Dataset Information

Exploring the Utility of Community-Generated Social Media Content for Detecting Depression: An Analytical Study on Instagram.

ABSTRACT:

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.

SUBMITTER: Ricard BJ

PROVIDER: S-EPMC6302231 | biostudies-literature | 2018 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Exploring the Utility of Community-Generated Social Media Content for Detecting Depression: An Analytical Study on Instagram.

Ricard Benjamin J BJ Marsch Lisa A LA Crosier Benjamin B Hassanpour Saeed S

Journal of medical Internet research 20181206 12

<h4>Background</h4>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 ...[more]

PMID: 30522991

Similar Datasets

Project description:BackgroundThe human papillomavirus (HPV) vaccine is a major advancement in cancer prevention and this primary prevention tool has the potential to reduce and eliminate HPV-associated cancers; however, the safety and efficacy of vaccines in general and the HPV vaccine specifically have come under attack, particularly through the spread of misinformation on social media. The popular social media platform Instagram represents a significant source of exposure to health (mis)information; 1 in 3 US adults use Instagram.ObjectiveThe objective of this analysis was to characterize pro- and anti-HPV vaccine networks on Instagram, and to describe misinformation within the anti-HPV vaccine network.MethodsFrom April 2018 to December 2018, we collected publicly available English-language Instagram posts containing hashtags #HPV, #HPVVaccine, or #Gardasil using Netlytic software (n=16,607). We randomly selected 10% of the sample and content analyzed relevant posts (n=580) for text, image, and social media features as well as holistic attributes (eg, sentiments, personal stories). Among antivaccine posts, we organized elements of misinformation within four broad dimensions: 1) misinformation theoretical domains, 2) vaccine debate topics, 3) evidence base, and 4) health beliefs. We conducted univariate, bivariate, and network analyses on the subsample of posts to quantify the role and position of individual posts in the network.ResultsCompared to provaccine posts (324/580, 55.9%), antivaccine posts (256/580, 44.1%) were more likely to originate from individuals (64.1% antivaccine vs 25.0% provaccine; P<.001) and include personal narratives (37.1% vs 25.6%; P=.003). In the antivaccine network, core misinformation characteristics included mentioning #Gardasil, purporting to reveal a lie (ie, concealment), conspiracy theories, unsubstantiated claims, and risk of vaccine injury. Information/resource posts clustered around misinformation domains including falsification, nanopublications, and vaccine-preventable disease, whereas personal narrative posts clustered around different domains of misinformation, including concealment, injury, and conspiracy theories. The most liked post (6634 likes) in our full subsample was a positive personal narrative post, created by a non-health individual; the most liked post (5604 likes) in our antivaccine subsample was an informational post created by a health individual.ConclusionsIdentifying characteristics of misinformation related to HPV vaccine on social media will inform targeted interventions (eg, network opinion leaders) and help sow corrective information and stories tailored to different falsehoods.

Project description:BackgroundAlthough organ transplantation is a very effective clinical solution to save the lives of patients suffering from organ failure, the supply of donated organs still cannot meet its growing demand. Educating the society about organ donation is a critical success factor in increasing donation rates, especially in countries that require potential donors to proactively register and opt-in (e.g., Germany). While social media has emerged as an effective tool for disseminating health information, recent evidence suggests that published organ donation content (both online and offline), aimed at raising awareness, still lacks effectiveness. To develop recommendations for optimizing organ donation messaging via social media, this study not only examines the current state of organ donation communication on Instagram, but also identifies factors that contribute to message effectiveness.MethodsWe conducted a retrospective content analysis to in-depth assess organ donation-related content published on Instagram in Germany between January and March 2022. Systematic coding allowed to identify common themes, sentiments, and communication strategies, which were analyzed for their effectiveness using linear regression analyses.ResultsOf the 500 organ donation posts, 57% were published by institutional authors while the remainder was shared by private accounts. Most content was aimed at the general population and shared neutral (80%) or positive sentiments (17%). Transformative messages, positive emotions, posts published by the transplant recipient and the image of a human served as predictors for post effectiveness measured in terms of likes (p < 0.001) and comments (p < 0.01). Sharing personal experiences (p < 0.01) and highlighting the meaning of organ donations (p < 0.05) resulted in significantly higher audience engagement than any other topic discussed.ConclusionOur findings highlight the need for health officials to work closely with organ transplant recipients to publicly advocate for organ donations by sharing personal and transformative messages. The high share of posts published by transplant recipients indicates a certain openness to share personal experiences with broad audiences. Different message characteristics served as predictors for message effectiveness (i.e., increased audience engagement) which can likely be extrapolated to other health-related use cases (e.g., cancer screening).

Project description:BackgroundThe popularization of social media has led to the coalescing of user groups around mental health conditions; in particular, depression. Social media offers a rich environment for contextualizing and predicting users' self-reported burden of depression. Modern artificial intelligence (AI) methods are commonly employed in analyzing user-generated sentiment on social media. In the forthcoming systematic review, we will examine the content validity of these computer-based health surveillance models with respect to standard diagnostic frameworks. Drawing from a clinical perspective, we will attempt to establish a normative judgment about the strengths of these modern AI applications in the detection of depression.MethodsWe will perform a systematic review of English and German language publications from 2010 to 2020 in PubMed, APA PsychInfo, Science Direct, EMBASE Psych, Google Scholar, and Web of Science. The inclusion criteria span cohort, case-control, cross-sectional studies, randomized controlled studies, in addition to reports on conference proceedings. The systematic review will exclude some gray source materials, specifically editorials, newspaper articles, and blog posts. Our primary outcome is self-reported depression, as expressed on social media. Secondary outcomes will be the types of AI methods used for social media depression screen, and the clinical validation procedures accompanying these methods. In a second step, we will utilize the evidence-strengthening Population, Intervention, Comparison, Outcomes, Study type (PICOS) tool to refine our inclusion and exclusion criteria. Following the independent assessment of the evidence sources by two authors for the risk of bias, the data extraction process will culminate in a thematic synthesis of reviewed studies.DiscussionWe present the protocol for a systematic review which will consider all existing literature from peer reviewed publication sources relevant to the primary and secondary outcomes. The completed review will discuss depression as a self-reported health outcome in social media material. We will examine the computational methods, including AI and machine learning techniques which are commonly used for online depression surveillance. Furthermore, we will focus on standard clinical assessments, as indicating content validity, in the design of the algorithms. The methodological quality of the clinical construct of the algorithms will be evaluated with the COnsensus-based Standards for the selection of health status Measurement Instruments (COSMIN) framework. We conclude the study with a normative judgment about the current application of AI to screen for depression on social media.Systematic review registrationInternational Prospective Register of Systematic Reviews PROSPERO (registration number CRD42020187874).

Dataset Information

Exploring the Utility of Community-Generated Social Media Content for Detecting Depression: An Analytical Study on Instagram.

Background

Objective

Methods

Results

Conclusions

Publications

Exploring the Utility of Community-Generated Social Media Content for Detecting Depression: An Analytical Study on Instagram.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets