Can Alexa be your Therapist?: How Back-Channeling Transforms Smart-Speakers to be Active Listeners
The DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Abstract
Smart-speakers such as Amazon Alexa are becoming increasingly popular among the general population. These devices support a wide range of user-initiated tasks. However, their current interaction capabilities are limited to quick turn-takings and short dialogues, which leads to limited user engagement. In this project, we aim to enhance the user engagement and interaction abilities of a smart-speaker by transforming it into an active listener. Specifically, we explored how providing random back-channelling (i.e., verbal continuers including "hm", "uhum", "aha", "yeah") can result in longer interactions and more sustained user engagement. The findings of the study have implications for usability and future design of smart-speakers. We also explored how the enhanced interactions in smart-speakers through back-channeling can be used for self-centered therapy leading to betTer emotional and social support.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Emotional and physical health benefits of expressive writing
Baikie, K. A., & Wilhelm, K. (2005) · Advances in Psychiatric Treatment · doi:10.1192/apt.11.5.338 · Cited by 517 · cited 1×
“Expressive writing has been effective in emotion control and improving wellbeing in clinical populations with different symptoms including PTSD [3], anxiety [5], depression [7], and mood disorder [1].”
BackgroundFrancis, M. E., & Pennebaker, J. W. (1992) · American Journal of Health Promotion · doi:10.4278/0890-1171-6.4.280 · Cited by 300 · cited 2×
“Pennebaker et al. [5] introduced expressive writing in which participants disclosed information about traumatic events or emotional upheavals in written forms.”
BackgroundGearhart, C. C., & Bodie, G. D. (2011) · Communication Reports · doi:10.1080/08934215.2011.610731 · Cited by 118 · cited 1×
“The study used the following surveys and open-ended questionnaires: • Measures of usability and interaction quality by using a 7-point Likert Scale following Gearhart et al. [6] and Lala et al [8].”
MethodKrpan, K. M., Kross, E., Berman, M. G., Deldin, P. J., Askren, M. K., & Jonides, J. (2013) · Journal of Affective Disorders · doi:10.1016/j.jad.2013.05.065 · Cited by 94 · cited 1×
“Expressive writing has been effective in emotion control and improving wellbeing in clinical populations with different symptoms including PTSD [3], anxiety [5], depression [7], and mood disorder [1].”
BackgroundAttentive listening system with backchanneling, response generation and flexible turn-taking
Lala, D., Milhorat, P., Inoue, K., Ishida, M., Takanashi, K., & Kawahara, T. (2017) · Annual Meeting of the Special Interest Group on Discourse and Dialogue · doi:10.18653/v1/w17-5516 · Cited by 93 · cited 1×
“The study used the following surveys and open-ended questionnaires: • Measures of usability and interaction quality by using a 7-point Likert Scale following Gearhart et al. [6] and Lala et al [8].”
MethodBugg, A., Turpin, G., Mason, S. M., & Scholes, C. (2008) · Behaviour Research and Therapy · doi:10.1016/j.brat.2008.10.006 · Cited by 60 · cited 1×
“Expressive writing has been effective in emotion control and improving wellbeing in clinical populations with different symptoms including PTSD [3], anxiety [5], depression [7], and mood disorder [1].”
BackgroundOn active listening in person-centred, solution-focused psychotherapy
Fitzgerald, P. E., & Leudar, I. (2010) · Journal of Pragmatics · doi:10.1016/j.pragma.2010.07.007 · Cited by 60 · cited 1×
“One of our key goals is to transform these devices into “active listener" [4] — devices that can help users to engage in troubles talk and disclosure.”
BackgroundOertel, C., Lopes, J., Yu, Y., Mora, K. A. F., Gustafson, J., Black, A. W., & Odobez, J.-M. (2016) · Proceedings of the 18th ACM International Conference on Multimodal Interaction · doi:10.1145/2993148.2993188 · Cited by 21 · cited 2×
“Verbal continuers (e.g., “hm", “uhum", “aha", “yeah") can enhance perceived human-likeness of conversational agents [10, 11].”
