The DOI matches its Crossref record; 31 of the 36 references it cites were found in a registry or an index.
A Collaborative Approach to Identifying Social Media Markers of Schizophrenia by Employing Machine Learning and Clinical Appraisals
Open accessAbstract
BACKGROUND: Linguistic analysis of publicly available Twitter feeds have achieved success in differentiating individuals who self-disclose online as having schizophrenia from healthy controls. To date, limited efforts have included expert input to evaluate the authenticity of diagnostic self-disclosures. OBJECTIVE: This study aims to move from noisy self-reports of schizophrenia on social media to more accurate identification of diagnoses by exploring a human-machine partnered approach, wherein computational linguistic analysis of shared content is combined with clinical appraisals. METHODS: Twitter timeline data, extracted from 671 users with self-disclosed diagnoses of schizophrenia, was appraised for authenticity by expert clinicians. Data from disclosures deemed true were used to build a classifier aiming to distinguish users with schizophrenia from healthy controls. Results from the classifier were compared to expert appraisals on new, unseen Twitter users. RESULTS: Significant linguistic differences were identified in the schizophrenia group including greater use of interpersonal pronouns (P<.001), decreased emphasis on friendship (P<.001), and greater emphasis on biological processes (P<.001). The resulting classifier distinguished users with disclosures of schizophrenia deemed genuine from control users with a mean accuracy of 88% using linguistic data alone. Compared to clinicians on new, unseen users, the classifier's precision, recall, and accuracy measures were 0.27, 0.77, and 0.59, respectively. CONCLUSIONS: These data reinforce the need for ongoing collaborations integrating expertise from multiple fields to strengthen our ability to accurately identify and effectively engage individuals with mental illness online. These collaborations are crucial to overcome some of mental illnesses' biggest challenges by using digital technology.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Studies have reported that individuals living with a range of mental disorders, including depression, psychotic disorders, or other severe mental illnesses, use social media platforms at comparable rates as the general population”
From Social Media and Mental Health: Benefits, Risks, and Opportunities for Research and Practice (2020) · cites this paper as M. L. Birnbaum et al., 2017
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“For adolescents and young adults ages 12 to 21 with psychotic disorders and mood disorders, over 97% reported using social media, with average use exceeding 2.5 hours per day (M. L. Birnbaum et al., 2017).”
From Social Media and Mental Health: Benefits, Risks, and Opportunities for Research and Practice (2020) · cites this paper as M. L. Birnbaum et al., 2017
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Several studies have also demonstrated that when compared to a control group, Twitter users with a self-disclosed diagnosis of schizophrenia show unique online communication patterns (Michael L Birnbaum, Ernala, Rizvi, De Choudhury, & Kane, 2017), including more frequent discussion of tobacco use (Hswen et al., 2017), symptoms of depression and anxiety (Hswen, Naslund, Brownstein, & Hawkins, 2018b”
From Social Media and Mental Health: Benefits, Risks, and Opportunities for Research and Practice (2020) · cites this paper as Michael L Birnbaum, Ernala, Rizvi, De Choudhury, & Kane, 2017
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“connecting with mental health providers (M. L. Birnbaum et al., 2017)”
From Social Media and Mental Health: Benefits, Risks, and Opportunities for Research and Practice (2020) · cites this paper as M. L. Birnbaum et al., 2017
Experimental — accuracy not yet measured
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
Book Review: Pattern Recognition and Machine Learning
Nasrabadi, N. M. (2007) · Journal of Electronic Imaging · doi:10.1117/1.2819119 · Cited by 22,066 · cited 2×
“The classifier was built and evaluated by applying 10-fold cross-validation, an established technique in supervised machine learning [25].”
MethodPersonality, Gender, and Age in the Language of Social Media: The Open-Vocabulary Approach
Schwartz, H. A., Eichstaedt, J. C., Kern, M. L., Dziurzynski, L., Ramones, S. M., Agrawal, M., Shah, A., Kosinski, M., Stillwell, D., Seligman, M. E. P., et al. (2013) · PLoS ONE · doi:10.1371/journal.pone.0073791 · Cited by 1,700
Pandemics in the Age of Twitter: Content Analysis of Tweets during the 2009 H1N1 Outbreak
Chew, C., & Eysenbach, G. (2010) · PLoS ONE · doi:10.1371/journal.pone.0014118 · Cited by 1,614
Perkins, D., Gu, H., Boteva, K., & Lieberman, J. (2005) · American Journal of Psychiatry · doi:10.1176/appi.ajp.162.10.1785 · Cited by 1,304 · cited 1×
“Results from the Recovery After Initial Schizophrenia Episode-Early Treatment Program (RAISE-ETP) trial [31] suggest that the median duration of untreated psychosis is 74 weeks [32] and support the established hypothesis that lengthy duration of untreated psychosis (DUP) leads to worse outcomes [31,33].”
