“I wrote as if I were telling a story to someone I knew.”: Designing Chatbot Interactions for Expressive Writing in Mental Health
Open accessThe DOI matches its Crossref record; 29 of the 29 references it cites were found in a registry or an index.
Abstract
Writing about experiences of trauma and other challenges in life is known to provide measurable health benefits. Though writing for an audience may ensure better benefits, confiding one's most troubled memories in others risks a social stigma. Conversational agents can provide a virtual audience that ensures privacy and allows social disclosure. To understand the writing experience with an agent, we created Diarybot, a chatbot assistant for expressive writing. We designed two versions, Basic and Responsive, to explore the writing experience with and without bot follow-up interactions compared to a Google doc baseline. Findings from a 4-day user study with 30 participants reveal that social disclosure with Diarybot can encourage narrative writing, with relative ease and emotional expression in Basic chat. Responsive chat can mediate social acceptance of the bot and provide guidance for self-reflection in the process. We discuss design reflections on social disclosure with agents in pursuit of wellbeing.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Using thematic analysis in psychology
Braun, V., & Clarke, V. (2006) · Qualitative Research in Psychology · doi:10.1191/1478088706qp063oa · Cited by 194,414
The Psychological Meaning of Words: LIWC and Computerized Text Analysis Methods
Tausczik, Y. R., & Pennebaker, J. W. (2010) · Journal of Language and Social Psychology · doi:10.1177/0261927x09351676 · Cited by 5,774 · cited 3×
“…responses to the expressive writing instructions were first anonymized and then analyzed in terms of their use of affective and cognitive words with the Linguistic Inquiry and Word Count (LIWC), serviced in Korean translation [45, 87], to find any sentiment differences across writing conditions.”
BackgroundELIZA—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 · cited 1×
“This find-and-match algorithm is useful to preserve conversational context and continue on with the conversation [90].”
BackgroundFitzpatrick, K. K., Darcy, A., & Vierhile, M. (2017) · JMIR Mental Health · doi:10.2196/mental.7785 · Cited by 2,730 · cited 2×
“Woebot [20], Wysa [37], are in popular and successful service.”
BackgroundWriting About Emotional Experiences as a Therapeutic Process
Pennebaker, J. W. (1997) · Psychological Science · doi:10.1111/j.1467-9280.1997.tb00403.x · Cited by 2,486
Nass, C., Steuer, J., & Tauber, E. R. (1994) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/191666.191703 · Cited by 2,148 · cited 2×
“Commonly referred to as the phrase “computers are social actors (CASA),” it is widely accepted in HCI that people sometimes interact with the computer in ways that mimic social interactions with others, especially when it has certain anthropomorphic qualities [44, 57].”
Emotion Elicits the Social Sharing of Emotion: Theory and Empirical Review
Rimé, B. (2009) · Emotion Review · doi:10.1177/1754073908097189 · Cited by 1,546 · cited 9×
“Previous research has that we are wired to share our emotions with others [11, 59, 75, 77].”
BackgroundInfluentialExperimental disclosure and its moderators: A meta-analysis.
Frattaroli, J. (2006) · Psychological Bulletin · doi:10.1037/0033-2909.132.6.823 · Cited by 1,502 · cited 2×
“However, critique points out that such approach deviates from the “expressive” nature of the writing paradigm [21].”
BackgroundInkster, B., Sarda, S., & Subramanian, V. (2018) · doi:10.2196/preprints.12106 · Cited by 1,063
The SAGE Handbook of Qualitative Research in Psychology
Willig, C., & Rogers, W. S. (2017) · doi:10.4135/9781526405555 · Cited by 1,035
It's only a computer: virtual humans increase willingness to disclose
Lucas, G. M., Gratch, J., King, A., & Morency, L.-P. (2014) · Computers in Human Behavior · doi:10.1016/j.chb.2014.04.043 · Cited by 977 · cited 2×
“Others include virtual humans [48] and relational agents [3, 4, 81, 88], with evidence for less fear of self-disclosure and more intense emotional expression in interacting with agents, and that such interaction is enjoyable and capable of facilitating empathy and trust with these agents, leading to positive health be…”
BackgroundLinguistic predictors of adaptive bereavement
Pennebaker, J. W., Mayne, T. J., & Francis, M. E. (1997) · Journal of Personality and Social Psychology · doi:10.1037/0022-3514.72.4.863 · Cited by 970
Accelerating the coping process.
Pennebaker, J. W., Colder, M., & Sharp, L. K. (1990) · Journal of Personality and Social Psychology · doi:10.1037//0022-3514.58.3.528 · Cited by 798
Ho, A., Hancock, J., & Miner, A. S. (2018) · Journal of Communication · doi:10.1093/joc/jqy026 · Cited by 629 · cited 2×
“While others have used Wizard-of-Oz [33] for a social setting of expressive writing, we are keen to investigate a chatbot interaction with the current state-of-the-art technology to evaluate social disclosure with AI in a more technologically realistic setting.”
Nass, C., Steuer, J., & Tauber, E. R. (1994) · Conference companion on Human factors in computing systems - CHI '94 · doi:10.1145/259963.260288 · Cited by 579
CORE: Clinical Outcomes in Routine Evaluation
Evans, C., Mellor-Clark, J., Margison, F., Barkham, M., Audin, K., Connell, J., & McGrath, G. (2000) · Journal of Mental Health · doi:10.1080/713680250 · Cited by 560 · cited 1×
“”) [18].”
The role of nonspecific factors in cognitive-behavior therapy for depression.
