On Being Told How We Feel: How Algorithmic Sensor Feedback Influences Emotion Perception
The DOI matches its Crossref record; 70 of the 73 references it cites were found in a registry or an index.
Abstract
Algorithms and sensors are increasingly deployed for highly personal aspects of our everyday lives. Recent work suggests people have imperfect understanding of system outputs, often assuming sophisticated capabilities and deferring to feedback. We explore how people construe algorithmic interpretations of emotional data in personal informatics systems. A survey (n=188) showed strong interest in automatic stress and emotion tracking, but many respondents expected these systems to provide objective measurements for their emotional experiences. A second study examined how algorithmic sensor feedback influences emotional self-judgments, by comparing three system framings of physiological ElectroDermal Activity data (EDA): Positive ("alert and engaged"), Negative ("stressed"), and Control (no frame) in a mixed-methods study with 64 participants. Despite users reporting strategies to test system outputs, users still deferred to feedback and their perceived emotions were significantly influenced by feedback frames. Some users overrode personal judgments, believing the system had access to privileged information about their emotions. Based on these findings, we explore design implications for personal informatics including risks of users trusting systems that seemingly "unlock" hidden aspects of the self. We propose design approaches that provide opportunities for future emotion-monitoring systems to exploit these framing effects, and for users to more actively construe emotional states.
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
“Emotional analytics is perceived as a key application by many users [16,17,18,39,90].”
From Progressive Disclosure: When, Why, and How Do Users Want Algorithmic Transparency Information? (2020) · cites this paper as [39]
In the citing paper
“Other work has shown that users will modify high stakes personal health behaviors based on false inferences about an algorithm's high accuracy [39,70].”
From Progressive Disclosure: When, Why, and How Do Users Want Algorithmic Transparency Information? (2020) · cites this paper as [39]
In the citing paper
“Emotional analytics is perceived as a key application by many users [38].”
From Progressive disclosure (2019) · cites this paper as [38]
Citations
Cites
Development and validation of brief measures of positive and negative affect: The PANAS scales.
Watson, D., Clark, L. A., & Tellegen, A. (1988) · Journal of Personality and Social Psychology · doi:10.1037/0022-3514.54.6.1063 · Cited by 32,433
A General Inductive Approach for Analyzing Qualitative Evaluation Data
Thomas, D. R. (2006) · American Journal of Evaluation · doi:10.1177/1098214005283748 · Cited by 10,858
An argument for basic emotions
Ekman, P. (1992) · Cognition and Emotion · doi:10.1080/02699939208411068 · Cited by 9,646 · cited 1×
“Classical theories of emotions argue for a set of basic, discrete emotional states (‘fear’, ‘anger’, ‘surprise’, ‘happiness’, ‘disgust’, ‘sadness’) that can be detected through physiological fingerprints such as heart rate, electrodermal activity (EDA), facial expression and so forth [19, 34].”
Background(1999) · Cited by 5,934
State-Trait Anxiety Inventory for Adults
Spielberger, C. D. (2012) · PsycTESTS Dataset · doi:10.1037/t06496-000 · Cited by 3,479 · cited 1×
“State-Trait Anxiety Inventory (STAI) Survey: The STAI for Adults short-form [69] is a 20-item scale to assess mental and physical symptoms of anxiety.”
