"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 701–800 of 1,007
Rajaram, S., Surale, H. B., McConkey, C., Rognon, C., Mehta, H., Glueck, M., & Collins, C. M. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3714310 · Cited by 6
Should my Chatbot be Register-Specific? Designing Appropriate Utterances for Tourism
Chaves, A. P. (2020) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3334480.3375033 · Cited by 6
Human Expectations and Perceptions of Learning in Machine Teaching
Mishra, S., & Rzeszotarski, J. M. (2023) · ACM Conference on User Modeling, Adaptation and Personalization (UMAP) · doi:10.1145/3565472.3595612 · Cited by 8
Apprentice of Oz: Human in the Loop System for Conversational Robot Wizard of Oz
Shin, A., Oh, J., & Lee, J. (2019) · ACM/IEEE International Conference on Human-Robot Interaction (HRI) · doi:10.1109/hri.2019.8673205 · Cited by 6
“Conversational robots (CR) are robots that inherit the conversational abilities of a conversational agent, a humanlike dialog system that interacts with users in long, personalized discourses [3].”
BackgroundFerland, L., & Koutstaal, W. (2020) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3334480.3375227 · Cited by 6
PwR: Exploring the Role of Representations in Conversational ProgrammingPreprint
Pradyumna, Y. M., Ganesan, V., Arumugam, D. K., Gupta, M., Shadagopan, N., Dixit, T., Segal, S., Kumar, P., Jain, M., & Rajamani, S. K. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2309.09495 · Cited by 9
“In the pre-LLM era of chatbots, researchers noted a significant gap between user experience and user expectation with respect to the understanding of chatbot [10, 11, 17, 21].”
BackgroundZhu, S., Rzeszotarski, J. M., & Mimno, D. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.05767 · Cited by 7
“Users of conversational agents [50] and smart speakers [65] struggle to discover system capabilities and form accurate mental models without persistent visual cues.”
Bhat, M. (2025) · Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1609/aies.v8i1.36560 · Cited by 9
Lee, M., & Lee, S. (2021) · Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411763.3451812 · Cited by 5
“According to a study by [9], user expectations of the CA system are far from the practical realities of use, and users spent a lot of time trying to get the expected task response from CA.”
BackgroundBotmorphosis in E-commerce: exploring the impact of chatbot eeriness on purchase intentions
Abeden, A. Z. U., Wang, J., Ali, S., & Maqbool, M. (2025) · Behaviour and Information Technology · doi:10.1080/0144929x.2025.2547916 · Cited by 9
“However, chatbots may also be problematic due to users’ diverse expectations and experiences (Luger and Sellen 2016).”
Salminen, J. O., Jung, S., Kaate, I., Xuan, T. T. T., Azem, J. Y., Aldous, K. K., Amin, D., & Jansen, B. J. J. (2026) · Decision Support Systems · doi:10.1016/j.dss.2026.114633 · Cited by 5
Does Sycophancy Change Decisions? Effect of LLM Sycophancy on AI-Assisted Decision-Making
Li, Z., Pan, J., Liu, Q., Xi, Y., Zhou, Y., Jin, Y., Mao, R., & Chen, P. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3790934 · Cited by 13
Petridis, S., Liu, M. X., Fiannaca, A. J., Cai, C. J., & Terry, M. A. (2026) · Designing Interactive Systems Conference · doi:10.1145/3800645.3812956 · Cited by 7
Chatting About Data - Interacting with Voice Interfaces to Engage with Election Panel Data
Jordan, B., Koesten, L. M., & Möller, T. B. (2023) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3571884.3597126 · Cited by 5
Human Speakers Help Machine Listeners To account For Visual Asymmetries in Dialogue
Peña, P. R., Doyle, P. R., Garaialde, D., Wu, Y., McDonnell, R., & Cowan, B. R. (2023) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3571884.3597124 · Cited by 5
“For example, people are more likely to adapt their language choices [1, 10, 23, 58, 62, 63] toward machine interlocutors compared to human interlocutors; they are more likely to engage in audience design in HMD compared to HHD [73, 76]; they are often more likely to align to computer partners than to human partners [8…”
BackgroundResultAgriAid: An Intelligent Farmer Companion Using Deep Learning Approach
Ilakiyaselvan, N., Dhandapani, A., Khadar Nawas, K., & Bhattacharya, A. (2024) · International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics (IITCEE) · doi:10.1109/iitcee59897.2024.10467751 · Cited by 5
“Ewa Luger et al [12] study .’s covered the appearance of chatbots across a range of mobile and ubiquitous platforms.”
