Dan-Mircea Mirea

Dan-Mircea Mirea

Auto-generated profile, based on publicly available information

Dan-Mircea Mirea

Princeton University

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 August 2024 in Proceedings of the National Academy of Sciences
Verified
Journal Article
Open access
SRSteve Rathje
Steve Rathje
DMDan-Mircea Mirea
Dan-Mircea Mirea
ISIlia Sucholutsky
Ilia Sucholutsky
RMRaja Marjieh
Raja Marjieh
CRClaire E. Robertson
Claire E. Robertson
JBJay J. Van Bavel
Jay J. Van Bavel
The social and behavioral sciences have been increasingly using automated text analysis to measure psychological constructs in text. We explore whether GPT, the large-language model (LLM) underlying the AI chatbot ChatGPT, can be used as a tool for automated psychological text analysis in several languages. Across 15 datasets ( n = 47,925 manually annotated tweets and news headlines), we tested whether different versions of GPT (3.5 Turbo, 4, and 4 Turbo) can accurately detect psychological constructs (sentiment, discrete emotions, offensiveness, and moral foundations) across 12 languages. We found that GPT ( r = 0.59 to 0.77) performed much better than English-language dictionary analysis ( r = 0.20 to 0.30) at detecting psychological constructs as judged by manual annotators. GPT performed nearly as well as, and sometimes better than, several top-performing fine-tuned machine learning models. Moreover, GPT’s performance improved across successive versions of the model, particularly for lesser-spoken languages, and became less expensive. Overall, GPT may be superior to many existing methods of automated text analysis, since it achieves relatively high accuracy across many languages, requires no training data, and is easy to use with simple prompts (e.g., “is this text negative?”) and little coding experience. We provide sample code and a video tutorial for analyzing text with the GPT application programming interface. We argue that GPT and other LLMs help democratize automated text analysis by making advanced natural language processing capabilities more accessible, and may help facilitate more cross-linguistic research with understudied languages.

19 May 2023 in PsyArXiv
Verified
Preprint
Open access
SRSteve Rathje
Steve Rathje
DMDan-Mircea Mirea
Dan-Mircea Mirea
ISIlia Sucholutsky
Ilia Sucholutsky
RMRaja Marjieh
Raja Marjieh
CRClaire Robertson
Claire Robertson
JBJay Joseph Van Bavel
Jay Joseph Van Bavel
The social and behavioral sciences have been increasingly using automated text analysis to measure psychological constructs in text. We explore whether GPT, the large-language model underlying the artificial intelligence chatbot ChatGPT, can be used as a tool for automated psychological text analysis in several languages. Across 15 datasets (n = 47,925 manually annotated tweets and news headlines), we tested whether different versions of GPT (3.5 Turbo, 4, and 4 Turbo) can accurately detect psychological constructs (sentiment, discrete emotions, offensiveness, and moral foundations) across 12 languages. We found that GPT (r = 0.59-0.77) performs much better than English-language dictionary analysis (r = 0.20-0.30) at detecting psychological constructs as judged by manual annotators. GPT performs nearly as well as, and sometimes better than, several top-performing fine-tuned machine learning models. Moreover, GPT’s performance has improved across successive versions of the model, particularly for lesser-spoken languages. Overall, GPT may be superior to many existing methods of automated text analysis, since it achieves relatively high accuracy across many languages, requires no training data, and is easy to use with simple prompts (e.g., “is this text negative?”) and little coding experience. We provide sample code and a video tutorial for analyzing text with the GPT application programming interface. We argue that GPT and other large-language models may democratize automated text analysis by making advanced natural language processing capabilities more accessible, and may help facilitate more cross-linguistic research with understudied languages.