BackgroundKane, J. M., Robinson, D. G., Schooler, N. R., Mueser, K. T., Penn, D. L., Rosenheck, R. A., Addington, J., Brunette, M. F., Correll, C. U., Estroff, S. E., et al. (2015) · American Journal of Psychiatry · doi:10.1176/appi.ajp.2015.15050632 · Cited by 896 · cited 1×
“Results from the Recovery After Initial Schizophrenia Episode-Early Treatment Program (RAISE-ETP) trial [31] suggest that the median duration of untreated psychosis is 74 weeks [32] and support the established hypothesis that lengthy duration of untreated psychosis (DUP) leads to worse outcomes [31,33].”
BackgroundSelf-citationQuantifying Mental Health Signals in Twitter
Coppersmith, G., Dredze, M., & Harman, C. (2014) · Proceedings of the Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality · doi:10.3115/v1/w14-3207 · Cited by 722 · cited 2×
“Prior work identifying markers of mental illness online used similar filtering techniques based on self-reported diagnoses [22,23].”
BackgroundMethodChristofides, E., Muise, A., & Desmarais, S. (2009) · CyberPsychology & Behavior · doi:10.1089/cpb.2008.0226 · Cited by 696 · cited 1×
“More than 90% of US youth use social media daily [1], placing it ahead of texting, email, and instant messaging, and they disclose considerably more about themselves online than offline [2].”
BackgroundAutomated analysis of free speech predicts psychosis onset in high-risk youths
Bedi, G., Carrillo, F., Cecchi, G. A., Slezak, D. F., Sigman, M., Mota, N. B., Ribeiro, S., Javitt, D. C., Copelli, M., & Corcoran, C. M. (2015) · npj Schizophrenia · doi:10.1038/npjschz.2015.30 · Cited by 673 · cited 2×
“Furthermore, classifiers designed to automatically sort individual cases into diagnostic categories have achieved success in recognizing participants with psychotic disorders from healthy controls based on linguistic differences in writing samples [15] and speech [13,18].”
BackgroundResultSocial media as a measurement tool of depression in populations
De Choudhury, M., Counts, S., & Horvitz, E. (2013) · Proceedings of the 5th Annual ACM Web Science Conference · doi:10.1145/2464464.2464480 · Cited by 497
Broniatowski, D. A., Paul, M., & Dredze, M. (2013) · PLoS ONE · doi:10.1371/journal.pone.0083672 · Cited by 474
Flagged first, then by citations
5 of the 36 references couldn’t be matched to a known paper.
Research works printed but not linked: 3
- McManus, K, 2015, AMIA Jt Summits Transl Sci Proc, 2015, 122
- Bishop, CM, 2006, Pattern Recognition and Machine Learning
- CoppersmithGHarmanCDredzeMMeasuring post traumatic stress disorder in TwitterProceedings of the International AAAI Conference on Web and Social Media Eighth International AAAI Conference on Weblogs and Social Media2014Eighth International AAAI Conference on Weblogs and Social MediaJun 1-4, 2014Ann Arbor, MI16
Cited by
Sorted by citations
Items 101–158 of 158
Zingg, A., Singh, T., & Myneni, S. (2021) · Frontiers in Digital Health · doi:10.3389/fdgth.2021.653769 · Cited by 11
“Some examples are the application of computational linguistic analysis to identify Twitter posts where users show signs of schizophrenia (31), and the application of machine learning techniques in online cancer support groups to extract participant’s behaviors, treatments, and emotions (32).”
BackgroundAnonymous Prediction of Mental Illness in Social Media
Tadisetty, S., & Ghazinour, K. (2021) · IEEE Annual Computing and Communication Workshop and Conference (CCWC) · doi:10.1109/ccwc51732.2021.9376140 · Cited by 10
“Over 2 billion users engage with social media websites [11].”