BackgroundChatGPT: Advocacy or Opposition Through Mixed Methods
Meah, M. R., & Qin, H. (2024) · Journal of Computer Information Systems · doi:10.1080/08874417.2024.2372036 · Cited by 5
The Field of Usability and User Experience (UX) Design
Ghosh, S., & Dubey, S. (2024) · Advances in social networking and online communities book series · doi:10.4018/979-8-3693-2337-3.ch005 · Cited by 9
Trivedi, C. N., Kumar, S., Mohd, I., Bhalla, R., Lone, N. A., & Dogra, D. (2024) · International Conference on Artificial Intelligence and Quantum Computation-Based Sensor Application (ICAIQSA) · doi:10.1109/icaiqsa64000.2024.10882305 · Cited by 5
LLM-Powered Conversational AI in Customer Service: Users’ Expectations and Anticipated Use
Larsen, A. G., Skjuve, M. B., Kvale, K., & Følstad, A. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-88045-2_14 · Cited by 7
Guedes, L. S., Mitchell, A., Sitbon, L., Dedò, S., & Landoni, M. (2024) · International Conference on Software Development and Technologies for Enhancing Accessibility and Fighting Info-exclusion (DSAI) · doi:10.1145/3696593.3696618 · Cited by 5
“This is in line with the literature that identifies discrepancies between user expectations and experience [24].”
Emotion, Language, and Trust: Rethinking E-Commerce Support with Generative AI and Ethical Messaging
Kole, D., Kapoor, S., Soni, J. A., Sahoo, I., Kumar, U., Bidkar, D. M., Dontireddy, S. R. R., & Aggarwal, A. (2025) · International Conference on Artificial Intelligence and Machine Vision (AIMV) · doi:10.1109/aimv66517.2025.11203627 · Cited by 5
“The findings of the research conducted by Luger and Sellen (2016) has demonstrates that users incline to respond more constructively to systems that clearly recognize themselves as non-human and offer prompt ways to connect with human representatives when necessary.”
Motta, I., & Quaresma, M. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-05412-9_34 · Cited by 6
Towards a comprehensive repair framework for human-chatbot interaction: the case of rephrasing
Asisof, A. (2022) · ACM International Conference on Intelligent Virtual Agents (IVA) · doi:10.1145/3514197.3549641 · Cited by 8
“Repair, defined as “the replacement of an error or mistake by what is correct” [14], has been a prominent field of research in the past decades [3, 4, 8, 11].”
BackgroundDesigning Pedagogical Conversational Agents for Achieving Common Ground
Tolzin, A., Körner, A., Dickhaut, E., Janson, A., Rummer, R., & Leimeister, J. M. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-32808-4_22 · Cited by 10
“As conversational interactions are fragile, especially in learning situations that mimic teacher-student interactions, they can easily fail after misunderstandings during the dialogue and impact the effectiveness between learners and PCAs [8, 9].”
BackgroundLessons Learned from Modeling the Interaction with Conversational Agents
Fernandes, U. D. S., Barbosa, G. A. R., Chagas, B. A., Barbosa, G. D. J., Barbosa, S. D. J., & Prates, R. O. (2023) · Interaction design & architecture(s)/ID&A Interaction design & architecture(s) · doi:10.55612/s-5002-055-007 · Cited by 5
A User Preference and Intent Extraction Framework for Explainable Conversational Recommender Systems
Park, J., Kim, S., & Lee, S. (2023) · ACM SIGCHI Symposium on Engineering Interactive Computing Systems (EICS) · doi:10.1145/3596454.3597178 · Cited by 6
“Specifically, our system helps users build an image of the system by making it easy to interpret the system and enabling positive evaluation of it [20].”