BackgroundMethodAutomated computer-based feedback in expressive writing
Bond, M. P., & Pennebaker, J. W. (2012) · Computers in Human Behavior · doi:10.1016/j.chb.2012.01.003 · Cited by 20 · cited 1×
“It has been shown to have positive health effects for non-clinical populations as well [2].”
BackgroundOertel, C., Gustafson, J., & Black, A. W. (2016) · Interspeech (USB) · doi:10.21437/interspeech.2016-1274 · Cited by 4 · cited 2×
“Verbal continuers (e.g., “hm", “uhum", “aha", “yeah") can enhance perceived human-likeness of conversational agents [10, 11].”
BackgroundMethod
Research works printed but not linked: 1
- NPR and Edison Research. 2019. The Smart Audio Report (Spring 2019). Available at https://www.nationalpublicmedia.com/wp-content/uploads/2019/06/The_Smart_Audio_Report_Spring_2019.pdf.
Cited by
Festerling, J., & Siraj, I. (2022) · Integrative Psychological and Behavioral Science · doi:10.1007/s12124-021-09668-y · Cited by 64
“…et al., 2020; Wang, 2017; Waytz et al., 2014a)), and especially in the context of DVAs (e.g., (Voit et al., 2020; Gao et al., 2018; Lee et al., 2020; Lopatovska & Williams, 2018; Pradhan et al., 2019; Biele et al., 2019; Motalebi et al., 2019; Purington et al., 2017; Wagner & Schramm-Klein, 2019)).”
BackgroundMetaphors in Voice User Interfaces: A Slippery Fish
Desai, S., & Twidale, M. (2023) · ACM Transactions on Computer-Human Interaction · doi:10.1145/3609326 · Cited by 42
“In exploring VUI use in the context of learning and healthcare, designers and researchers also used the “coach/teacher/tutor” [ 78 , 156 , 160 ] and “therapist” [ 112 ] comparisons.”
MethodCho, E., Motalebi, N., Sundar, S. S., & Abdullah, S. (2022) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3555164 · Cited by 50
“These pause durations were selected based on pilot data [53] to minimize user interruptions.”
MethodSelf-citationDesai, S., & Chin, J. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581507 · Cited by 38
“Other similar systems have been developed to educate the users about vaccinations [85], counselling [77], and medication adherence [65].”
BackgroundExamining Humanness as a Metaphor to Design Voice User Interfaces
Desai, S., Dubiel, M., & Leiva, L. A. (2024) · ACM Conversational User Interfaces 2024 · doi:10.1145/3640794.3665535 · Cited by 21
“ABSTRACT Voice User Interfaces (VUIs) increasingly leverage ‘humanness’ as a foundational design metaphor, adopting roles like ‘assistants,’ ‘teachers,’ and ‘secretaries’ to foster natural interactions.”
Background
Metadata
- Authors
- Motalebi, N., Cho, E., Sundar, S. S., & Abdullah, S.
- Affiliations
- Pennsylvania State University (US)
- Venue
- Companion Publication of the 2019 Conference on Computer Supported Cooperative Work and Social Computing
- Publisher
- ACM
- Published
- 2019-11-09
- Pages
- 309-313
- OpenAlex
- W2985336104
- Cited by
- 15
- References
- 10
- Citations by year
- 2025: 2 · 2024: 6 · 2023: 2 · 2022: 2 · 2021: 3
- FWCI
- 0.48
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM Conference on Computer Supported Cooperative Work (CSCW) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Social Sciences › Psychology › Social Psychology › Social Robot Interaction and HRI
- Physical Sciences › Computer Science › Human-Computer Interaction › Innovative Human-Technology Interaction
- Keywords
- smart speakers, Amazon Alexa, backchanneling, user engagement, chatbots, active listening, emotional support, social support
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.