BackgroundMerayo, N., Lanchares, A. A., & González‐Sanguino, C. (2024) · PeerJ Computer Science · doi:10.7717/peerj-cs.2251 · Cited by 15
“…way, on analysing emotional response in social networks, in contrast to existing research that focuses mainly on identifying types of psychopathology ( Ahmed et al., 2022 ; Birnbaum et al., 2017 ; Fodeh et al., 2019 ; Guntuku et al., 2017 ; Joshi & Kanoongo, 2022 ; Lejeune et al., 2022 ).”
ResultFranco, O. H., Calkins, M. E., Giorgi, S., Ungar, L., Gur, R. E., Kohler, C. G., & Tang, S. X. (2022) · JMIR Formative Research · doi:10.2196/30230 · Cited by 15
“For example, a classification model based on social media language was able to identify early relapse signs for people experiencing first episode psychosis [6].”
BackgroundCharacterizing Anxiety Disorders with Online Social and Interactional Networks
Dutta, S., & Choudhury, M. D. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-60152-2_20 · Cited by 10
Mim, M. N., Firoz, M., Islam, M. M., Hasan, M., & Habib, M. (2024) · Bulletin of Electrical Engineering and Informatics · doi:10.11591/eei.v13i5.5680 · Cited by 9
Price, G. D., Heinz, M. V., Nemesure, M., McFadden, J., & Jacobson, N. (2022) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2022.807116 · Cited by 9
“Specific to individuals with schizophrenia, an extensive corpus of research has shown machine learning efficacious in classifying schizophrenia and psychosis-related symptoms from neuroimaging data (32–34), qualitative social media information (35, 36), and passively collected smartphone data.”
BackgroundCross-Platform Detection of Psychiatric Hospitalization via Social Media Data: Comparison Study
Nguyen, V. C., Lu, N. Y., Kane, J. M., Birnbaum, M. L., & Choudhury, M. D. (2022) · JMIR Mental Health · doi:10.2196/39747 · Cited by 14
“These include certain word frequencies, word categories, and self-referential pronouns [11,12].”
BackgroundMethodSelf-citationHaCohen‐Kerner, Y., Manor, N., Goldmeier, M., & Bachar, E. (2022) · IEEE Access · doi:10.1109/access.2022.3162685 · Cited by 14
“VOLUME XX, 2021 depression [8], post-traumatic stress disorder (PTSD) [4], suicide [9], anxiety [10], schizophrenia [11], and bipolar disorder [12].”
BackgroundEthics of the Use of Social Media as Training Data for AI Models Used for Digital Phenotyping
Jaiswal, A., Shah, A., Harjadi, C., Windgassen, E., & Washington, P. Y. (2024) · JMIR Formative Research · doi:10.2196/59794 · Cited by 11
Into the Unknown: Exploration of Search Engines’ Responses to Users with Depression and Anxiety
Milton, A., & Pera, M. S. (2023) · ACM Transactions on the Web · doi:10.1145/3580283 · Cited by 9
“[15] have contemplated the feasibility of detecting the early onset of MHD from query logs.”
BackgroundADHD Diagnosis Using Text Features and Predictive Machine Learning and Deep Learning Algorithms
Alsharif, N. H., Al-Adhaileh, M. H., Alsubari, S. N., & Al‐Yaari, M. (2024) · Journal of Disability Research · doi:10.57197/jdr-2024-0082 · Cited by 13
“Birnbaum et al. (2017) investigated the potential of social media in detecting persons with schizophrenia by integrating clinical assessments with social media information.”
BackgroundTechnological Advances in Clinical Assessment
Trull, T. J., Griffin, S. A., & Helle, A. C. (2019) · Cambridge University Press eBooks · doi:10.1017/9781108235433.007 · Cited by 3
Xu, T., Wang, N., Jin, Y., Chen, Y., & Ma, K. (2025) · Neural Regeneration Research · doi:10.4103/nrr.nrr-d-25-00121 · Cited by 5
“…Table 2 summarizes representative studies in the last 5 years that applied ML and DL methods in mental disorders research (Chang et al., 2011; Birnbaum et al., 2017, 2020; Jaiswal et al., 2017; Shim et al., 2019; Srinivasagopalan et al., 2019; Yan et al., 2019; Li et al., 2020, 2021; Tadesse…”
Improving Mental Health Classifier Generalization with Pre-diagnosis Data
Liu, Y., Biester, L., & Mihalcea, R. F. (2023) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v17i1.22169 · Cited by 3
“Based on these diagnosis patterns, some work further includes experts to verify the authenticity of identified diagnosed users (Mitchell, Hollingshead, and Coppersmith 2015; Ernala et al. 2017; Cohan et al. 2018; Birnbaum et al. 2017).”