(2007) · Cited by 3,233
Fredrickson, B. L., Tugade, M. M., Waugh, C. E., & Larkin, G. R. (2003) · Journal of Personality and Social Psychology · doi:10.1037/0022-3514.84.2.365 · Cited by 2,797
Boucsein, W. (2012) · doi:10.1007/978-1-4614-1126-0 · Cited by 2,526
(2017) · Cited by 2,433
Appraisal Processes in Emotion: Theory, Methods, Research
(2001) · doi:10.1093/oso/9780195130072.001.0001 · Cited by 2,384
Research works printed but not linked: 3
- Pennebaker James W, 2001, Linguistic inquiry and word count: LIWC 2001. Mahway, Lawrence Erlbaum Associates, 71, 2001
- Rosch Paul J, 2001, The quandary of job stress compensation, Health and Stress, 3, 1
- 10.1037/1089-2680.5.3.241 · doi:10.1037/1089-2680.5.3.241 · Paper page
Cited by
Human trust in artificial intelligence: Review of empirical research
Glikson, E., & Woolley, A. W. (2020) · Academy of Management Annals · doi:10.5465/annals.2018.0057 · Cited by 2,921
Haque, M. D. R., & Rubya, S. (2023) · JMIR mHealth and uHealth · doi:10.2196/44838 · Cited by 404
Mapping and Taking Stock of the Personal Informatics Literature
Epstein, D. A., Caldeira, C., Figueiredo, M. C., Lu, X., Silva, L. M., Williams, L., Lee, J. H., Li, Q., Ahuja, S., Chen, Q., et al. (2020) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3432231 · Cited by 218
“and appraisal theory [252] to make sense of how algorithmic framing in an interface might influence a person’s reaction to seeing emotion data [113].”
BackgroundDesigning for Emotion Regulation Interventions: An Agenda for HCI Theory and Research
Slovak, P., Antle, A., Theofanopoulou, N., Daudén Roquet, C., Gross, J., & Isbister, K. (2023) · ACM Transactions on Computer-Human Interaction · doi:10.1145/3569898 · Cited by 142
The Placebo Effect of Artificial Intelligence in Human–Computer Interaction
Kosch, T., Welsch, R., Chuang, L., & Schmidt, A. (2022) · ACM Transactions on Computer-Human Interaction · doi:10.1145/3529225 · Cited by 137
Ho, T. M., Mantello, P. A., Ghotbi, N., Nguyen, M., Nguyen, H. T., & Vuong, Q. (2022) · Technology in Society · doi:10.1016/j.techsoc.2022.102011 · Cited by 154
Kim, H., Kim, Y., Mahmood, M., Kwon, S., Zavanelli, N., Kim, H. S., Rim, Y. S., Epps, F., & Yeo, W. (2020) · Advanced Science · doi:10.1002/advs.202000810 · Cited by 120
Springer, A., & Whittaker, S. (2019) · Proceedings of the 24th International Conference on Intelligent User Interfaces · doi:10.1145/3301275.3302322 · Cited by 115
“Other work has shown that emotional analytics is evaluated by users as one of the key applications of PI technology [38].”
BackgroundResultInfluentialSelf-citationCosta, J. M. D. R., Guimbretière, F. V., Jung, M. F., & Choudhury, T. (2019) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3328911 · Cited by 141
“Similarly, previous studies have shown that individuals’ beliefs about the feedback presented by emotion tracking technologies can affect their own emotional self-judgments [19][42].”
BackgroundResultProgressive Disclosure: When, Why, and How Do Users Want Algorithmic Transparency Information?
Springer, A., & Whittaker, S. (2020) · ACM Transactions on Interactive Intelligent Systems · doi:10.1145/3374218 · Cited by 84
“Instead our aim was to have users directly experience the algorithm, evaluating it in situ, as it made decisions about their own personally generated data [38, 39].”
BackgroundResultInfluentialSelf-citationZhang, R., Ringland, K. E., Paan, M., Mohr, D. C., & Reddy, M. C. (2021) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445771 · Cited by 92
Kim, T., Shin, D., Kim, Y.-H., & Hong, H. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642693 · Cited by 75
“Because it is difcult to determine an individual’s mental/psychological state, people often tend to trust the output of the algorithm rather than their judgment [23].”
InfluentialSignificant Otter: Understanding the Role of Biosignals in Communication
Liu, F., Park, C., Tham, Y. J., Tsai, T.-Y., Dabbish, L., Kaufman, G. F., & Monroy‐Hernández, A. (2021) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445200 · Cited by 78
“This aligns with prior work by Hollis and colleagues [19], which suggests that people may overly trust emotion sensing systems and be infuenced by the system’s interpretations of their emotions.”