Ilardi, S. S., & Craighead, W. E. (1994) · Clinical Psychology: Science and Practice · doi:10.1111/j.1468-2850.1994.tb00016.x · Cited by 501
Barkham, M., Bewick, B., Mullin, T., Gilbody, S., Connell, J., Cahill, J., Mellor-Clark, J., Richards, D., Unsworth, G., & Evans, C. (2013) · Counselling and Psychotherapy Research · doi:10.1080/14733145.2012.729069 · Cited by 413
Butler, G., Fennell, M., Robson, P., & Gelder, M. (1991) · Journal of Consulting and Clinical Psychology · doi:10.1037/0022-006x.59.1.167 · Cited by 365 · cited 1×
“(CBT), interpretation takes place when a client evaluates psychological threat [8] and the therapist tries to help restructure any maladaptive thoughts [36].”
Background'It's just like you talk to a friend': relational agents for older adults
Bickmore, T. W., Caruso, L., Clough-Gorr, K., & Heeren, T. (2005) · Interacting with Computers · doi:10.1016/j.intcom.2005.09.002 · Cited by 341 · cited 1×
“Others include virtual humans [48] and relational agents [3, 4, 81, 88], with evidence for less fear of self-disclosure and more intense emotional expression in interacting with agents, and that such interaction is enjoyable and capable of facilitating empathy and trust with these agents, leading to positive health be…”
BackgroundExpressive Writing: Connections to Physical and Mental Health
Pennebaker, J. W., & Chung, C. K. (2012) · The Oxford Handbook of Health Psychology · doi:10.1093/oxfordhb/9780195342819.013.0018 · Cited by 337 · cited 3×
“For decades, Pennebaker et al. have studied this act of constructing a story on traumatic life experiences that lead to improved health outcomes [6, 64–66, 68, 71, 85].”
BackgroundMethodBenefits of Expressive Writing in Lowering Rumination and Depressive Symptoms
Gortner, E.-M., Rude, S. S., & Pennebaker, J. W. (2006) · Behavior Therapy · doi:10.1016/j.beth.2006.01.004 · Cited by 328 · cited 1×
“In fact, expressive writing has been widely studied as an important therapeutic instrument [13, 25, 26, 46, 83, 84].”
BackgroundMorris, R. R., Kouddous, K., Kshirsagar, R., & Schueller, S. M. (2018) · Journal of Medical Internet Research · doi:10.2196/10148 · Cited by 273
Emotional expression and physical health: Revising traumatic memories or fostering self-regulation?
Greenberg, M. A., Wortman, C. B., & Stone, A. A. (1996) · Journal of Personality and Social Psychology · doi:10.1037/0022-3514.71.3.588 · Cited by 247
Key Considerations for Incorporating Conversational AI in Psychotherapy
Miner, A. S., Shah, N., Bullock, K. D., Arnow, B. A., Bailenson, J., & Hancock, J. (2019) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2019.00746 · Cited by 166
Relational Agents in Clinical Psychiatry
Bickmore, T., & Gruber, A. (2010) · Harvard Review of Psychiatry · doi:10.3109/10673221003707538 · Cited by 112 · cited 1×
“Others include virtual humans [48] and relational agents [3, 4, 81, 88], with evidence for less fear of self-disclosure and more intense emotional expression in interacting with agents, and that such interaction is enjoyable and capable of facilitating empathy and trust with these agents, leading to positive health be…”
BackgroundZhou, C., Wu, Y., An, S., & Li, X. (2015) · PLOS ONE · doi:10.1371/journal.pone.0131802 · Cited by 48
Expressive Writing in the Clinical Context
Smyth, J. M., Nazarian, D., & Arigo, D. (2007) · Emotion Regulation · doi:10.1007/978-0-387-29986-0_14 · Cited by 42
Structured writing about current stressors: The benefits of developing plans
Lestideau, O. T., & Lavallee, L. F. (2007) · Psychology & Health · doi:10.1080/14768320601176089 · Cited by 7
Cited by
Collaborating with ChatGPT in argumentative writing classrooms
Su, Y., Lin, Y., & Lai, C. (2023) · Assessing Writing · doi:10.1016/j.asw.2023.100752 · Cited by 563
Fuchs, K. (2023) · Frontiers in Education · doi:10.3389/feduc.2023.1166682 · Cited by 353
Jo, E., Epstein, D. A., Jung, H., & Kim, Y.-H. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581503 · Cited by 174
“Specifcally, studies have designed chatbots for eliciting self-disclosure [40, 41, 55] or increasing self-compassion by taking care of chatbots that experience distress [30, 38].”
BackgroundA Design Space for Intelligent and Interactive Writing Assistants
Lee, M., Gero, K. I., Chung, J. J. Y., Shum, S. B., Raheja, V., Shen, H., Venugopalan, S., Wambsganss, T., Zhou, D., Alghamdi, E. A., et al. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642697 · Cited by 136
“We choose this approach because we find it more during the idea generation stage, writers brainstorm and develop concepts.”
InfluentialHua, Y., Siddals, S., Ma, Z., Galatzer‐Levy, I., Xia, W., Hau, C., Na, H., Flathers, M., Linardon, J., Ayubcha, C., et al. (2025) · World Psychiatry · doi:10.1002/wps.21352 · Cited by 117
Metadata
- Authors
- Park, S., Thieme, A., Han, J., Lee, S., Rhee, W., & Suh, B.
- Venue
- Designing Interactive Systems Conference 2021
- Publisher
- ACM
- Published
- 2021-06-28
- Pages
- 926-941
- OpenAlex
- W3174098556
- Cited by
- 57
- References
- 29
- FWCI
- 4.05
- Type
- conference paper
- Language
- en
- Open access
- bronze
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.