BackgroundAre you sure you want to order that? On Appropriateness of Voice-only Proactive Feedback Strategies
Dubiel, M., Bongard-Blanchy, K., Leiva, L. A., & Sergeeva, A. (2023) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3571884.3604312 · Cited by 6
Bylieva, D. S. (2023) · Lecture notes in networks and systems · doi:10.1007/978-3-031-48020-1_2 · Cited by 5
Modelling the Perceived Pragmatic and Hedonic Quality of Intelligent Personal Assistants
Orehovački, T., Babić, S., & Etinger, D. (2017) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-73888-8_91 · Cited by 5
Miyamoto, T., Katagami, D., Shigemitsu, Y., Usami, M., Tanaka, T., & KANAMORI, H. (2018) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.30.5_753 · Cited by 10
Roussou, M., Perry, S., Katifori, A., Vassos, S., Tzouganatou, A., & McKinney, S. (2019) · Cited by 5
Characterizing Human vs. Automated Coaching: Preliminary Results
Mitchell, E. G., Maimone, R., & Mamykina, L. (2020) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3334480.3383081 · Cited by 5
Tell Me About Your Day: Designing a Conversational Agent for Time and Stress Management
Ferland, L., Sauve, J., Lucke, M., Nie, R., Khadar, M., Pakhomov, S., & Gini, M. L. (2020) · Studies in computational intelligence · doi:10.1007/978-3-030-53352-6_28 · Cited by 5
Heck, M., Shon, S. H., & Becker, C. (2022) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3490099.3511129 · Cited by 5
“It has been found to be especially useful when executing simple tasks that require only minimal input [1, 27].”
BackgroundCross-Modal Repair: Gaze and Speech Interaction for List Advancement
Jaber, R., & McMillan, D. (2022) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3543829.3543833 · Cited by 5
“Luger and Sellen [40] highlighted the limited functionality of existing commercially-available voice interfaces and how it causes a gulf between their capabilities and the users’ expectations.”
BackgroundInfluentialConversational AI in Academia: A Practical Exploration with ChatGPT
Ekellem, E. A. F. (2023) · International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT) · doi:10.1109/ismsit58785.2023.10304845 · Cited by 5
“Luger & Sellen (2016) [6] shed light on the potential discrepancy between user expectations and their actual experiences with conversational agents, pointing to the complexities in creating chatbots that align with human anticipations.”
BackgroundInfluentialChatbot - Magic in a box? : A study of a chatbot in a Swedish bank
Jonsson, S., & Bredmar, J. (2018) · Uppsala University Publications (Uppsala University) · Cited by 5
Towards Teachable Conversational AgentsPreprint
Chhibber, N., & Law, E. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.10387 · Cited by 5
MimiTalk: Revolutionizing Qualitative Research with Dual-Agent AIPreprint
Liu, F., & Yu, S. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2511.03731 · Cited by 5
“This phenomenon forms an interesting contrast with the findings of Luger et al. [35].”
Zhang, C., Zhu, S., Yang, X., Tseng, Y.-C., Jiang, S., & Rzeszotarski, J. M. (2025) · Proceedings of the 7th ACM Conference on Conversational User Interfaces · doi:10.1145/3719160.3736618 · Cited by 4
Challenges in Automatic Speech Recognition for Adults with Cognitive Impairment
Cohn, M., Lanzi, A., Ishihara, Y., Chuah, C.-N., Zellou, G., & Weakley, A. (2026) · Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791581 · Cited by 4
“Understanding these errors has important implications for Human-Computer Interaction (HCI) frameworks.”
