scholarly journals The relationship between linguistic expression in blog content and symptoms of depression, anxiety, and suicidal thoughts: A longitudinal study

PLoS ONE ◽  
2021 ◽  
Vol 16 (5) ◽  
pp. e0251787
Author(s):  
Bridianne O’Dea ◽  
Tjeerd W. Boonstra ◽  
Mark E. Larsen ◽  
Thin Nguyen ◽  
Svetha Venkatesh ◽  
...  
Keyword(s):  
Social Media ◽  
Longitudinal Study ◽  
Depression And Anxiety ◽  
Linguistic Features ◽  
Suicidal Thoughts ◽  
Subject Analysis ◽  
Symptoms Of Depression ◽  
Final Sample ◽  
Social Media Platforms ◽  
Within Subjects

Data generated within social media platforms may present a new way to identify individuals who are experiencing mental illness. This study aimed to investigate the associations between linguistic features in individuals’ blog data and their symptoms of depression, generalised anxiety, and suicidal ideation. Individuals who blogged were invited to participate in a longitudinal study in which they completed fortnightly symptom scales for depression and anxiety (PHQ-9, GAD-7) for a period of 36 weeks. Blog data published in the same period was also collected, and linguistic features were analysed using the LIWC tool. Bivariate and multivariate analyses were performed to investigate the correlations between the linguistic features and symptoms between subjects. Multivariate regression models were used to predict longitudinal changes in symptoms within subjects. A total of 153 participants consented to the study. The final sample consisted of the 38 participants who completed the required number of symptom scales and generated blog data during the study period. Between-subject analysis revealed that the linguistic features “tentativeness” and “non-fluencies” were significantly correlated with symptoms of depression and anxiety, but not suicidal thoughts. Within-subject analysis showed no robust correlations between linguistic features and changes in symptoms. The findings may provide evidence of a relationship between some linguistic features in social media data and mental health; however, the study was limited by missing data and other important considerations. The findings also suggest that linguistic features observed at the group level may not generalise to, or be useful for, detecting individual symptom change over time.

Risk Factors for Symptoms of Depression and Anxiety One Year Poststroke: A Longitudinal Study

2016 ◽  
Vol 97 (6) ◽  
pp. 919-928 ◽  
Author(s):  
Joyce A. Kootker ◽  
Maria L. van Mierlo ◽  
Jan C. Hendriks ◽  
Judith Sparidans ◽  
Sascha M. Rasquin ◽  
...  
Keyword(s):  
Risk Factors ◽  
Longitudinal Study ◽  
Depression And Anxiety ◽  
Symptoms Of Depression ◽  
One Year

scholarly journals Exploring the Utility of Community-Generated Social Media Content for Detecting Depression: An Analytical Study on Instagram (Preprint)

2018 ◽  
Author(s):  
Benjamin J Ricard ◽  
Lisa A Marsch ◽  
Benjamin Crosier ◽  
Saeed Hassanpour
Keyword(s):  
Social Media ◽  
Mental Illness ◽  
Population Level ◽  
Predictive Analysis ◽  
Linguistic Features ◽  
Test Set ◽  
Intervention Delivery ◽  
Patient Health ◽  
Social Media Platforms ◽  
The Individual

