Search

Abstract In the most comprehensive population surveys, mental health is only broadly captured through questionnaires asking about “mentally unhealthy days” or feelings of “sadness.” Further, population mental health estimates are predominantly consolidated to yearly estimates at the state level, which is considerably coarser than the best estimates of physical health. Through the large-scale analysis of social media, robust estimation of population mental health is feasible at finer resolutions. In this study, we created a pipeline that used ~1 billion Tweets from 2 million geo-located users to estimate mental health levels and changes for depression and anxiety, the two leading mental health conditions. Language-based mental health assessments (LBMHAs) had substantially higher levels of reliability across space and time than available survey measures. This work presents reliable assessments of depression and anxiety down to the county-weeks level. Where surveys were available, we found moderate to strong associations between the LBMHAs and survey scores for multiple levels of granularity, from the national level down to weekly county measurements (fixed effects β = 0.34 to 1.82; p

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 such applications is mounting in the field as well as industry. These developments promise to address insufficient mental healthcare system capacity and scale individual access to personalized treatments. However, clinical psychology is an uncommonly high stakes application domain for AI systems, as responsible and evidence-based therapy requires nuanced expertise. This paper provides a roadmap for the ambitious yet responsible application of clinical LLMs in psychotherapy. First, a technical overview of clinical LLMs is presented. Second, the stages of integration of LLMs into psychotherapy are discussed while highlighting parallels to the development of autonomous vehicle technology. Third, potential applications of LLMs in clinical care, training, and research are discussed, highlighting areas of risk given the complex nature of psychotherapy. Fourth, recommendations for the responsible development and evaluation of clinical LLMs are provided, which include centering clinical science, involving robust interdisciplinary collaboration, and attending to issues like assessment, risk detection, transparency, and bias. Lastly, a vision is outlined for how LLMs might enable a new generation of studies of evidence-based interventions at scale, and how these studies may challenge assumptions about psychotherapy.

Abstract The Cantril Ladder is among the most widely administered subjective well-being measures; every year, it is collected in 140+ countries in the Gallup World Poll and reported in the World Happiness Report. The measure asks respondents to evaluate their lives on a ladder from worst (bottom) to best (top). Prior work found Cantril Ladder scores sensitive to social comparison and to reflect one’s relative position in the income distribution. To understand this, we explored how respondents interpret the Cantril Ladder. We analyzed word responses from 1581 UK adults and tested the impact of the (a) ladder imagery, (b) scale anchors of worst to best possible life, and c) bottom to top. Using three language analysis techniques (dictionary, topic, and word embeddings), we found that the Cantril Ladder framing emphasizes power and wealth over broader well-being and relationship concepts in comparison to the other study conditions. Further, altering the framings increased preferred scale levels from 8.4 to 8.9 (Cohen’s d = 0.36). Introducing harmony as an anchor yielded the strongest divergence from the Cantril Ladder, reducing mentions of power and wealth topics the most (Cohen’s d = −0.76). Our findings refine the understanding of historical Cantril Ladder data and may help guide the future evolution of well-being metrics and guidelines.

Trust is predictive of civic cooperation and economic growth. Recently, the U.S. public has demonstrated increased partisan division and a surveyed decline in trust in institutions. There is a need to quantify individual and community levels of trust unobtrusively and at scale. Using observations of language across more than 16,000 Facebook users, along with their self-reported generalized trust score, we develop and evaluate a language-based assessment of generalized trust. We then apply the assessment to more than 1.6 billion geotagged tweets collected between 2009 and 2015 and derive estimates of trust across 2,041 U.S. counties. We find generalized trust was associated with more affiliative words (love, we, and friends) and less angry words (hate and stupid) but only had a weak association with social words primarily driven by strong negative associations with general othering terms (“they” and “people”). At the county level, associations with the Centers for Disease Control and Prevention (CDC) and Gallup surveys suggest that people in high-trust counties were physically healthier and more satisfied with their community and their lives. Our study demonstrates that generalized trust levels can be estimated from language as a low-cost, unobtrusive method to monitor variations in trust in large populations.