BackgroundMethodNitzburg, G. C., Weber, I. G., & Yom‐Tov, E. (2019) · Journal of Medical Internet Research · doi:10.2196/10946 · Cited by 8
“Although many researchers investigating online patterns in psychiatric disorders and SUD have opted to examine social media activity rather than search engine queries [36-48], Web-search log data analysis is particularly well suited to the study of alcohol-related medical symptoms.”
The detection of mental health conditions by incorporating external knowledge
Lin, Y. S., Tai, L. K., & Chen, A. L. P. (2023) · Journal of Intelligent Information Systems · doi:10.1007/s10844-022-00774-w · Cited by 6
“Moreover, a growing body of research is concentrating on analyzing the copious amounts of text on social media to learn more about mental health conditions (Coppersmith et al., 2015; Birnbaum et al., 2017).”
BackgroundMental Health Consultations on College Campuses: Examining the Predictive Ability of Social MediaPreprint
Saha, K., Yousuf, A., Boyd, R. L., Pennebaker, J., & Choudhury, M. D. (2021) · Social Science Research Network · doi:10.21203/rs.3.rs-196605/v1 · Cited by 5
Social Media and Early Psychosis Intervention: A Comprehensive Review of the Literature
Li, I., Estafanous, A., Choudhury, M. D., Álvarez‐Jiménez, M., & Birnbaum, M. L. (2024) · Current Treatment Options in Psychiatry · doi:10.1007/s40501-024-00314-z · Cited by 4
Self-citationSocial media in screening and monitoring for early intervention in psychosis
Feldman, J., Hamlyn, A., & Rice, T. (2021) · Schizophrenia Research · doi:10.1016/j.schres.2021.09.023 · Cited by 3
Improving Psychiatric Care Through Integrated Digital Technologies
Fowler, J. C., Madan, A., Bruce, C. R., Frueh, B. C., Kash, B. A., Jones, S. L., & Sasangohar, F. (2021) · Journal of Psychiatric Practice · doi:10.1097/pra.0000000000000535 · Cited by 4
Investigating non lexical markers of the language of schizophrenia in spontaneous conversations
Li, C., Amblard, M., Braud, C., Demily, C., Franck, N., & Musiol, M. (2021) · Workshop on Computational Approaches to Discourse (CODI) · doi:10.18653/v1/2021.codi-main.3 · Cited by 4
“For schizophrenia, previous work has mainly focused on lexical information (Mitchell et al., 2015; Hong et al., 2012; Birnbaum et al., 2017; Xu et al., 2019).”
BackgroundNesbitt, B., Virgadamo, D. S., Aguirre, C. A., DeCamp, M. W., Dredze, M. H., Harrigian, K., Lhaksampa, T. C., Meuchel, J. M., Meyer, A. M., Walker, A., et al. (2025) · JMIR Research Protocols · doi:10.2196/63279 · Cited by 5
“…activity on different social media platforms are associated with and can be used to develop computational models that distinguish individuals with depression [14-17], postpartum depression [17], schizophrenia [18-20], posttraumatic stress disorder [21], and other serious mental illnesses [22,23].”
Social networks use in the context of Schizophrenia: a review of the literature
Suárez-Llevat, C., Jiménez-Gómez, B., Ruíz-Núñez, C., Fernández-Quijano, I., Rodriguez-González, E. M., de la Torre-Domingo, C., & Herrera‐Peco, I. (2024) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2024.1255073 · Cited by 4
Detection of Depression-Positive Thai Facebook Users Using Posts and Their Usage Behavior
Hemtanon, S., Aekwarangkoon, S., & Kittiphattanabawon, N. (2021) · Lecture Notes in Networks and Systems · doi:10.1007/978-3-030-79757-7_8 · Cited by 3
Aich, A., & Parde, N. (2022) · Workshop on Computational Linguistics and Clinical Psychology (CLPsych) · doi:10.18653/v1/2022.clpsych-1.8 · Cited by 2
“…an ability to learn powerful, quantifiable signals from tweets to predict users’ mental states (Coppersmith et al., 2014), and more clinically advanced mental health conditions such as psychosis have also been detected using short appraisals of social media posts (Birnbaum et al., 2017).”
