scholarly journals Can the internet tell that you’re depressed? Machine learning of language use on Twitter reveals weak and non-specific predictions

2021 ◽  
Author(s):  
Sean Kelley ◽  
Caoimhe Ní Mhaonaigh ◽  
Louise Burke ◽  
Robert Whelan ◽  
Claire Gillan

Background: Depressed individuals use language differently than healthy controls and it has been proposed that social media posts could therefore be used to identify depression. But much of the evidence behind this claim relies on indirect measures of mental health that are sometimes circular, such as statements of self-diagnosis (“Got an OCD diagnosis today”) on social media or membership in disorder-specific online forums. Relatedly, few studies have tested if these language features are specific to depression versus other aspects of mental health. Methods: We analyzed the Tweets of 1,006 participants who completed questionnaires assessing symptoms of depression and 8 other mental health conditions. Daily Tweets were subjected to textual analysis and the resulting linguistic features were used to train an Elastic Net model on depression severity, using nested cross validation. We then tested performance in a held-out test set (30%), comparing predictions of depression versus 8 other aspects of mental health. Results: The depression trained model had only modest predictive performance when tested out of sample, explaining just 2.5% of variance in depression symptoms (R2 = 0.025). The performance of this model was as-good or superior when used to identify other aspects of mental health: schizotypy (R2 = 0.035), social anxiety (R2 = 0.025), eating disorders (R2 = 0.025), generalized anxiety (R2 = 0.041), above chance for obsessive-compulsive disorder (R2 = 0.011), apathy (R2 = 0.008), but not significant for alcohol abuse (R2 = -0.012).

2020 ◽  
Author(s):  
Alisa M. Loosen ◽  
Vasilisa Skvortsova ◽  
Tobias U. Hauser

AbstractBackgroundIncreased mental health problems as a reaction to stressful life events, such as the Covid-19 pandemic, are common. Critically, successful adaptation helps reduce such symptoms to baseline, preventing long-term psychiatric disorders. It is thus important to understand whether and which psychiatric symptoms only show transient elevations, and which persist long-term and become chronically heightened. At particular risk for the latter trajectory are disorders with symptoms directly affected by the pandemic, such as obsessive-compulsive disorder.MethodsIn this longitudinal large-scale study (N=416), we assessed how obsessive-compulsive (OC), anxiety, and depression symptoms changed throughout the course of the first pandemic wave in a sample of the general UK public. We further examined how these symptoms affected pandemic-related information seeking and adherence to governmental guidelines.FindingsAll psychiatric domains were initially elevated, but showed distinct adaptation patterns. Depression scores decreased during the first pandemic wave, however, OC symptoms further increased, even after the end of lockdown. These OC symptoms were directly linked to Covid-related information seeking which gave rise to higher adherence to government guidelines.InterpretationThe rise and persistence of OC symptoms, despite the ease of Covid-19 restrictions, shows that OCD is disproportionally and chronically affected by the pandemic. This is particularly worrying with regards to the long-term impact of the Covid-19 pandemic on public mental health and indicates that patients with OCD may require particular treatment efforts.


Medicina ◽  
2021 ◽  
Vol 57 (8) ◽  
pp. 793
Author(s):  
Laura Orsolini ◽  
Simone Pompili ◽  
Virginio Salvi ◽  
Umberto Volpe

Background and Objectives: The Internet is widely used and disseminated amongst youngsters and many web-based applications may serve to improve mental health care access, particularly in remote and distant sites or in settings where there is a shortage of mental health practitioners. However, in recent years, specific digital psychiatry interventions have been developed and implemented for special populations such as children and adolescents. Materials and Methods: Hereby, we describe the current state-of-the-art in the field of TMH application for young mental health, focusing on recent studies concerning anxiety, obsessive-compulsive disorder and affective disorders. Results: After screening and selection process, a total of 56 studies focusing on TMH applied to youth depression (n = 29), to only youth anxiety (n = 12) or mixed youth anxiety/depression (n = 7) and youth OCD (n = 8) were selected and retrieved. Conclusions: Telemental Health (TMH; i.e., the use of telecommunications and information technology to provide access to mental health assessment, diagnosis, intervention, consultation, supervision across distance) may offer an effective and efficacious tool to overcome many of the barriers encountering in the delivery of young mental health care.


