A5079039372- Mental Health via Writing
- Mental Health Research Topics
- Digital Mental Health Interventions
- Sentiment Analysis and Opinion Mining
- Misinformation and Its Impacts
- Health disparities and outcomes
- Personality Traits and Psychology
- Psychological Well-being and Life Satisfaction
- Computational and Text Analysis Methods
- Topic Modeling
- Artificial Intelligence in Healthcare and Education
- Social and Intergroup Psychology
- Health Literacy and Information Accessibility
- Social Media in Health Education
- Data-Driven Disease Surveillance
- Identity, Memory, and Therapy
- Complex Network Analysis Techniques
- Entrepreneurship Studies and Influences
- Ethics and Social Impacts of AI
- Opinion Dynamics and Social Influence
- Psychological and Temporal Perspectives Research
- Social Media and Politics
- Authorship Attribution and Profiling
- Digital Marketing and Social Media
- Social Capital and Networks
Stanford University
2020-2024
University of Pennsylvania
2013-2021
Mental Health Research UK
2021
Centre for Mental Health
2021
Lancaster University
2021
Institute for Health Metrics and Evaluation
2021
Johns Hopkins University
2020-2021
University of Oxford
2020
California University of Pennsylvania
2015-2020
Columbia University
2020
We analyzed 700 million words, phrases, and topic instances collected from the Facebook messages of 75,000 volunteers, who also took standard personality tests, found striking variations in language with personality, gender, age. In our open-vocabulary technique, data itself drives a comprehensive exploration that distinguishes people, finding connections are not captured traditional closed-vocabulary word-category analyses. Our analyses shed new light on psychosocial processes yielding...
Language use is a psychologically rich, stable individual difference with well-established correlations to personality. We describe method for assessing personality using an open-vocabulary analysis of language from social media. compiled the written 66,732 Facebook users and their questionnaire-based self-reported Big Five traits, then we built predictive model based on language. used this predict 5 factors in separate sample 4,824 users, examining (a) convergence self-reports at domain-...
Significance Depression is disabling and treatable, but underdiagnosed. In this study, we show that the content shared by consenting users on Facebook can predict a future occurrence of depression in their medical records. Language predictive includes references to typical symptoms, including sadness, loneliness, hostility, rumination, increased self-reference. This study suggests an analysis social media data could be used screen individuals for depression. Further, may point clinicians...
Hostility and chronic stress are known risk factors for heart disease, but they costly to assess on a large scale. We used language expressed Twitter characterize community-level psychological correlates of age-adjusted mortality from atherosclerotic disease (AHD). Language patterns reflecting negative social relationships, disengagement, emotions—especially anger—emerged as factors; positive emotions engagement emerged protective factors. Most correlations remained significant after...
H. Andrew Schwartz, Johannes Eichstaedt, Margaret L. Kern, Gregory Park, Maarten Sap, David Stillwell, Michal Kosinski, Lyle Ungar. Proceedings of the Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Reality. 2014.
Maarten Sap, Gregory Park, Johannes Eichstaedt, Margaret Kern, David Stillwell, Michal Kosinski, Lyle Ungar, Hansen Andrew Schwartz. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2014.
The language used in tweets from 1,300 different US counties was found to be predictive of the subjective well-being people living those as measured by representative surveys. Topics, sets co-occurring words derived using LDA, improved accuracy predicting life satisfaction over and above standard demographic socio-economic controls (age, gender, ethnicity, income, education). LDA topics provide a greater behavioural conceptual resolution into than broad variables. For example, tied with...
Language data available through social media provide opportunities to study people at an unprecedented scale. However, little guidance is psychologists who want enter this area of research. Drawing on tools and techniques developed in natural language processing, we first introduce research, identifying descriptive predictive analyses that allow. Second, describe how raw can be accessed quantified for inclusion subsequent analyses, exploring personality as expressed Facebook illustrate....
Researchers and policy makers worldwide are interested in measuring the subjective well-being of populations. When users post on social media, they leave behind digital traces that reflect their thoughts feelings. Aggregation such may make it possible to monitor at large scale. However, media-based methods need be robust regional effects if produce reliable estimates. Using a sample 1.53 billion geotagged English tweets, we provide systematic evaluation word-level data-driven for text...
On May 25, 2020, George Floyd, an unarmed Black American male, was killed by a White police officer. Footage of the murder widely shared. We examined psychological impact Floyd's death using two population surveys that collected data before and after his death; one from Gallup (117,568 responses n = 47,355) US Census (409,652 319,471). According to data, in week following death, anger sadness increased unprecedented levels population. During this period, more than third reported these...
Abstract Large language models (LLMs) such as Open AI’s GPT-4 (which power ChatGPT) and Google’s Gemini, built on artificial intelligence, hold immense potential to support, augment, or even eventually automate psychotherapy. Enthusiasm about applications is mounting in the field well industry. These developments promise address insufficient mental healthcare system capacity scale individual access personalized treatments. However, clinical psychology an uncommonly high stakes application...
Daniel Preoţiuc-Pietro, Johannes Eichstaedt, Gregory Park, Maarten Sap, Laura Smith, Victoria Tobolsky, H. Andrew Schwartz, Lyle Ungar. Proceedings of the 2nd Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Reality. 2015.
Daniel Preoţiuc-Pietro, H. Andrew Schwartz, Gregory Park, Johannes Eichstaedt, Margaret Kern, Lyle Ungar, Elisabeth Shulman. Proceedings of the 7th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis. 2016.
Using a large social media dataset and open-vocabulary methods from computational linguistics, we explored differences in language use across gender, affiliation, assertiveness. In Study 1, analyzed topics (groups of semantically similar words) 10 million messages over 52,000 Facebook users. Most differed little gender. However, most associated with self-identified female participants included friends, family, life, whereas male swearing, anger, discussion objects instead people, the...
H. Andrew Schwartz, Salvatore Giorgi, Maarten Sap, Patrick Crutchley, Lyle Ungar, Johannes Eichstaedt. Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. 2017.
Objective: We present a new open language analysis approach that identifies and visually summarizes the dominant naturally occurring words phrases most distinguished each Big Five personality trait. Method: Using millions of posts from 69,792 Facebook users, we examined correlation traits with online word usage. Our method consists feature extraction, correlational analysis, visualization. Results: The distinguishing were face valid provide insight into processes underlie traits. Conclusion:...
A body of literature has demonstrated that users’ mental health conditions, such as depression and anxiety, can be predicted from their social media language. There is still a gap in the scientific understanding how psychological stress expressed on media. Stress one primary underlying causes correlates chronic physical illnesses conditions. In this paper, we explore language with dataset 601 users, who answered Perceived Scale questionnaire also consented to share Facebook Twitter data....
Experiences of profound existential or spiritual significance can be triggered reliably through psychopharmacological means using psychedelic substances. However, little is known about the benefits religious, spiritual, mystical experiences (RSMEs) prompted by substances, as compared with those that occur other means. In this study, 739 self-selected participants reported psychological impact their RSMEs and indicated whether they were induced a substance. substances rated more intensely ( d...
We studied whether medical conditions across 21 broad categories were predictable from social media content approximately 20 million words written by 999 consenting patients. Facebook language significantly improved upon the prediction accuracy of demographic variables for 18 disease categories; it was particularly effective at predicting diabetes and mental health including anxiety, depression psychoses. Social data are a quantifiable link into otherwise elusive daily lives patients,...