Virtual Agents in Internet-Based Cognitive Behavioral Therapy: Enhancing Engagement and Alleviating Depression
Abstract
With the rise of digital therapy environments, Cognitive Behavioral Therapy (CBT) has evolved into an internet-based form, iCBT. However, iCBT is often criticized for its high dropout rates and reduced therapeutic effectiveness compared to traditional methods. This study suggests the integration of virtual agents to address these issues, hypothesizing that such agents can improve the therapeutic alliance—a crucial element for successful iCBT. To empirically test this, we conducted an experiment with 80 participants divided into two groups. The intervention group interacted with iCBT content incorporating a virtual agent for two weeks, while the control group accessed identical content without the agent. Results showed a significant reduction in PHQ-9 (Patient Health Questionnaire-9) scores for the intervention group, a change not seen in the control group. Sentiment analysis via zero-shot classification further confirmed a more positive sentiment in the intervention group's responses. Notably, the former reported increased engagement, potentially addressing iCBT's high dropout concern. In conclusion, while virtual agents might not resolve all iCBT challenges, they do appear to enhance their efficacy. This study provides a significant step towards optimizing the incorporation of virtual agents in therapeutic settings, showcasing a novel contribution to the field of digital mental health interventions.
Integrity signals
Registry
Cites
Statistics
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?
Jeong reported 0.30 SD baseline difference for depression.
“For example, Jeong [99] reported 0.30 SD for depression, McFadyen et al [61] reported 0.26 SD for anxiety, Sabour [64] reported 0.33 SD for depression.”
From Generative AI Mental Health Chatbots as Therapeutic Tools: Systematic Review and Meta-Analysis of Their Role in Reducing Mental Health Issues (2025) · cites this paper as [99]
Cites
Karyotaki, E., Efthimiou, O., Miguel, C., Maas genannt Bermpohl, F., Furukawa, T. A., Cuijpers, P., Individual Patient Data Meta-Analyses for Depression (IPDMA-DE) Collaboration, Riper, H., Patel, V., Mira, A., et al. (2021) · JAMA Psychiatry · doi:10.1001/jamapsychiatry.2020.4364 · Cited by 866 · see citing works
Hedman, E., Ljótsson, B., & Lindefors, N. (2012) · Expert Review of Pharmacoeconomics & Outcomes Research · doi:10.1586/erp.12.67 · Cited by 672 · see citing works
Internet-Based Cognitive-Behavioral Therapy for Depression: Current Progress and Future Directions
Webb, C. A., Rosso, I. M., & Rauch, S. L. (2017) · Harvard Review of Psychiatry · doi:10.1097/hrp.0000000000000139 · Cited by 217 · see citing works
Karyotaki, E., Kemmeren, L., Riper, H., Twisk, J., Hoogendoorn, A., Kleiboer, A., Mira, A., Mackinnon, A., Meyer, B., Botella, C., et al. (2018) · Psychological Medicine · doi:10.1017/s0033291718000648 · Cited by 167 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Zhang, Q., Zhang, R., Xiong, Y., Sui, Y., Tong, C., & Lin, F.-H. (2025) · Journal of Medical Internet Research · doi:10.2196/78238 · Cited by 56 · see citing works
“For example, Jeong [99] reported 0.30 SD for depression, McFadyen et al [61] reported 0.26 SD for anxiety, Sabour [64] reported 0.33 SD for depression.”
Influential
- Authors
- Jeong, H., Yoo, J. H., & Goh, M.
- Affiliations
- Sungkyunkwan University (KR)
- Venue
- 2023 IEEE International Conference on Agents (ICA)
- Publisher
- IEEE
- Published
- 2023-12-04
- Pages
- 57-62
- OpenAlex
- W4391306714
- Cited by
- 2
- References
- 4
- Citations by year
- 2025: 1 · 2024: 1
- FWCI
- 0.96
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Conference on Agents (ICA) (publishedVersion)
- Topics
- Social Sciences › Psychology › Applied Psychology › Digital Mental Health Interventions
- Social Sciences › Psychology › Social Psychology › Social Robot Interaction and HRI
- Health Sciences › Medicine › Public Health, Environmental and Occupational Health › Telemedicine and Telehealth Implementation
- Keywords
- virtual agents, internet-based cognitive behavioral therapy, depression, dropout rates, therapeutic relationship, patient engagement, digital mental health interventions, PHQ-9, sentiment analysis, zero-shot classification
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