2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Alisa M. Loosen ◽  
Vasilisa Skvortsova ◽  
Tobias U. Hauser

AbstractIncreased mental-health symptoms as a reaction to stressful life events, such as the Covid-19 pandemic, are common. Critically, successful adaptation helps to reduce such symptoms to baseline, preventing long-term psychiatric disorders. It is thus important to understand whether and which psychiatric symptoms show transient elevations, and which persist long-term and become chronically heightened. At particular risk for the latter trajectory are symptom dimensions directly affected by the pandemic, such as obsessive–compulsive (OC) symptoms. In this longitudinal large-scale study (N = 406), we assessed how OC, anxiety and depression symptoms changed throughout the first pandemic wave in a sample of the general UK public. We further examined how these symptoms affected pandemic-related information seeking and adherence to governmental guidelines. We show that scores in all psychiatric domains were initially elevated, but showed distinct longitudinal change patterns. Depression scores decreased, and anxiety plateaued during the first pandemic wave, while OC symptoms further increased, even after the ease of Covid-19 restrictions. These OC symptoms were directly linked to Covid-related information seeking, which gave rise to higher adherence to government guidelines. This increase of OC symptoms in this non-clinical sample shows that the domain is disproportionately affected by the pandemic. We discuss the long-term impact of the Covid-19 pandemic on public mental health, which calls for continued close observation of symptom development.


2002 ◽  
Vol 106 (2) ◽  
pp. 143-149 ◽  
Author(s):  
Renee Goodwin ◽  
Karestan C. Koenen ◽  
Fred Hellman ◽  
Mary Guardino ◽  
Elmer Struening

Author(s):  
Morgan E. Browning ◽  
Nathaniel P. Van Kirk ◽  
Jason W. Krompinger

Abstract Background: Obsessive compulsive disorder (OCD) and depression commonly co-occur. Past research has evaluated underlying mechanisms of depression in the context of other diagnoses, but few to no studies have done this within OCD. Aims: This study examines the relationships between distress tolerance (DT), experiential avoidance (EA), depression, and OCD symptom severity across intensive/residential treatment (IRT) for OCD. It was hypothesized that all variables would be significantly moderately related and EA would emerge as a potential contributing factor to change in depression and OCD symptoms across IRT for OCD. Method: The sample included 311 participants with a primary diagnosis of OCD seeking IRT. Correlations were performed between all variables at both admission and discharge. A two-step hierarchical regression with change in OCD symptoms and change in DT in the first block and change in EA in the second block examined if change in EA explained change in depression above and beyond change in OCD and DT ability. Results: At both admission and discharge, higher EA, lower DT, and higher OCD symptom severity were significantly associated with more depressive symptoms. Change in EA explained a significant amount of variance in change in depression above and beyond change in OCD symptom severity and change in DT. Conclusions: This study expands past results within an OCD sample, emphasizing EA as an important treatment target in OCD. Future studies could utilize samples from other treatment contexts, use a measure of EA specific to OCD, and utilize a longitudinal model that takes temporal precedence into account.


2020 ◽  
Vol 73 (1) ◽  
Author(s):  
Ananda Ughini Bertoldo Pires ◽  
Amália de Fátima Lucena ◽  
Andressa Behenck ◽  
Elizeth Heldt

ABSTRACT Objective: To analyze the application of nursing outcomes and indicators selected from the Nursing Outcomes Classification (NOC) to evaluate patients with obsessive-compulsive disorder (OCD) in outpatient follow-up. Method: Outcome-based research. First, a consensus was achieved between nurses specialized in mental health (MH) and in the nursing process to select NOC-related outcomes and indicators, followed by the elaboration of their conceptual and operational definitions. Then, an instrument was created with these, which was tested in a pilot group of six patients treated at a MH outpatient clinic. The instrument was applied to patients with OCD undergoing Group Cognitive Behavioral Therapy (GCBT). The study was approved by the Research Ethics Committee of the institution. Results: Four NOC outcomes and 17 indicators were selected. There was a significant change in the scores of nine indicators after CBGT. Conclusion: The study showed feasibility for evaluating symptoms of patients with OCD through NOC outcomes and indicators in an outpatient situation.