Users' error recovery strategies in the interaction with voice assistants (VAs)
Motta, I., & Quaresma, M. (2022) · Lecture Notes in Networks and Systems · doi:10.1007/978-3-030-74614-8_82 · Cited by 4
Beyond the Illusion: LLMs and the Case for Pragmatic Cues in Conversation
Spillner, L., Rockstroh, J., Peña, P. R., Wenig, N., Zargham, N., & Cowan, B. R. (2025) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3719160.3737614 · Cited by 4
Unveiling the two-sided effects of robotic anthropomorphism on consumers’ experience
Mordi, G. T., Elsharnouby, M. H., AbdelAziz, G. S., & Jayawardhena, C. (2025) · Journal of Humanities and Applied Social Sciences · doi:10.1108/jhass-11-2024-0193 · Cited by 4
Exploring Confirmation Strategies for Voice Interaction in Multi-Tasking Scenario
Wang, J., Xu, Z., Zhai, W., & Xu, F. (2025) · International Journal of Social Robotics · doi:10.1007/s12369-025-01302-w · Cited by 4
“…of voice interaction, when users repeatedly encounter inconsistencies between their expected results and the system’s execution results, known as conversation barriers, it negatively affects user experience, and users may be unwilling to delegate complex or sensitive tasks to voice assistants [30].”
Exploring users' mental models of conversational agents: a systematic review
Cena, F., & Grasso, F. (2025) · Behaviour and Information Technology · doi:10.1080/0144929x.2025.2573436 · Cited by 4
“This difference in expectation and reality is caused by the development of an incorrect Mental Model of the agent by the user (Luger and Sellen 2016).”
InfluentialAbbas, A., Wohn, C., Jagtap, A., Rho, E. H. R., Kim, Y.-H., & Lee, S. W. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3790957 · Cited by 9
“Because conversations leverage social intelligence, understanding users’ planning and reflection behaviors requires examining how they interpret the agent as a social entity.”
AI ‐Powered Chatbot as a Health Literacy Tool for Enhancing Oral Cancer Awareness: Expert Feedback
Abosamak, N. E., Namoos, A. M., Ramadan, R., Olex, A. L., & Gal, T. S. (2026) · Clinical and Translational Science · doi:10.1111/cts.70499 · Cited by 4
Human–AI relationships as designed relationality: a sociotechnical model
Carpenter, J. (2026) · AI & Society · doi:10.1007/s00146-026-02908-y · Cited by 5
“The first encounter with a socially responsive AI system often triggers fascination, play/amusement, or disorientation (DeGraf et al. 2015; Luger and Sellen 2016).”
Kuang, E., Soure, E. J., Shen, L., Goyal, N., Fan, M., & Shinohara, K. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3790536 · Cited by 5
Examining the Effect of Narrative Features and Thematic Music in an Audio-Based Exergame
Oh, S.-J., Kim, J. L., & Gweon, G. (2023) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2023.2255412 · Cited by 4
“Audio-only exergames have the advantage of providing an eyes-free and hands-free environment (Cowan et al., 2017; Luger & Sellen, 2016), allowing users to engage in various types of exercises that require full use of eyes or hands.”
Saari, M., Rantanen, P., Nurminen, M., Kilamo, T., Systä, K., & Abrahamsson, P. (2024) · Springer eBooks · doi:10.1007/978-3-031-55642-5_16 · Cited by 6
Unveiling Information Through Narrative In Conversational Information Seeking
Javadi, V. S., Trippas, J. R., & Flek, L. (2024) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3640794.3665884 · Cited by 8
Understanding Linguistic and Visual Factors that Affect Human Trust Perception of Virtual Agents
Tyulina, N., Emmanouil, T. A., & Levitan, S. I. (2024) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3640794.3665581 · Cited by 6
“As these agents aim to simulate human-like conversation, a crucial factor that profoundly influences user engagement and satisfaction is trust [6, 7].”
BackgroundWang, M., & Wang, M. (2025) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2025.103473 · Cited by 4
Implementation of Voice Search Technology in Digital Library Systems
Sallaah, M. H., Kumar, S., Manimekalai, M. A. P., Khamitdkhanovich, N. A., Thiyagu, T. M., & Udayakumar, R. (2025) · Indian Journal of Information Sources and Services · doi:10.51983/ijiss-2025.ijiss.15.2.15 · Cited by 4
Jacka, R., Peña, P. R., Leonard, S. J., Székely, É., & Cowan, B. R. (2025) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3719160.3737625 · Cited by 5
“A mismatch in expectations can negatively affect perceptions of virtual agents [24, 43], with context and task proposed as playing a key role in setting such expectations [34], which may explain the fluent condition post-interaction.”
