited by 3
"Why Doesn't He Just Ride the Robot Vacuum?": Humor in Everyday Interactions with Smart Homes
Liu, R., & Wu, Y. (2026) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3772363.3798925 · Cited by 2
“Prior work has shown how discrepancies between system models and users’ situated understandings give rise to inter-actional trouble, and how breakdowns can be revealing moments that expose assumptions embedded in technological design [22].”
Voices of the crowd: Exploring user evaluations of ChatGPT using structural topic modeling
Ding, K., Yang, Y., Zhao, D., Sun, X., & Wang, L. (2026) · Acta Psychologica · doi:10.1016/j.actpsy.2026.106827 · Cited by 2
Çelik, A. A., Balcioğlu, Y. S., & Altındağ, E. (2026) · International Journal of Tourism Cities · doi:10.1080/20565607.2026.2666251 · Cited by 2
Esposito, A., Lanzilotti, R., Matera, M., Piccinno, A., Piro, L., Pucci, E., & Ragone, G. (2026) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2026.2659951 · Cited by 3
Zhang, Y., Ma, Y., Fu, D., Portales, S. Z., Fjeld, M., & Kragić, D. (2026) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2026.2675404 · Cited by 2
Rohida, L., & Resa, E. (2026) · Jurnal Wacana Kinerja Kajian Praktis-Akademis Kinerja dan Administrasi Pelayanan Publik · doi:10.31845/jwk.v29i1.1058 · Cited by 2
“Penelitian (Luger & Sellen, 2016) menunjukkan bahwa penerimaan pengguna terhadap chatbot sangat dipengaruhi oleh persepsi kejelasan komunikasi dan kemampuan sistem dalam menangani kesalahan ( error handling ).”
Exploring Perceptions of Robo-advisors for Personal Investing
Cooney, O., Leonard, S. J., Peña, P. R., Hannah, J., & Cowan, B. R. (2026) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3816046.3816211 · Cited by 2
“Yet such human-likeness may lead to unrealistic expectations as to the agent’s capabilities [42, 45], with the appropriateness of such a design choice needing to be considered more deeply [21, 39].”
Empathy through the Lens of Conversational Agents: A Systematic Review
Khadka, S., & Desai, S. (2026) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3816046.3816220 · Cited by 3
“However, this tendency to anthropomorphize collided with technical reality, creating a “gulf of expectation” [76].”
The CogSIS Project: Examining the Cognitive Effects of Speech Interface Synthesis
Clark, L., Cabral, J. P., & Cowan, B. R. (2018) · Electronic workshops in computing · doi:10.14236/ewic/hci2018.170 · Cited by 2
Evaluating Voice Applications by User-Aware Design Guidelines Using an Automatic Voice Crawler.
Han, X., & YEH, T. P. (2019) · IUI Workshops · Cited by 2
Understanding Anthropomorphism in the Expression and Interaction Between infant and AI Speakers
Chung, J.-H., & Jun, S. (2020) · Journal of Digital Contents Society · doi:10.9728/dcs.2020.21.8.1521 · Cited by 2
Designing a Synthesized Content Feed System for Community Radio
Scott, K. M., Ashby, S., & Stan, A. (2020) · Nordic Conference on Human-Computer Interaction · doi:10.1145/3419249.3420177 · Cited by 2
A Dialogue SystemMaking Humor by Pseudo Mishearing of a Part of Users’ Queries Based on Examples
Seki, Y. (2021) · Transactions of the Japanese Society for Artificial Intelligence · doi:10.1527/tjsai.36-2_c-ka3 · Cited by 2
Sakr, M. (2021) · Springer eBooks · doi:10.1007/978-3-030-70803-0_8 · Cited by 3
Let’s Chat Internal: User Acceptance of an In-Company Service Desk Chatbot
Stütz, L., & Riener, A. (2021) · Mensch und Computer (MuC) · doi:10.1145/3473856.3474005 · Cited by 2
“Keeping chatbots less human-like prevents them from eeriness through the uncanny valley effect [3] and an overes-timation of their capabilities [19] which should be communicated clearly [2, 13].”
BackgroundLi, T. J.-J., Mitchell, T. M., & Myers, B. A. (2021) · Human-computer interaction series · doi:10.1007/978-3-030-82681-9_15 · Cited by 2
Knowledge Modelling for Establishment of Common Ground in Dialogue Systems
Varonina, L., & Kopp, S. (2021) · Italian Journal of Computational Linguistics · doi:10.4000/ijcol.797 · Cited by 2
“For instance, they argue that the predefined request-response format of the interaction with VAs cannot be equated with interactively emerging adjacency pairs, such as question-response, that serve as the basic organisational unit of many of our everyday conversations.”
BackgroundInfluentialLui, M. D. L. C., Oliveira, M. D., Bernardes, R. C., Borini, F. M., & Rodrigo, P. (2022) · International Journal of Innovation and Technology Management · doi:10.1142/s0219877022410097 · Cited by 2
Embrace your incompetence! Designing appropriate CUI communication through an ecological approach
Becker, S., Doyle, P. R., & Edwards, J. (2022) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3543829.3544531 · Cited by 2
“Some suggest the difference between the capabilities of current systems and the polished and professionalsounding human-like voices they use is so stark that it causes critical communication breakdowns leading to very limited use and even abandonment [26, 37, 40].”