BackgroundWearables measuring electrodermal activity to assess perceived stress in care: a scoping review
Klimek, A., Mannheim, I., Schouten, G., Wouters, E., & Peeters, M. W. H. (2023) · Acta Neuropsychiatrica · doi:10.1017/neu.2023.19 · Cited by 89
“…2.7% (Seoane et al ., 2014; Lee et al ., 2020b) used a glove with integrated sensors, 24.3% articles described devices with electrodes placed on the fingers, often with Velcro, for example, the Shimmer3 sensor, Biopac systems and the E243 inVivo metric systems corp. Marko (2016), Hollis et al .”
InfluentialPrediction of stress and drug craving ninety minutes in the future with passively collected GPS data
Epstein, D. H., Tyburski, M., Kowalczyk, W. J., Burgess-Hull, A. J., Phillips, K. A., Curtis, B. L., & Preston, K. L. (2020) · npj Digital Medicine · doi:10.1038/s41746-020-0234-6 · Cited by 74
Data Sensemaking in Self-Tracking: Towards a New Generation of Self-Tracking Tools
Coşkun, A., & Karahanoğlu, A. (2022) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2022.2075637 · Cited by 64
“For instance, they may misinterpret their data (Hollis et al., 2018) as different data types can present conflicting results based on the contexts and use cases (Victorelli et al., 2020).”
BackgroundInfluentialKim, T., Kim, H., Lee, H. Y., Goh, H., Abdigapporov, S., Jeong, M., Cho, H., Han, K., Noh, Y., Lee, S.-J., et al. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3517701 · Cited by 62
“, stress [1], mood [13, 54], and emotion [29]).”
BackgroundMethodInfluentialMood and personal information management: how we feel influences how we organize our information
Whittaker, S., & Massey, C. (2020) · Personal and Ubiquitous Computing · doi:10.1007/s00779-020-01412-4 · Cited by 34
Self-citationScaffolding the Online Peer-support Experience: Novice Supporters' Strategies and Challenges
Chen, T., Zhang, K., Kraut, R. E., & Dabbish, L. (2021) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3479510 · Cited by 24
A Meta-Synthesis of the Barriers and Facilitators for Personal Informatics Systems
Kabir, K. S., & Wiese, J. (2023) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3610893 · Cited by 17
Eagle, T., Mehrotra, A., Sharma, A., Zuniga, A., & Whittaker, S. (2022) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3555155 · Cited by 28
“New diagnostic methods include automatic identification of MH symptoms from personal data, such as phone records [15,38,117], GSR [58], EEG [109,118] and facial expressions [140].”
MethodSelf-citationChatbots as Advisers: the Effects of Response Variability and Reply Suggestion Buttons
Milana, F., Costanza, E., & Fischer, J. E. (2023) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3571884.3597132 · Cited by 20
“This observation extends recent work that has drawn attention to similar types of cognitive bias in text recognition systems and biosignal sensors [20, 25].”
BackgroundFigueiredo, M. C., Ankrah, E. A., Powell, J. E., Epstein, D. A., & Chen, Y. (2023) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3631414 · Cited by 27
“Hollis et al. [39] reported that users might defer to an algorithm’s classification of their emotional experience over their personal judgment of that experience.”
BackgroundMendel, T., Nov, O., & Wiesenfeld, B. M. (2024) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3686925 · Cited by 23
“Hollis et al. found that users demonstrated high initial cognitive trust in algorithmic sensor feedback, as evidenced by being influenced by the AI feedback [55].”
Micro-narratives: A Scalable Method for Eliciting Stories of People’s Lived Experience
Skeggs, A., Mehta, A., Yap, V., Ibrahim, S. B., Rhodes, C., Gross, J. J., Munson, S. A., Klasnja, P., Orben, A., & Slovak, P. (2025) · Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713999 · Cited by 14
Progressive Disclosure: Designing for Effective TransparencyPreprint
Springer, A., & Whittaker, S. (2018) · arXiv.org · doi:10.48550/arxiv.1811.02164 · Cited by 24
“Users are prone to blindly believing outputs from algorithmic systems, a phenomena referred to as algorithmic omniscience [23,36,74] and automation bias [17,56].”