Mirbabaie, M., Marx, J., Möllmann, N., & Matt, S. (2025) · ACM SIGMIS Database the DATABASE for Advances in Information Systems · doi:10.1145/3757308.3757312 · Cited by 5
“DA are becoming increasingly important in research and practice due to the ongoing attention to the progress of AI (Gnewuch et al., 2017) and improvements in underlying machine learning algorithms (Luger & Sellen, 2016).”
Hornbæk, K., Kristensson, P. O., & Oulasvirta, A. (2025) · Oxford University Press eBooks · doi:10.1093/oso/9780192864543.003.0017 · Cited by 4
Say It with Emojis: Co-Designing Relevance Cues for Searching in the Classroom
Aliannejadi, M., Landoni, M., Huibers, T. W. C., Murgia, E., Pera, M. S., Cantador, I., Chevalier, M., Melucci, M., & Mothe, J. (2020) · UvA-DARE (University of Amsterdam) · Cited by 4
Towards a Systematic Approach for Chatbot Development in Digital Work Environments
Börsting, I., & Hesenius, M. (2021) · Lecture notes in logistics · doi:10.1007/978-3-030-58430-6_5 · Cited by 5
Expectation vs Reality in Users’ Willingness to Delegate to Digital Assistants
Svikhnushina, E., Schellenberg, M., Niedbala, A. K., Barišic, I., & Miles, J. N. V. (2023) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3544549.3585763 · Cited by 7
“This implies that the tasks users entrust to DAs are not the most useful, which aligns with previous studies [32, 45].”
BackgroundResultBourass, H., & Noufail, O. S. (2023) · International Conference on Optimization and Applications (ICOA) · doi:10.1109/icoa58279.2023.10376326 · Cited by 4
“[17] • AI is the study of methods that allow computers to do what humans do best.”
BackgroundDevising Scrutable User Models for Time Management Assistants
Jeromela, J., & Conlan, O. (2024) · ACM Conference on User Modeling, Adaptation and Personalization (UMAP) · doi:10.1145/3631700.3665182 · Cited by 4
Artificial Intelligence: Society’s New Black Box?
Nelu, C. E. (2024) · Development · doi:10.1057/s41301-024-00417-3 · Cited by 4
“Luger and Sellen (2016) explained that AI helps people execute simple and complex tasks, from switching on lights in the house by just using your voice to having a car that drives itself.”
Wen, Q., Kochhar, P., Zeyada, S., Javaheri, T., & Rawassizadeh, R. (2025) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2025.2561760 · Cited by 5
“Also, multi-agent platforms enhance user engagement and input quality (Jiang et al., 2023), along with efficiency, by reducing context switching and cognitive load (Luger & Sellen, 2016).”
Artworks’ Features Discovery Through Engaging Conversations for Children
Jaramillo, J. C., Occhiuto, D., & Garzotto, F. (2018) · IOP Conference Series Materials Science and Engineering · doi:10.1088/1757-899x/364/1/012097 · Cited by 4
“When designing conversational interfaces, there are several requirements to keep in mind [18].”
BackgroundTowards a Pattern Language for Smart Personal Assistants
Knote, R., Söllner, M., & Leimeister, J. M. (2018) · Alexandria (UniSG) (University of St.Gallen) · Cited by 4
A Fuzzy Reasoning Process for Conversational Agents in Cognitive Cities
D’Onofrio, S., Müller, S. M., & Portmann, E. (2019) · Lecture notes in business information processing · doi:10.1007/978-3-030-26169-6_6 · Cited by 4
An Honest Conversation: Transparently Combining Machine and Human Speech Assistance in Public Spaces
Reitmaier, T., Robinson, S., Pearson, J. S., Raju, D. K., & Jones, M. (2020) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3313831.3376310 · Cited by 5
VISH: Does Your Smart Home Dialogue System Also Need Training Data?