Abstract Opioid poisoning mortality is a substantial public health crisis in the United States, with opioids involved in approximately 75% of the nearly 1 million drug related deaths since 1999. Research suggests that the epidemic is driven by both over-prescribing and social and psychological determinants such as economic stability, hopelessness, and isolation. Hindering this research is a lack of measurements of these social and psychological constructs at fine-grained spatial and temporal resolutions. To address this issue, we use a multi-modal data set consisting of natural language from Twitter, psychometric self-reports of depression and well-being, and traditional area-based measures of socio-demographics and health-related risk factors. Unlike previous work using social media data, we do not rely on opioid or substance related keywords to track community poisonings. Instead, we leverage a large, open vocabulary of thousands of words in order to fully characterize communities suffering from opioid poisoning, using a sample of 1.5 billion tweets from 6 million U.S. county mapped Twitter users. Results show that Twitter language predicted opioid poisoning mortality better than factors relating to socio-demographics, access to healthcare, physical pain, and psychological well-being. Additionally, risk factors revealed by the Twitter language analysis included negative emotions, discussions of long work hours, and boredom, whereas protective factors included resilience, travel/leisure, and positive emotions, dovetailing with results from the psychometric self-report data. The results show that natural language from public social media can be used as a surveillance tool for both predicting community opioid poisonings and understanding the dynamic social and psychological nature of the epidemic.

Introduction: Although surveys are a well-established instrument to capture the population prevalence of mental health at a moment in time, public Twitter is a continuously available data source that can provide a broader window into population mental health. We characterized the relationship between COVID-19 case counts, stay-at-home orders because of COVID-19, and anxiety and depression in 7 major U.S. cities utilizing Twitter data. Methods: We collected 18 million Tweets from January to September 2019 (baseline) and 2020 from 7 U.S. cities with large populations and varied COVID-19 response protocols: Atlanta, Chicago, Houston, Los Angeles, Miami, New York, and Phoenix. We applied machine learning‒based language prediction models for depression and anxiety validated in previous work with Twitter data. As an alternative public big data source, we explored Google Trends data using search query frequencies. A qualitative evaluation of trends is presented. Results: Twitter depression and anxiety scores were consistently elevated above their 2019 baselines across all the 7 locations. Twitter depression scores increased during the early phase of the pandemic, with a peak in early summer and a subsequent decline in late summer. The pattern of depression trends was aligned with national COVID-19 case trends rather than with trends in individual states. Anxiety was consistently and steadily elevated throughout the pandemic. Google search trends data showed noisy and inconsistent results. Conclusions: Our study shows the feasibility of using Twitter to capture trends of depression and anxiety during the COVID-19 public health crisis and suggests that social media data can supplement survey data to monitor long-term mental health trends.

BackgroundAn infodemic is excess information, including false or misleading information, that spreads in digital and physical environments during a public health emergency. The COVID-19 pandemic has been accompanied by an unprecedented global infodemic that has led to confusion about the benefits of medical and public health interventions, with substantial impact on risk-taking and health-seeking behaviors, eroding trust in health authorities and compromising the effectiveness of public health responses and policies. Standardized measures are needed to quantify the harmful impacts of the infodemic in a systematic and methodologically robust manner, as well as harmonizing highly divergent approaches currently explored for this purpose. This can serve as a foundation for a systematic, evidence-based approach to monitoring, identifying, and mitigating future infodemic harms in emergency preparedness and prevention. ObjectiveIn this paper, we summarize the Fifth World Health Organization (WHO) Infodemic Management Conference structure, proceedings, outcomes, and proposed actions seeking to identify the interdisciplinary approaches and frameworks needed to enable the measurement of the burden of infodemics. MethodsAn iterative human-centered design (HCD) approach and concept mapping were used to facilitate focused discussions and allow for the generation of actionable outcomes and recommendations. The discussions included 86 participants representing diverse scientific disciplines and health authorities from 28 countries across all WHO regions, along with observers from civil society and global public health–implementing partners. A thematic map capturing the concepts matching the key contributing factors to the public health burden of infodemics was used throughout the conference to frame and contextualize discussions. Five key areas for immediate action were identified. ResultsThe 5 key areas for the development of metrics to assess the burden of infodemics and associated interventions included (1) developing standardized definitions and ensuring the adoption thereof; (2) improving the map of concepts influencing the burden of infodemics; (3) conducting a review of evidence, tools, and data sources; (4) setting up a technical working group; and (5) addressing immediate priorities for postpandemic recovery and resilience building. The summary report consolidated group input toward a common vocabulary with standardized terms, concepts, study designs, measures, and tools to estimate the burden of infodemics and the effectiveness of infodemic management interventions. ConclusionsStandardizing measurement is the basis for documenting the burden of infodemics on health systems and population health during emergencies. Investment is needed into the development of practical, affordable, evidence-based, and systematic methods that are legally and ethically balanced for monitoring infodemics; generating diagnostics, infodemic insights, and recommendations; and developing interventions, action-oriented guidance, policies, support options, mechanisms, and tools for infodemic managers and emergency program managers.