BackgroundInfluentialAn Interpretable Word Sense Classifier for Human Explainable Chatbot
Yadav, R. K., Jiao, L., Granmo, O., & Goodwin, M. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-10161-8_13 · Cited by 2
The Effect of Prolonged Exposure to Online Education on a Classroom Search Companion
Aliannejadi, M., Huibers, T. W. C., Landoni, M., Murgia, E., & Pera, M. S. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-13643-6_5 · Cited by 4
“Taking such a SCCC from theory to practice requires that we first understand what children expect from technology, how and why technology is used in a classroom setting, and which factors influence acceptance and success [32].”
BackgroundDesigning AI Agent’s Social Interaction Quality in AI-based Fitness Services as a Mediator
Lee, Y., & Lee, Y. (2022) · Archives of Design Research · doi:10.15187/adr.2022.08.35.3.145 · Cited by 2
Salai, A.-M., Cook, G. A., & Holmquist, L. E. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-42280-5_11 · Cited by 3
Cultural Differences in the Assessment of Synthetic Voices
Cuciniello, M., Amorese, T., Greco, C., Callejas, Z., Vogel, C. M., Cordasco, G., & Esposito, A. A. (2024) · International Journal of Neural Systems · doi:10.1142/s0129065724500084 · Cited by 2
An Assessment for Knowledge Sharing and Collaborative Learning in the Era of ChatGpt-4.0
(2024) · Journal of Logistics Informatics and Service Science · doi:10.33168/jliss.2024.0211 · Cited by 3
Digital Government and AI: Empowering Citizen Participation for a More Inclusive Democracy
Kenaphoom, S., Supsin, J., Suktam, W., & Lapchit, S. (2024) · Practice, progress, and proficiency in sustainability · doi:10.4018/979-8-3693-7989-9.ch007 · Cited by 2
Bhattacharya, A., Eugenio, B. D., Grosso, V., Johnson, A. E., Tabalba, R., Kirshenbaum, N., Leigh, J., & Zellner, M. (2024) · Statistical Analysis and Data Mining The ASA Data Science Journal · doi:10.1002/sam.11714 · Cited by 4
Shaping the Future of Service Marketing
Thandayuthapani, S., Thirumoorthi, P., Krishnan, S. A., Rohini, V., Singh, D. A. P., & Prakash, K. (2025) · IGI Global eBooks · doi:10.4018/979-8-3373-0164-8.ch005 · Cited by 2
Introduction to human–computer interaction
Hornbæk, K., Kristensson, P. O., & Oulasvirta, A. (2025) · Oxford University Press eBooks · doi:10.1093/oso/9780192864543.003.0001 · Cited by 7
Preiß, N., & Westner, M. K. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-6438-2_15 · Cited by 2
Supporting Complex Tasks Using Multiple Devices
Nouri, E., Fourney, A., Sim, R. B., & White, R. W. (2019) · Cited by 9
Paired Conversational Agents for Easy-to-Understand Instruction
Akahori, W., Miyake, A., Sugiyama, H., Watanabe, M., & Minami, H. (2019) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3290607.3312794 · Cited by 2
“Furthermore, Luger and Sellen [5] found that those with lower levels of technical knowledge had a high level of frustration because their high expectations of the conversational agents created mismatch in the perception of system intelligence.”
BackgroundDesign and Implementation of a Disambiguity Framework for Smart Voice Controlled Devices
Lei, K., Ma, T., Jia, J., Zhang, C., & Yang, Z. (2019) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/948 · Cited by 2
How Voice Interface Influences Users’ Music Experience : An Exploratory Study Using YouTube Videos
Jeong, Y., Jeong, Y., Lee, J., Lee, J., Kim, S., Kim, S., Kang, Y., & Kang, Y. (2020) · Archives of Design Research · doi:10.15187/adr.2020.02.33.1.165 · Cited by 2
Human-Centric Preference Modeling for Virtual Agents
Knijnenburg, B. P., & Hubig, N. (2020) · ACM International Conference on Intelligent Virtual Agents (IVA) · doi:10.1145/3383652.3423909 · Cited by 2
“The third problem with existing modeling approaches lies in the fact that most of them are implemented as black box closed-loop systems: they can only be adjusted by changing one’s behaviorÐ explicit control mechanisms are seldomly implemented [21, 24], especially in agent-based systems [3, 29].”
BackgroundArchitekturmuster für Multi-Chatbot-Landschaften: Bot-Orchestrator und Alternativen
Stucki, T., & D’Onofrio, S. (2020) · HMD Praxis der Wirtschaftsinformatik · doi:10.1365/s40702-020-00668-x · Cited by 2
Functions of Imagined Interactions With AI Among Alexa-Users
Gaspard, T., & Madison, T. P. (2021) · Imagination Cognition and Personality · doi:10.1177/02762366211005361 · Cited by 2
“Luger and Sellen (2016) measured how users with a poor understanding of how their VPA worked and lack of feedback led to frustration and discontinued use.”
BackgroundHan, X., & YEH, T. P. (2020) · Cited by 5
Taming the Interaction Jungle: Embodiment is All You Need
Simpson, J., & Richards, D. (2021) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3469595.3469612 · Cited by 2
Predicting Success of a Persuasion through Joint Modeling of Utterance Categorization
Sinha, M., & Dasgupta, T. (2021) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3459637.3482160 · Cited by 2
“3482160 The goal of such agents is to enable a user towards completion of a specific task by providing suitable knowledge and facilitate better human-engagements [2, 9, 16, 31].”
Background
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.