Noura, M., Heil, S., & Gaedke, M. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-50578-3_13 · Cited by 4
Proactivity: The Next Step in Voice Assistants for the TV Ecosystem
Abreu, J., Santos, R., Silva, T., Marques, T., & Cardoso, B. (2020) · Communications in computer and information science · doi:10.1007/978-3-030-56574-9_7 · Cited by 5
Remote Work Aided by Conversational Agents
Qiu, S., Gadiraju, U., Bozzon, A., Mark, G. J., & Rintel, S. (2020) · Research Repository (Delft University of Technology) · Cited by 4
Sanni, S. A., & Rajabu, N. (2020) · Journal of Applied Science Information and Computing · doi:10.59568/jasic-2020-1-2-01 · Cited by 4
“The application can communicate with humans in their natural language and answer questions, perform required tasks, or provide information (Luger & Sellen 2016; Radziwill & Benton 2017).”
BackgroundThe Language of Human-Machine Communication
Bylieva, D. S. (2020) · PhilPapers (PhilPapers Foundation) · doi:10.48417/technolang.2020.01.04 · Cited by 5
“A woman describes her interaction with a virtual assistant in the following way: “There was one time I was very [sarcastic] to it, I was like ‘oh thanks that’s really helpful’ and it just said, I swear, in an equally sarcastic tone ‘that’s fine it’s my pleasure’” (Luger & Sellen, 2016).”
BackgroundVoice Assistants as Learning Companions: An Initial Exploration With Computer Science Students
Sayago, S. (2020) · International Conference on Human-Computer Interaction with Mobile Devices and Services (MobileHCI) · doi:10.1145/3406324.3410707 · Cited by 4
“This expanding research is due in part to the increasing popularity of VA [8] and interest in Conversational User Interfaces in the HCI community [2], and the fact that we know little about how people use VA [7].”
BackgroundPark, C., Lim, Y., Choi, J., & Sung, J. E. (2021) · Intelligent Service Robotics · doi:10.1007/s11370-021-00374-7 · Cited by 4
Phukon, M., Shrivastava, A., & Balentine, B. (2022) · Indian Conference on Human-Computer Interaction (IndiaHCI) · doi:10.1145/3570211.3570215 · Cited by 5
An Instrument for measuring users’ meta-intents
Ma, Y., Donkers, T., Kleemann, T., & Ziegler, J. (2023) · Conference on Human Information Interaction and Retrieval · doi:10.1145/3576840.3578317 · Cited by 4
Chen, P., Tielman, M. L., Heylen, D., Jonker, C. M., & van Riemsdijk, M. B. (2023) · Frontiers in artificial intelligence and applications · doi:10.3233/faia230077 · Cited by 4
“This coincides with [48]’s findings on the dissonance between user expectations and their assessment of the intelligence of the conversational agents.”
Background‘Hey Siri, You’re Dumb!’: Investigating Blurting Instances of Voice-Based Assistants
Rijhwani, V., & Edwards, C. (2023) · Interacting with Computers · doi:10.1093/iwc/iwad047 · Cited by 4
"Let's Face It": Investigating User Preferences for Virtual Humanoid Home Assistants
Zargham, N., Alexandrovsky, D., Mildner, T., Porzel, R., & Malaka, R. (2023) · International Conference on Human-Agent Interaction (HAI) · doi:10.1145/3623809.3623821 · Cited by 6
“Despite the technological advancements and the benefits that such systems provide, it is still highly challenging to design a satisfying experience with VAs, as many users still find interaction with such systems unsatisfactory, disappointing, or embar-rassing [11, 18, 56, 72, 96].”
BackgroundJeromela, J., & Conlan, O. (2023) · International Conference on Human-Agent Interaction (HAI) · doi:10.1145/3623809.3623851 · Cited by 4
Evaluating a voice-based interaction: a qualitative analysis
Guerino, G. C., & Valentim, N. (2019) · Brazilian Symposium on Human Factors in Computing Systems (IHC) · doi:10.1145/3357155.3360472 · Cited by 4
“Some studies perform a detailed qualitative analysis, such as Luger and Sellen [10], which performs the analysis of conversational agents with the Thematic Network Analysis (TNA) approach [2].”