2021 ◽  
Vol 03 (03) ◽  
pp. 321-330
Author(s):  
Jafar Muhammad Aref JARADAT ◽  
Fawqia Muhammad Aref JARADAT

The study aimed at identifying the degree to which medical staff had psychological health in light of the spread of the Corona epidemic. The study sample consisted of (51) members of medical staff who is working in Palestinian health centers. The modified psychological health scale was adopted (SCL_90_R). The study came out with a set of results, the most important of which are: that there are no statistically significant differences in the averages of possessing the psychological health among medical staff according to the sex and age variables, it also showed the level of mental health was low, and that there was a high rate of acceptance on the mental health scale of the obsessive-compulsive disorder with a high arithmetic average. Whereas, the average was low at the psychotic dimension, which means that the respondents rejected psychotic characteristics in the psychological health scale. The study came out with a number of recommendations, the most important of which is activating the role of supporting programs and psychological immunization to deal with emergency conditions and crises.


2003 ◽  
Vol 48 (2) ◽  
pp. 72-77 ◽  
Author(s):  
Mario Masellis ◽  
Neil A Rector ◽  
Margaret A Richter

Objective: An anxiety disorder severely affects the sufferer's quality of life (QOL), and this may be particularly true of those with obsessive–compulsive disorder (OCD). This study examines the differential impact of obsessions, compulsions, and depression comorbidity on the QOL of individuals with OCD. Method: Forty-three individuals diagnosed with OCD according to DSM-IV criteria and experiencing clinically significant obsessions and compulsions completed measures of QOL, obsessive–compulsive symptom severity, and depression severity. Results: Obsession severity was found to significantly predict patient QOL, whereas the severity of compulsive rituals did not impact on QOL ratings. Comorbid depression severity was the single greatest predictor of poor QOL, accounting for 54% of the variance. Conclusions: Given the importance of these symptoms, treatments that directly target obsessions and secondary depression symptoms in OCD are warranted. However, replication of these findings in a prospective cohort study is required, because although the the current study's cross-sectional design allows for the examination of the associations among obsessions, depression, and QOL, it cannot establish their temporal framework (that is, causal relations).


2021 ◽  
Author(s):  
Christian Shaunlyn Chan ◽  
Takeshi Hamamura

PurposeSocial media are increasingly pivotal as the platform where activists and observers plan, promote, and respond to collective actions. To examine how mental health discourse might be impacted by mass protests, this study analyzed their time-dependent association during the 2019 anti-government social unrest in Hong Kong.MethodsConsecutive day-by-day user-generated content on online forums and social network sites (SNS) from June to November 2019 was obtained. A Cantonese term-list was created to identify terms related to mass protests and mental health discourse. The frequency of comments containing such terms was analyzed using time series models.ResultsThere were 3,572,665 social media comments in the investigation period. As hypothesized, the frequency of comments with mass protest terms was higher on days with mass protests than on days without. Frequency of comments with both mass protest- and mental health-terms was also higher on days with protests than days without. A time-lagged effect of protest-terms was found on online forums but not on SNS. Our results suggest a positive association between offline protest activities and online psychological reactions.ConclusionsSocial media content reveals discussion of mental health concerns stemming from, or exacerbated by, social unrest. The potential mutual influences between mass protests and online reactions, as well as the functional differences between online forums and SNS in this regard, are discussed. Street protests and their associated mental health discourse can be readily detected on popular online forums. Mental health services should consider such dynamic relationships between on- and offline activities.


Author(s):  
Monnica T. Williams

Abstract: This chapter discusses the research regarding microaggressions and negative mental health outcomes. Microaggressions are associated with increased stress, increased physical ailments such as hypertension and impaired immune responses, increased depression and depressive symptoms, lower self-esteem and self-efficacy, increased alcohol abuse and binge drinking, substance use disorders, increased post-traumatic stress disorder symptoms, higher levels of suicidal ideation, increased anxiety, increased somatic symptoms and negative affect, and increased obsessive–compulsive disorder symptoms. Overall, those who experience everyday discrimination have higher odds of any lifetime mental health issue. This is illustrated using a case example of a student who developed depression and anxiety from experiencing microaggressions in school, leading to a negative impact on mental health. The chapter presents an example interaction between a client and a therapist illustrating that microaggressions can be harmful to White people as well in indirect ways. Furthermore, to address mental health disparities and treatment barriers as a result of various pathways including microaggressions, clinicians need to address their own possible implicit biases that can lead to perpetuating these problems.


Sign in / Sign up

Export Citation Format

Share Document