BACKGROUND The content produced by individuals on various social media platforms has been successfully used to identify mental illness, including depression. However, most of the previous work in this area has focused on user-generated content, that is, content created by the individual, such as an individual’s posts and pictures. In this study, we explored the predictive capability of community-generated content, that is, the data generated by a community of friends or followers, rather than by a sole individual, to identify depression among social media users. OBJECTIVE The objective of this research was to evaluate the utility of community-generated content on social media, such as comments on an individual’s posts, to predict depression as defined by the clinically validated Patient Health Questionnaire-8 (PHQ-8) assessment questionnaire. We hypothesized that the results of this research may provide new insights into next generation of population-level mental illness risk assessment and intervention delivery. METHODS We created a Web-based survey on a crowdsourcing platform through which participants granted access to their Instagram profiles as well as provided their responses to PHQ-8 as a reference standard for depression status. After data quality assurance and postprocessing, the study analyzed the data of 749 participants. To build our predictive model, linguistic features were extracted from Instagram post captions and comments, including multiple sentiment scores, emoji sentiment analysis results, and meta-variables such as the number of likes and average comment length. In this study, 10.4% (78/749) of the data were held out as a test set. The remaining 89.6% (671/749) of the data were used to train an elastic-net regularized linear regression model to predict PHQ-8 scores. We compared different versions of this model (ie, a model trained on only user-generated data, a model trained on only community-generated data, and a model trained on the combination of both types of data) on a test set to explore the utility of community-generated data in our predictive analysis. RESULTS The 2 models, the first trained on only community-generated data (area under curve [AUC]=0.71) and the second trained on a combination of user-generated and community-generated data (AUC=0.72), had statistically significant performances for predicting depression based on the Mann-Whitney U test (P=.03 and P=.02, respectively). The model trained on only user-generated data (AUC=0.63; P=.11) did not achieve statistically significant results. The coefficients of the models revealed that our combined data classifier effectively amalgamated both user-generated and community-generated data and that the 2 feature sets were complementary and contained nonoverlapping information in our predictive analysis. CONCLUSIONS The results presented in this study indicate that leveraging community-generated data from social media, in addition to user-generated data, can be informative for predicting depression among social media users.

scholarly journals The endowment effect in Chinese social media platforms: Existence, size, and associations with personality and social media use

2021 ◽  
Author(s):  
Cornelia Sindermann ◽  
Haibo Yang ◽  
Shixin Yang ◽  
Jon D. Elhai ◽  
Christian Montag
Keyword(s):  
Social Media ◽  
Individual Differences ◽  
Big Five ◽  
Endowment Effect ◽  
Design Studies ◽  
Social Media Addiction ◽  
Two Samples ◽  
Social Media Platforms ◽  
Within Subjects ◽  
Chinese Social Media

The present studies followed the aim to investigate the endowment effects for prominent Chinese social media platforms in between-groups and within-subjects design studies. For between-groups investigations, two samples (each: N = 196; n = 98 men) asked either forwillingness to accept (WTA) or willingness to pay (WTP) for WeChat and two samples (each: N = 182; n = 91 men) providing information on either WTA or WTP for QQ were recruited. For within-subjects investigations, N = 250 (n = 125 men; WeChat) and N = 256 (n = 128 men; QQ) individuals completed items on WTA, WTP, the Big Five Inventory, time spent on WeChat/QQ, and the short Bergen Social Media Addiction Scale. WTA/WTP disparities in the between-groups design were larger than those in the within-subjects design. Many individuals were not willing to pay anything or barely anything. Individual differences in the disparity were negatively associated with Openness across platforms. Especially the low WTP scores reveal important knowledge on the (lack of) acceptance of a monetary payment model currently discussed for social media platforms.

Governance of Voice in Digital Platforms

2020 ◽  
Vol 31 ◽  
pp. 24-36
Author(s):  
Hussein Fadlallah ◽  
Robert A. Phillips ◽  
Keyword(s):  
Social Media ◽  
Longitudinal Study ◽  
Private Firms ◽  
Digital Platforms ◽  
Social Media Platform ◽  
Governance Tools ◽  
Social Media Platforms ◽  
Media Platform ◽  
Marginalized Community

We study the governance of voice in digital platforms in light of contestations and struggles over meaning and resources among their stakeholders. In particular, we argue that social media platforms as fields are subject to power imbalances that might constrain the voices of marginalized and under-represented individuals and groups. Consequently, the governance decisions that private firms (i.e. platform owners) undertake are critical in providing users and communities with the capacity to self-present and identify. Through a qualitative longitudinal study of a popular social media platform, we study the means through which a marginalized community leverages the governance tools at its disposal to overcome the contestation within the platform. We present implications for the governance of digital platforms and their evolution.

