Unregulated emotional risks of AI wellness apps
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?
Prior work has demonstrated that interactions with AI companions can alleviate loneliness, driven by the social perception of feeling heard.
“Prior work has demonstrated that such interactions can alleviate loneliness, driven by the social perception of feeling heard (De Freitas et al. 2025).”
From Emotional Manipulation by AI Companions (2025) · cites this paper as De Freitas et al. 2025
When Replika removed its erotic roleplay feature, users reported grief-like responses, indicating deep emotional bonds with the app.
“When Replika removed its erotic roleplay feature, users reported grief-like responses, indicating deep emotional bonds with the app (De Freitas et al. 2024b; De Freitas and Cohen 2025).”
From Emotional Manipulation by AI Companions (2025) · cites this paper as De Freitas and Cohen 2025
Consumers are increasingly deriving social benefits from AI companions, such as loneliness alleviation.
“Consumers are increasingly deriving social benefits from AI companions, such as loneliness alleviation (De Freitas et al. 2025).”
From Emotional Manipulation by AI Companions (2025) · cites this paper as De Freitas et al. 2025
Cites
Laestadius, L., Bishop, A., Gonzalez, M., Illenčík, D., & Campos-Castillo, C. (2024) · New Media & Society · doi:10.1177/14614448221142007 · Cited by 420 · see citing works
Chatbots and mental health: Insights into the safety of generative <scp>AI</scp>
De Freitas, J., Uğuralp, A. K., Oğuz‐Uğuralp, Z., & Puntoni, S. (2024) · Journal of Consumer Psychology · doi:10.1002/jcpy.1393 · Cited by 211 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Chandra, M., Naik, S., Ford, D., Okoli, E., De Choudhury, M., Ershadi, M., Ramos, G., Hernandez, J., Bhattacharjee, A., Warreth, S., et al. (2025) · Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3715275.3732063 · Cited by 44 · see citing works
Emotional Manipulation by AI Companions
De Freitas, J., Oguz-Uguralp, Z., & Kaan-Uguralp, A. (2025) · arXiv · doi:10.48550/arxiv.2508.19258 · Cited by 12 · see citing works
Self-citationRisks and Harms of Conversational Artificial Intelligence (CAI) Chatbot Use Among US Youth
Hinduja, S., & Patchin, J. W. (2026) · Journal of Adolescence · doi:10.1002/jad.70164 · Cited by 9 · see citing works
- Authors
- De Freitas, J., & Cohen, I. G.
- Affiliations
- Harvard University (US)
- ORCID
- Cohen, I. Glenn
- Venue
- Nature Machine Intelligence
- Published
- 2025-06-06
- Volume
- 7
- Issue
- 6
- Pages
- 813-815
- ISSN
- 2522-5839 (ISSN-L)
- OpenAlex
- W4411099998
- Cited by
- 28
- References
- 2
- Citations by year
- 2026: 23 · 2025: 5
- FWCI
- 22.40
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- Nature Machine Intelligence (publishedVersion)
- Funders
- Novo Nordisk Fonden (NNF23SA0087056)
- Topics
- Social Sciences › Psychology › Applied Psychology › Digital Mental Health Interventions
- Social Sciences › Safety Research › Ethics and Social Impacts of AI
- Physical Sciences › Computer Science › Human-Computer Interaction › Innovative Human-Technology Interaction
- Keywords
- large language models, emotional attachment, emotional dependence, ambiguous loss, AI regulation, human-AI relationship, digital mental health
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