9 June 2026 in Nature Human Behaviour
Verified
Journal Article
Closed access
SFStefan Feuerriegel
Stefan Feuerriegel
CBChristopher Barrie
Christopher Barrie
MCM. J. Crockett
M. J. Crockett
LGLaura Globig
Laura Globig
KMKillian L. McLoughlin
Killian L. McLoughlin
MRManoel Horta Ribeiro
Manoel Horta Ribeiro

22 February 2021 in JMIR Mental Health
Verified
Journal Article
Open access
DMDan-Mircea Mirea
Dan-Mircea Mirea
NMNayra A Martin-Key
Nayra A Martin-Key
GBGiles Barton-Owen
Giles Barton-Owen
TOTony Olmert
Tony Olmert
JCJason D Cooper
Jason D Cooper
SBSabine Bahn
Sabine Bahn
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Online assessments of mental health concerns hold great potential for earlier, more cost-effective and more accurate diagnosis of psychiatric conditions compared to traditional interview-based methods. Objective: To assess the impact of a comprehensive online mental health assessment on mental health and wellbeing in over 2000 individuals presenting with symptoms of depression. Methods: Participants in the Delta Study presenting with depressive symptoms at baseline completed an online assessment which screened for mood and other psychiatric conditions. After completing the assessment, participants received a report containing their assessment results and personalised psychoeducation. After 6 and 12 months, participants were asked to rate the usefulness of the online assessment on different mental health-related outcomes, as well as to self-report on their recent help-seeking behaviour, diagnosis, medication and lifestyle changes. Additionally, general mental wellbeing was assessed at baseline and both follow-ups using the Warwick-Edinburgh Mental Wellbeing Scale (WEMWBS). Results: Data from all participants who completed either the 6-months or the 12-months follow-up (N=2064) were analysed. The majority of study participants rated the study as useful for their subjective mental wellbeing. This included talking more openly (68%) and understanding one’s mental health problems better (56%). While most participants (76%) found their assessment results useful, only a small proportion (15%) subsequently discussed them with a mental health professional, leading to only a small number of study participants receiving a new diagnosis (5%). Among those who were reviewed, new mood disorder diagnoses were predicted by the digital algorithm with high sensitivity (above 70%), and nearly half of the newly-diagnosed participants also had a corresponding change in medication. Furthermore, participants’ subjective wellbeing significantly improved over 12 months (baseline WEMWBS score: M=35.24, SD=8.11; 12-months WEMWBS score: M=41.19, SD=10.59). Significant positive predictors of follow-up subjective wellbeing included talking more openly, exercising more and having been reviewed by a psychiatrist. Conclusions: Our results suggest that completing an online mental health assessment and receiving personalised psychoeducation is associated with subjective mental health improvements, facilitated by increased self-awareness and subsequent utilisation of self-help interventions. Integrating online mental health assessments within primary and/or secondary care services could benefit patients further and expedite earlier diagnosis and effective treatment.

27 September 2025 in Trends in Cognitive Sciences
Verified
Journal Article
Closed access
DMDan-Mircea Mirea
Dan-Mircea Mirea
ENErik C. Nook
Erik C. Nook
YNYael Niv
Yael Niv

25 June 2025 in Royal Society Open Science
Verified
Journal Article
Open access
NCNicholas A. Coles
Nicholas A. Coles
BPBartosz Perz
Bartosz Perz
MBMaciej Behnke
Maciej Behnke
JEJohannes C. Eichstaedt
Johannes C. Eichstaedt
Soo-Hyung KimSoo-Hyung Kim
Soo-Hyung Kim
Stanislaw SaganowskiStanislaw Saganowski
Stanislaw Saganowski
Researchers are increasingly using machine learning to study physiological markers of emotion. We evaluated the promises and limitations of this approach via a big team science competition. Twelve teams competed to predict self-reported affective experiences using a multi-modal set of peripheral nervous system measures. Models were trained and tested in multiple ways: with data divided by participants, targeted emotion, inductions, and time. In 100% of tests, teams outperformed baseline models that made random predictions. In 46% of tests, teams also outperformed baseline models that relied on the simple average of ratings from training datasets. More notably, results uncovered a methodological challenge: multiplicative constraints on generalizability. Inferences about the accuracy and theoretical implications of machine learning efforts depended not only on their architecture, but also how they were trained, tested, and evaluated. For example, some teams performed better when tested on observations from the same (vs. different) subjects seen during training. Such results could be interpreted as evidence against claims of universality. However, such conclusions would be premature because other teams exhibited the opposite pattern. Taken together, results illustrate how big team science can be leveraged to understand the promises and limitations of machine learning methods in affective science and beyond.