BackgroundZakowicz, P. T., Brzezicki, M. A., Pawlak, J., Skibińska, M., Jurga, S. J., Lewandowska, A., Vogel, B., Ungermann, E. M., & Remberk, B. (2025) · Scientific Reports · doi:10.1038/s41598-025-33765-2 · Cited by 2
Linguistic trajectories of bipolar disorder on social media
Plank, L., & Zlomuzica, A. (2025) · arXiv.org · doi:10.48550/arxiv.2509.10035 · Cited by 2
“Because laboratory-based language assessments are limited in scale, researchers have explored SM as a cost-efficient source of language data 49–52 .”
Miller, L., Lhaksampa, T. C., Walker, A., Aguirre, C. A., DeCamp, M. W., Harrigian, K., Meuchel, J. M., Meyer, A. M., Nesbitt, B., Sthapit, S., et al. (2025) · JMIR Mental Health · doi:10.2196/74212 · Cited by 2
Towards Comprehensive Language Analysis for Clinically Enriched Spontaneous Dialogue
Karacan, B., Aich, A., Quynh, A., Pinkham, A. E., Harvey, P. D., Depp, C. A., & Parde, N. (2024) · International Conference on Language Resources and Evaluation · doi:10.63317/4us68j7zakbd · Cited by 2
Comparative Analysis of Deep Learning Techniques for Drug Addiction
Sujana, S., Kumar, A., Charan, L. A. S., Nishitha, G., & Ratnababu, M. (2024) · 2024 IEEE 9th International Conference for Convergence in Technology (I2CT) · doi:10.1109/i2ct61223.2024.10544100 · Cited by 2
“The fact that mentoring and social support are crucial components of an addict’s recovery process served as the inspiration for this effort [5] [6].”
BackgroundAutomatic Detection and Prediction of Psychiatric Hospitalizations From Social Media Posts
Jiang, Z., Zomick, J., Levitan, S. I., Serper, M., & Hirschberg, J. (2021) · Workshop on Computational Linguistics and Clinical Psychology · doi:10.18653/v1/2021.clpsych-1.14 · Cited by 2
“To date, linguistic indicators of psychopathology have been identified for a wide range of psychiatric conditions (Zomick et al., 2019; Coppersmith et al., 2015; Birnbaum et al., 2017; Huang et al., 2017; De Choudhury et al., 2013; Shen and Rudzicz, 2017).”
BackgroundMayee, M. K., & Deepa, T. (2020) · International Conference on Inventive Systems and Control (ICISC) · doi:10.1109/icisc47916.2020.9171077 · Cited by 5
“…[12]. the information collected from twitter has been employed in analysis characterizing on-line communications and attitudes regarding schizophrenic disorder [13], analyze linguistic markers of the schizophrenic disorder [14,15], which gives support to observe people with schizophrenic disorder.”
MethodEarly Detection of Depression: Social Network Analysis and Random Forest Techniques (Preprint)
Cacheda, F., Fernández, D., Nóvoa, F., & Carneiro, V. (2018) · doi:10.2196/preprints.12554 · Cited by 2
Linguistic markers of schizophrenia: a case study of Robert Walser
Nenchev, I., Scheffler, T., Fuente, M. D. L. D. L., Stuke, H., Wilck, B., Just, S., & Montag, C. (2024) · Workshop on Computational Linguistics and Clinical Psychology · doi:10.18653/v1/2024.clpsych-1.4 · Cited by 2
“A commonly replicated linguistic feature of individuals with schizophrenia is the extensive use of first person singular pronouns as a marker of focus on the self (Ziv et al., 2021; Tang et al., 2021; Birnbaum et al., 2017; Lundin et al., 2023; Fineberg et al., 2015).”