Full national coverage below the state level is difficult to attain through survey-based data collection. Even the largest survey-based data collections, such as the CDC's Behavioral Risk Factor Surveillance System or the Gallup-Healthways Well-being Index (both with more than 300,000 responses p.a.) only allow for the estimation of annual averages for about 260 out of roughly U.S. 3,000 counties when a threshold of 300 responses per county is used. Using a relatively high threshold of 300 responses gives substantially higher convergent validity–higher correlations with health variables–than lower thresholds but covers a reduced and biased sample of the population. We present principled methods to interpolate spatial estimates and show that including large-scale geotagged social media data can increase interpolation accuracy. In this work, we focus on Gallup-reported life satisfaction, a widely-used measure of subjective well-being. We use Gaussian Processes (GP), a formal Bayesian model, to interpolate life satisfaction, which we optimally combine with estimates from low-count data. We interpolate over several spaces (geographic and socioeconomic) and extend these evaluations to the space created by variables encoding language frequencies of approximately 6 million geotagged Twitter users. We find that Twitter language use can serve as a rough aggregate measure of socioeconomic and cultural similarity, and improves upon estimates derived from a wide variety of socioeconomic, demographic, and geographic similarity measures. We show that applying Gaussian Processes to the limited Gallup data allows us to generate estimates for a much larger number of counties while maintaining the same level of convergent validity with external criteria (i.e., N = 1,133 vs. 2,954 counties). This work suggests that spatial coverage of psychological variables can be reliably extended through Bayesian techniques while maintaining out-of-sample prediction accuracy and that Twitter language adds important information about cultural similarity over and above traditional socio-demographic and geographic similarity measures. Finally, to facilitate the adoption of these methods, we have also open-sourced an online tool that researchers can freely use to interpolate their data across geographies.

We studied whether medical conditions across 21 broad categories were predictable from social media content across approximately 20 million words written by 999 consenting patients. Facebook language significantly improved upon the prediction accuracy of demographic variables for 18 of the 21 disease categories; it was particularly effective at predicting diabetes and mental health conditions including anxiety, depression and psychoses. Social media data are a quantifiable link into the otherwise elusive daily lives of patients, providing an avenue for study and assessment of behavioral and environmental disease risk factors. Analogous to the genome, social media data linked to medical diagnoses can be banked with patients' consent, and an encoding of social media language can be used as markers of disease risk, serve as a screening tool, and elucidate disease epidemiology. In what we believe to be the first report linking electronic medical record data with social media data from consenting patients, we identified that patients' Facebook status updates can predict many health conditions, suggesting opportunities to use social media data to determine disease onset or exacerbation and to conduct social media-based health interventions.

Advances in biotechnology and information technology are poised to transform well-being research. This article reviews the technologies that we predict will have the most impact on both measurement and intervention in the field of positive psychology over the next decade. These technologies include: psychopharmacology, non-invasive brain stimulation, virtual reality environments, and big-data methods for large-scale multivariate analysis. Some particularly relevant potential costs and benefits to individual and collective well-being are considered for each technology as well as ethical considerations. As these technologies may substantially enhance the capacity of psychologists to intervene on and measure well-being, now is the time to discuss the potential promise and pitfalls of these technologies.

Fluctuations in mood states are driven by unpredictable outcomes in daily life but also appear to drive consequential behaviors such as risk-taking. However, our understanding of the relationships between unexpected outcomes, mood, and risk-taking behavior has relied primarily upon constrained and artificial laboratory settings. Here we examine, using naturalistic datasets, how real-world unexpected outcomes predict mood state changes observable at the level of a city, in turn predicting changes in gambling behavior. By analyzing day-to-day mood language extracted from 5.2 million location-specific and public Twitter posts or 'tweets', we examine how real-world 'prediction errors'-local outcomes that deviate positively from expectations-predict day-to-day mood states observable at the level of a city. These mood states in turn predicted increased per-person lottery gambling rates, revealing how interplay between prediction errors, moods, and risky decision-making unfolds in the real world. Our results underscore how social media and naturalistic datasets can uniquely allow us to understand consequential psychological phenomena.