Characterization of depression in Spanish tweets: a behavioral and linguistic analysis (Preprint)

2019 ◽  
Author(s):  
Angela Leis ◽  
Francesco Ronzano ◽  
Miguel A. Mayer ◽  
Laura I. Furlong ◽  
Ferran Sanz
Keyword(s):  
Social Media ◽  
Mental Disorders ◽  
Healthcare Services ◽  
Linguistic Features ◽  
Second Person ◽  
Daily Lives ◽  
Control Dataset ◽  
Social Media Platforms ◽  
Twitter Users ◽  
Selection Of

BACKGROUND Mental disorders have become a major concern in public health and are one of the main causes of the overall disease burden worldwide. Social media platforms allow us to observe the activities, thoughts and feelings of people’s daily lives, including those of patients suffering from mental disorders. There are studies that have analyzed the influence of mental disorders, including depression, in the behavior of social media users, but they have been usually focused on messages written in English. OBJECTIVE The aim of this study is to identify the linguistic features of tweets in Spanish and the behavioral patterns of Twitter users that generate them, which could suggest signs of depression. METHODS This study was developed in two steps. In the first step, the selection of users and the compilation of tweets were performed. Three datasets of tweets were created, a depressive users dataset (made up of the timeline of 90 users who explicitly mention that they suffer from depression), a depressive tweets dataset (a manually curated selection of tweets from the previous users that include expressions indicative of depression) and a control dataset (made up of the timeline of 450 randomly selected users). In the second step, the comparison and analysis of the three datasets of tweets were carried out. RESULTS In comparison to the control dataset, the depressive users are less active in posting tweets, doing it more frequently between 23:00 and 6:00 (P<.001). The percentage of nouns used by the control dataset almost doubles that of the depressive users (P<.001). By contrast, the use of verbs is more common in the depressive users dataset (P<.001). The first-person singular pronoun was by far the most used in the depressive users dataset (80%) and the first and the second person plural were the less frequent (0.4% in both cases), being this distribution different to that of the control dataset (P<.001). Sadness and anger emotions were the most common in the depressive users and depressive tweets datasets with significant differences when comparing these datasets with the control one (P<.001). As for negation words, they were detected in the 34% and 46% of the tweets in the depressive users and depressive tweets respectively, which are significantly different to the control dataset (P<.001). Negative polarity was more frequent in the depressive users (54%) and depressive tweets (65%) datasets than in the control one (43.5%) (P<.001). CONCLUSIONS Twitter users who are potentially suffering from depression modify the general characteristics of their language and the way they interact on social media. Based on these changes these users can be monitored and supported, thus introducing new opportunities for the study of depression and for providing additional healthcare services to people with this disorder.

P4-378: A MULTI-DOMAIN VIRTUAL COGNITIVE HEALTH PROGRAM REDUCES SYMPTOMS OF DEPRESSION AND ANXIETY: SIX-MONTH RESULTS FROM A SINGLE-ARM LONGITUDINAL STUDY

2006 ◽  
Vol 14 (7S_Part_31) ◽  
pp. P1618-P1619
Author(s):  
Nicholas T. Bott ◽  
Shefali Kumar ◽  
Heidi Moseson ◽  
Jaspreet Uppal ◽  
Jennifer Tran ◽  
...  
Keyword(s):  
Longitudinal Study ◽  
Health Program ◽  
Depression And Anxiety ◽  
Cognitive Health ◽  
Symptoms Of Depression

scholarly journals Alcohol use among Norwegian students

2017 ◽  
Vol 34 (5) ◽  
pp. 415-429 ◽  
Author(s):  
Eilin K. Erevik ◽  
Ståle Pallesen ◽  
Øystein Vedaa ◽  
Cecilie S. Andreassen ◽  
Torbjørn Torsheim
Keyword(s):  
Alcohol Use ◽  
Binge Drinking ◽  
Psychological Health ◽  
Drinking Patterns ◽  
Depression And Anxiety ◽  
Symptoms Of Depression ◽  
Final Sample ◽  
Audit Score ◽  
Disorder Identification