BackgroundResultSelf-citationHuman-AI interaction: Augmenting decision-making for IT leader's project selection
Judkins, J. T., Hwang, Y., & Kim, S. (2024) · Information Development · doi:10.1177/02666669241249744 · Cited by 14
“Scholars have proposed that transparency of IT systems is a key mitigator of user overtrust, that is trusting AI more than it should be based on its overall capabilities (Hollis et al., 2018; Wagner et al., 2018).”
Multitudes: Widening the research agenda for personal informatics design
Winter, E., Knowles, B., Richards, D., Snooks, K., & Speed, C. (2022) · Proceedings of DRS · doi:10.21606/drs.2022.415 · Cited by 10
Fronczek, L. P., Mende, M., & Scott, M. L. (2022) · Journal of Consumer Affairs · doi:10.1111/joca.12478 · Cited by 16
van den Berg, M. K. N., Karahanoğlu, A., Noordzij, M. L., Maeckelberghe, E. L. M., & Ludden, G. (2025) · Interacting with Computers · doi:10.1093/iwc/iwaf036 · Cited by 10
An (E)Affective Bind: Situated Affectivity and the Prospect of Affect Recognition
Branford, J. (2023) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2023.3281069 · Cited by 8
“Indeed, there is already evidence of people favouring algorithmic assessments of their affective state over their own subjective experiences; believing AC to have access to additional/superior information (cf. [38], [39]).”
BackgroundDesigning for Data Sensemaking Practices: A Complex Challenge
Karahanoğlu, A., & Coşkun, A. (2024) · interactions · doi:10.1145/3664630 · Cited by 7
“It is not uncommon to see an influx of individuals tracking their health who get confused about what specific values indicate, especially when the values are not easy to understand, as was previously reported in several HCI studies [2,3,4].”
ResultZhang, T., & Tong, Q. (2025) · Information Technology and People · doi:10.1108/itp-10-2023-1082 · Cited by 12
Chandrasekaran, A., Bielicke, L., Shah, D., Janakiraman, H., & Mauriello, M. L. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713269 · Cited by 11
Are you stressed or just excited? What the Garmin Stress Score can say about your mood
van der Mee, D. J., Koyuncu, Z., & Lemmers-Jansen, I. L. J. (2025) · Journal of Affective Disorders Reports · doi:10.1016/j.jadr.2025.100974 · Cited by 9
"I had a solid theory before but it's falling apart": Polarizing Effects of Algorithmic TransparencyPreprint
Springer, A., & Whittaker, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.02163 · Cited by 16
“Similar results were shown in [32], showing that participants expected intelligent personal informatics systems to serve as ground truth for their experiences and even”
BackgroundResultSelf-citationEvaluating Just-In-Time Vibrotactile Feedback for Communication Anxiety
Raether, J., Nirjhar, E. H., & Chaspari, T. (2022) · INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION · doi:10.1145/3536221.3556590 · Cited by 5
“EDA measures the variation of the electrical conductance of the skin in response to sweat secretion and is frequently used as an indicator of sympathetic arousal [38, 40, 45, 52, 70].”
BackgroundPlanning the Future in a Longer Perspective: Effects of a One-week Forecast of Mental Health
Tateyama, N., Yokomura, R., Ban, Y., Warisawa, S., & Fukui, R. (2024) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3643538 · Cited by 5
“Previous studies have investigated how humans accept predictions of internal states by PI systems [20].”
BackgroundBogdanova, K., Cila, N., Kudina, O., & Bozzon, A. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3714399 · Cited by 4
“Consequently, users are quick to abandon PHT, when “epistemolog-ical tensions” arise, e.g. if data contradicts their self-perception and are ill-fitting to the narratives and existing sociocultural models of health [82, 175].”