BackgroundSilva, J., Rodrigues, C., & Brazil, E. V. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2026.1781552 · Cited by 1
“…trained on linguistic features have reported high classification accuracies for distinguishing SZ from control groups, typically ranging between 80 and 90% accuracy rate (Birnbaum et al., 2017; Bae et al., 2021; Ziv et al., 2022), computer models tend to overfit to strong contextual lexical cues.”
InfluentialBehind the hashtags: a review of Instagram posts on pediatric ADHD
Mahindrakar, N., Natarajan, S. K., Negi, A., Prajapati, V., Rajput, V., Tabassum, S., & Sharma, V. (2025) · International Journal of Contemporary Pediatrics · doi:10.18203/2349-3291.ijcp20251772 · Cited by 1
Investigating leadership discussion on social media: A NLP and machine learning perspective
Shankar, S., & Tewari, V. (2025) · Technology in Society · doi:10.1016/j.techsoc.2025.102936 · Cited by 1
Gender disparities and mental health manifestations in Twitter discourse on student loan debts
Sinha, G. R., Graaf, G., Larrison, C. R., & Brooks, I. S. (2024) · Social Work in Mental Health · doi:10.1080/15332985.2024.2425306 · Cited by 1
“Additionally, self-disclosed mental health statuses on social media posts are utilized to identify various mental health issues, such as depression (Yazdavar et al., 2020), ADHD (Guntuku et al., 2019), PTSD (Ismail et al., 2020), and schizophrenia (Birnbaum et al., 2017).”
Mahdavinejad, M. S., Adibi, P., Monadjemi, S. A., & Hitzler, P. (2024) · arXiv.org · doi:10.48550/arxiv.2407.21041 · Cited by 1
“Subsequently, the focus shifted towards developing feature engineering techniques and machine learning models for prediction (Birnbaum et al., 2017; Moreno et al., 2011; Nguyen et al., 2014; Rumshisky et al., 2016; Tsugawa et al., 2015).”
BackgroundWhose Mental Data? Privacy Inequities and Extended Minds
Dalrymple-Fraser, C. (2023) · AJOB Neuroscience · doi:10.1080/21507740.2023.2188311 · Cited by 1
“” Researchers seeking prodromal markers of psychiatric conditions may similarly seek to access mental content for designing, testing, and implementing diagnostic tools (see e.g., Birnbaum et al. 2017).”
BackgroundFranco, O. H., Calkins, M., Giorgi, S., Ungar, L., Gur, R., Kohler, C., & Tang, S. X. (2021) · medRxiv · doi:10.1101/2022.04.01.22273303 · Cited by 1
“For example, a social media language-based classification model was able to identify early relapse signs for people experiencing first episode psychosis [6].”
BackgroundSocial Behavior and Mental Health: A Snapshot Survey under COVID-19 PandemicPreprint
Dhelim, S., Chen, L., Ning, H., Das, S. K., Nugent, C., Burns, D., Leavey, G., Pesch, D., & White, E. B. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.08165 · Cited by 5
“Another method is to mine the shared content on social media to establish ground truth, for example searching the user content to find specific expressions, such as “I was diagnosed with depression” ([28][27][14]), or search for self-report anti-depression medication usage evidence [144].”
Artificial Intelligence in Schizophrenia
Schneider, H. (2021) · Springer eBooks · doi:10.1007/978-3-030-58080-3_214-1
Cipriani, M., Notsu, H., Vaidya, S., Castillo, J., Hau, C., Li, S., Xia, W., Yacoub, D., Zhou, S. (., Birnbaum, M. L., et al. (2026) · Schizophrenia Bulletin Open · doi:10.1093/schizbullopen/sgag023
“46 , 47 Future research may investigate these markers captured through digital phenotyping and processed with machine learning, thereby improving the granularity and objectivity of exposure measurement relative to self-report.”
Self-citationA Supervised Artificial Intelligence Framework for Schizophrenia Detection Using Twitter Data
Sadr, H., Barzgar, Z., Nazari, M., & Rotami, S. (2026) · International Conference on Web Research (ICWR) · doi:10.1109/icwr69602.2026.11513330
“Consequently, the specific vocabulary people utilize in their daily lives inherently contains crucial information regarding their underlying mental and physical states, to the extent that word choice can even predict physiological changes [11].”