Aims: This study investigates demographic, personality, and psychological health correlates of different drinking patterns. Design: Students at the four largest institutions of higher education in Bergen municipality were invited via email to complete an internet-based questionnaire. The final sample size was 11,236 (39.4%), mean age 24.9 years ( SD = 6.5), and 63.3% were women. The survey included the Alcohol Use Disorder Identification Test (AUDIT) and questions about demographics, personality traits, and symptoms of depression and anxiety. Binary logistic regressions were used to identify correlates of different drinking patterns. Results: A total of 53.0% of the students had an AUDIT score of or above 8 (i.e., hazardous drinking). Being native Norwegian, male, single, without children, non-religious, extroverted, unconscientious, and less open to experience were associated with higher AUDIT scores, drinking frequently, and binge drinking. Having parents with high alcohol or drug use increased the odds of engaging in binge drinking, but this factor was not associated with frequent drinking. Students scoring higher on neuroticism and openness were less likely to report problematic alcohol usage. Conclusions: A majority of the students reported alcohol habits that are associated with harm if they persist. This emphasises the need to examine the long-term consequences of students’ alcohol use.

scholarly journals We grow by Retweeting and Following: Examining the Pro-Eating Disorders community on Twitter via #Proana (Preprint)

2020 ◽  
Author(s):  
Suku SUKUNESAN
Keyword(s):  
Social Media ◽  
Eating Disorders ◽  
Online Community ◽  
Weight Control ◽  
Linear Models ◽  
Reciprocal Effect ◽  
Final Sample ◽  
Social Media Platforms ◽  
Twitter Users ◽  
Over Time

BACKGROUND There is increasing concern around communities which promote eating disorders (Pro-ED) on social media sites through messages and images which encourage dangerous weight control behaviours. These communities share group identity formed through interactions between members and can involve the exchange of ‘tips’, restrictive dieting plans, extreme exercise plans and motivating imagery of thin bodies. Unlike Instagram, Facebook or Tumblr, the absence of adequate policy to moderate Pro-ED content on Twitter presents a unique space Pro-ED community to freely communicate. While recent research have identified terms, themes and common lexicon used within the Pro-ED online community very few have been longitudinal. It is important to focus upon the engagement of Pro-ED online communities over time to further understand how members interact and stay connected, which is currently lacking. OBJECTIVE The purpose of this study was to explore beyond the common messages of Pro-ED on Twitter to understand how Pro-ED communities get traction over time by using the hashtag considered to symbolise the Pro-ED movement, #proana. Our focus was to collect longitudinal data to gain further understanding on the engagement of Pro-ED communities on Twitter. METHODS Descriptive statistics were used to identify the preferred tweeting style of Twitter users (either as mentioning another user in a tweet, or as an individual tweet to oneself, commonly referred to as ‘self-directed’) as well as their most frequently used hashtag, in addition to #proana. A series of Mann Whitney U tests were then conducted to compare preferred posting style across number of followed, followers, tweets and favourites. This was followed by Linear models using a forward step-wise approach, were applied for Pro-ED Twitter users to examine the factors associated with their number of followers. RESULTS This study consisted of 11,620 Pro-ED Twitter accounts who posted using the hashtag #proana between September 2015 and July 2018. These profiles then underwent before a two-step inclusion / exclusion criteria screen to reach the final sample of 967 profiles. Over 90% (10,484) of the profiles were found to have less than 6 tweets within the 34 months period. Most of the users were identified as preferring a mentioning style of tweeting (74.3%) over self-directed styles (25.7%). Further, #proana and #thinspo were used interchangeably to propagate shared themes and there was a reciprocal effect between followers and followed. CONCLUSIONS Our analysis showed that the number of accounts followed and number of Pro-ED tweets posted were significant predictors for the number of followers a user compared to likes. Our results could potentially be useful to social media platforms to understand which features could help or otherwise in curtailing spread of ED messages and activity. Our findings also show that Pro-ED communities are transient in nature engaging in superficial discussion threads but resilient, emulating cybersectarian behaviour.

Sign in / Sign up

Export Citation Format

Share Document