Toward Pluralizing Reflection in HCI through Daoism
Zhu, A. P., Mah, K., & Cho, J. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3790853 · Cited by 6
Krämer, S., Kottwitz, G. R., Woźniak, M. P., Meyer, J., & Koelle, M. (2024) · Nordic Conference on Human-Computer Interaction · doi:10.1145/3679318.3685372 · Cited by 5
The Voice of Endo: Leveraging Speech for an Intelligent System That Can Forecast Illness Flare-ups
Pichon, A., Blumberg, J. R., Mamykina, L., & Elhadad, N. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3714040 · Cited by 4
“Hollis et al. documented that people are willing to trust an intelligent system with intimate aspects of their personal self and associated risks with taking system outputs at objective face-value [49].”
Social Distancing and Social Biosensing: Intersubjectivity from Afar
Curran, M. T., & Chuang, J. C.-I. (2022) · Computer Supported Cooperative Work (CSCW) · doi:10.1007/s10606-022-09428-5 · Cited by 4
“…a tendency and at times even a desire people have to see biosensory information as objective, and the degree to which this influences perceived emotional states of oneself and others even when cautioned against the accuracy of this data for this purpose (Hollis et al., 2018; Howell et al., 2018).”
BackgroundWang, G., Singh, V. K., & Zhang, D. (2025) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3710921 · Cited by 6
Gooding, P. (2024) · Springer eBooks · doi:10.1007/978-981-19-6056-7_87 · Cited by 3
WSCoach: Wearable Real-time Auditory Feedback for Reducing Unwanted Words in Daily Communication
Zhang, Y., Janaka, N. N. P. K., Ram, A., Yin, P., Tian, Y., Zhao, S., & Dragicevic, P. (2025) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3749531 · Cited by 4
“[33] or gesture cues—may enhance both user experience and system effectiveness.”
Koh, Y., Kim, J., Lee, K., Jung, Y., Hong, H., & Lee, U. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791194 · Cited by 1
Seamful Design Considerations for Human-in-the-Loop Digital Phenotyping of Mental Health
Swain, V. D., Tongtawee, T., Wang, O., Hsu, J., Jacobson, N. C., & Mishra, V. (2026) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3832021 · Cited by 2
“Acting alone, users can undermine their self-judgment and accept insights from a DPMH tool [38], which could lead to a distorted sense of self [36].”
Gooding, P. (2023) · Springer eBooks · doi:10.1007/978-981-16-1278-7_87-1 · Cited by 1
Ho, T. M., Nguyen, M., Nguyen, H. T., & Vuong, Q. (2022) · OSF Preprints (OSF Preprints) · doi:10.31219/osf.io/df8zt · Cited by 1
Penney, J. W. (2025) · Cambridge University Press eBooks · doi:10.1017/9781108641784.017
Dritsa, D., & Houben, S. (2025) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2025.2597506 · Cited by 6
“Hollis et al. (2018) showed users two different framings of the same EDA data: one negative, indicating stress, and one positive, indicating engagement.”
Influential
Metadata
- Authors
- Hollis, V., Pekurovsky, A., Wu, E., & Whittaker, S.
- Affiliations
- University of California, Santa Cruz (US)
- Venue
- Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
- Published
- 2018-09-18
- Volume
- 2
- Issue
- 3
- Pages
- 1-31
- ISSN
- 2474-9567 (ISSN-L)
- OpenAlex
- W2889612522
- Cited by
- 52
- References
- 73
- Citations by year
- 2026: 3 · 2025: 11 · 2024: 7 · 2023: 7 · 2022: 11 · 2021: 3 · 2020: 6 · 2019: 2 · 2018: 2
- FWCI
- 3.24
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Human-Computer Interaction › Innovative Human-Technology Interaction
- Physical Sciences › Computer Science › Artificial Intelligence › Emotion and Mood Recognition
- Social Sciences › Psychology › Social Psychology › Social Robot Interaction and HRI
- Keywords
- emotion monitoring, stress monitoring, personal informatics, algorithmic feedback, electrodermal activity, physiological sensors, framing effects, system trust
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.