Cieślak, M., Baranowska, A., Oparcik, A., Orłowa, A., Kurczoba, L., Pakuła, A., Patrzykąt, K. M., Pawłowska, J., Szyszka, K., & Turlej, K. (2025) · International Journal of Innovative Technologies in Social Science · doi:10.31435/ijitss.4(48).2025.4572
Early Detection of Anorexia in Blog Posts Written in English
HaCohen‐Kerner, Y., Manor, N., Goldmeier, M., & Bachar, E. (2025) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3779415 · Cited by 1
“…the creation of datasets that can serve as excellent testbeds for detecting different mental health disorders, such as anxiety [4], bipolar disorder [5], depression [6, 7], eating disorders (EDs) [8], post-traumatic stress disorder (PTSD) [9, 10], schizophrenia [11, 12], and suicide risk [13, 14].”
Detecting psychosis via natural language processing of social media posts: potentials and pitfalls
Plank, L., & Zlomuzica, A. (2025) · Neuropsychologia · doi:10.1016/j.neuropsychologia.2025.109325
Jaafri, M., & Achour, H. (2025) · IEEE Afro-Mediterranean Conference on Artificial Intelligence (AMCAI) · doi:10.1109/amcai66110.2025.11474344
Using Machine Learning for the Prediction and Treatment of Mental Health Conditions
Tuleutayeva, T., & Myrzakerimova, A. (2025) · IEEE International Conference on Smart Information Systems and Technologies (SIST) · doi:10.1109/sist61657.2025.11139331 · Cited by 3
R, S., Ahmed, K., & O'Connor, M. (2025) · JMIR AI · doi:10.2196/71219
“Rater 1, as domain expert, played an integral role in the evaluation process [45], providing deep expertise to interpret mental health narratives.”
Lejeune, A., Robaglia, B.-M., Walter, M., Berrouiguet, S., & Lemey, C. (2022) · doi:10.2196/preprints.36986
Gooding, P., & Kariotis, T. (2020) · doi:10.2196/preprints.24668
Yoo, D. W., Birnbaum, M., Meter, A. V., Ali, A. F., Arenare, E., Abowd, G., & de Choudhury, M. (2019) · doi:10.2196/preprints.16969
Self-citationPereira-Sanchez, V., Álvarez-Mon, M., del Barco, A. A., Álvarez-Mon, M., & Teo, A. (2019) · doi:10.2196/preprints.14167
Boraste, P., Deshmukh, M. S., & Pawar, U. B. (2026) · EPJ Web of Conferences · doi:10.1051/epjconf/202639101015
Boraste, P., & Deshmukh, M. S. (2025) · AIP conference proceedings · doi:10.1063/5.0289459 · Cited by 1
Metadata
- Authors
- Birnbaum, M. L., Ernala, S. K., Rizvi, A. F., De Choudhury, M., & Kane, J. M.
- Affiliations
- Northwell Health (US)
- Georgia Institute of Technology (US)
- Corresponding author
- Birnbaum, Michael L
- Venue
- Journal of Medical Internet Research
- Publisher
- JMIR Publications Inc.
- Published
- 2017-08-14
- Volume
- 19
- Issue
- 8
- Pages
- e289
- ISSN
- 1438-8871 (ISSN-L)
- PMC
- PMC5575421
- OpenAlex
- W2748635631
- Cited by
- 168
- References
- 36
- Citations by year
- 2026: 6 · 2025: 20 · 2024: 20 · 2023: 17 · 2022: 22 · 2021: 30 · 2020: 23 · 2019: 21 · 2018: 8 · 2017: 1
- FWCI
- 20.76
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- Locations
- Journal of Medical Internet Research (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Funders
- National Institute of General Medical Sciences (R01GM112697)
- Topics
- Social Sciences › Psychology › Social Psychology › Mental Health via Writing
- Health Sciences › Medicine › Psychiatry and Mental health › Schizophrenia research and treatment
- Physical Sciences › Computer Science › Artificial Intelligence › Authorship Attribution and Profiling
- Keywords
- schizophrenia, social media, Twitter, linguistic analysis, self-disclosure, authenticity assessment, clinical evaluation, human-machine collaboration, mental disorder detection, friendship, biological processes, online engagement
- MeSH terms
- Machine Learning, Humans, Schizophrenia, Social Behavior, Social Support, Internet, Social Media
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