MethodThe Effect of Personal Pronouns on Users’ Emotional Experience in Voice Interaction
Qu, J., Zhou, R., Zou, L., Sun, Y., & Zhao, M. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-49062-1_16 · Cited by 5
Consumers’ Acceptance of a Voice Commerce Application in FMCG in Germany, U.S. and U.K.
Adolphs, E., & Zaharia, S. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-77750-0_1 · Cited by 7
Tell Me About Yourself: Using an AI-Powered Chatbot to Conduct Conversational Surveys.Preprint
Xiao, Z., Zhou, M. X., Liao, Q. V., Mark, G. J., Yan, C., Chen, W., & Yang, H. (2019) · arXiv (Cornell University) · Cited by 4
Evaluating Voice Skills by Design Guidelines Using an Automatic Voice CrawlerPreprint
Han, X., & YEH, T. P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.01122 · Cited by 5
“In [22], researchers interviewed 14 users of VAs in an effort to understand the factors affecting everyday use.”
BackgroundImpact of Conversational Agents on Customer Service Employees
Ugale, A. (2020) · Tuwhera (Auckland University of Technology) · Cited by 5
A Game-Based Approach for Helping Designers Learn Machine Learning ConceptsPreprint
Myers, C. M., Xie, J., & Zhu, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.05605 · Cited by 4
“We also see similar behavior with users of intelligent agents [32].”
ResultRodrigues, T. C., Reijnders, T., de Buisonjé, D. R., Santhanam, P., Kowatsch, T., Breeman, L. D., Janssen, V. R., Kraaijenhagen, R. A., Atsma, D. E., & Evers, A. W. M. (2021) · doi:10.2196/preprints.30057 · Cited by 4
Exploring Human Trust in Ai: The Influence of Ingroup/Outgroup Context and Ai Human-LikenessPreprint
Yu, S., Xu, C., Liang, X., He, X., Sun, Y., & Xu, H. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4406767 · Cited by 5
Speaker anonymization : representation, evaluation and formal guarantees
Srivastava, B. M. L. (2021) · theses.fr (ABES) · doi:10.70675/5dfccefaz18d3z4687z8a62za1359a91858b · Cited by 6
Meck, A.-M., Draxler, C., & Vogt, T. (2024) · International Journal of Human–Computer Interaction · doi:10.1080/10447318.2023.2266791 · Cited by 3
“As a consequence, user trust and satisfaction with CUIs can decrease and ultimately lead to product abandonment (Lee et al., 2010; Luger & Sellen, 2016; Skantze, 2007).”
InfluentialHornbæk, K., Kristensson, P. O., & Oulasvirta, A. (2025) · Oxford University Press eBooks · doi:10.1093/oso/9780192864543.003.0028 · Cited by 3
As if conscious: the instrumentality theorem in artificial intelligence
Freund, L. (2025) · AI and Ethics · doi:10.1007/s43681-025-00832-3 · Cited by 4
“A conversational agent that simulates empathy too convincingly may invite attachment that exceeds the system’s intended role [82, 44].”
Should robots display what they hear? Mishearing as a practical accomplishment
Rudaz, D., & Licoppe, C. (2025) · Frontiers in Robotics and AI · doi:10.3389/frobt.2025.1597276 · Cited by 3
Çakmak, F. (2025) · Behaviour and Information Technology · doi:10.1080/0144929x.2025.2587731 · Cited by 3
“Some studies have investigated the efficacy of chatbots employing social cues and quantified the experience as either disappointing (Luger and Sellen 2016) or completely satisfactory, some reported them to be motivating for social good (Song et al. 2025), and sensitive (Hu et al. 2018), depending…”
Kim, J.-Y., & Jo, H. (2025) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2025.2584727 · Cited by 4
“This construct is grounded in HCI literature, where responsiveness has been shown to reduce user frustration and foster trust in conversational agents (Chen et al., 2021; Følstad et al., 2018; Luger & Sellen, 2016; Truong & Chen, 2025).”
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.