Measuring attitudes towards mental health using social media: investigating stigma and trivialisation

Robinson, P.Brett; Turk, Daniel; Jilka, Sagar; Cella, Matteo

doi:10.1007/s00127-018-1571-5

Cited by 163 publications

(124 citation statements)

References 24 publications

Supporting

Mentioning

104

Contrasting

Order By: Relevance

“…Methodologically speaking, a key novelty of our work is that it reduces the need to incorporate extensive expert coded qualitative data for the purpose-an approach widely prevalent this far [22,24] -by making principled use of machine learning and access to vast amounts of unlabeled social media data. Nevertheless, using semi-supervised machine learning methods, the 0.64 mean accuracy of our methods reflects the challenges of quantifying the heterogeneity of mental health content.…”

Section: Discussionmentioning

confidence: 99%

“…Relating to the potential of social media as a platform to improve mental health literacy, recent studies suggest that people use Twitter to discuss mental health to build community, raise awareness, have a safe place to express themselves and discuss personal struggles, serve as a coping mechanism, get peer advice and help, and appropriate it as a tool toward empowerment [22]. In fact, it has been argued that the diverse communities on social media help to make mental illnesses, which are often invisible to friends and family, visible through postings, photos, and videos [16,23], and thereby can support altering perceptions of stigma [24]. But there is also evidence that mental health stigma has migrated online and some Twitter posts are inappropriate and condescending toward those with mental health conditions [25].…”

Section: Introductionmentioning

confidence: 99%

“…In addition, this work innovates over state of the art techniques to understand social media mental health content (e.g., see ref. [24]) that largely focuses on qualitative characterization and categorization of mental health awareness content on social media, requiring extensive effort-and time-consuming feedback from domain experts.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A computational study of mental health awareness campaigns on social media

Saha

Torous

Ernala

et al. 2019

Translational Behavioral Medicine

View full text Add to dashboard Cite

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A computational study of mental health awareness campaigns on social media

Saha

Torous

Ernala

et al. 2019

Translational Behavioral Medicine

View full text Add to dashboard Cite

show abstract

“…Benefits include the accessibility to useful tools and resources for mental health diagnosis and treatment, like the one presented in this very paper. Risks involve very negative mental health outcomes such as an increase in suicidal ideation [20] and the exacerbation of mental illness stigma [21].…”

Section: Introductionmentioning

confidence: 99%

Perla: A Conversational Agent for Depression Screening in Digital Ecosystems. Design, Implementation and Validation

Arrabales¹

2020

Preprint

View full text Add to dashboard Cite

Most depression assessment tools are based on self-report questionnaires, such as the Patient Health Questionnaire (PHQ-9). These psychometric instruments can be easily adapted to an online setting by means of electronic forms. However, this approach lacks the interacting and engaging features of modern digital environments. With the aim of making depression screening more available, attractive and effective, we developed Perla, a conversational agent able to perform an interview based on the PHQ-9. We also conducted a validation study in which we compared the results obtained by the traditional self-report questionnaire with Perla’s automated interview. Analyzing the results from this study we draw two significant conclusions: firstly, Perla is much preferred by Internet users, achieving more than 2.5 times more reach than a traditional form-based questionnaire; secondly, her psychometric properties (Cronbach's alpha of 0.81, sensitivity of 96% and specificity of 90%) are excellent and comparable to the traditional well-established depression screening questionnaires.

show abstract

“…In recent years, Online Social Networks (OSN) has become an increasingly popular approach for analyzing stigma and associated attitudes [22][23][24]. OSN (e.g., Weibo, Twitter) provides chances to comprehensively understand the psychological state of participants in a non-invasive way [25].…”

Section: Introductionmentioning

confidence: 99%

Stigma Towards Wuhan People During the COVID-19 Epidemic: An Exploratory Study Based on Social Media

et al. 2020

Preprint

View full text Add to dashboard Cite

Background: Stigma associated with infectious diseases is common and causes various negative effects on stigmatized people. With Wuhan as the center of the COVID-19 outbreak in China, its people have become an object of stigmatization. To provide necessary information for stigma mitigation, this study aims to identify the stigmatizing attitudes towards Wuhan people and trace their changes as the COVID-19 progressed in China by analyzing related posts on social media.Methods: We collected a total of 19,780 Weibo posts containing the keyword ‘Wuhan people’ and performed a content analysis to identify stigmatizing attitudes in the posts. Then we divided our observation time into three periods and performed Repeated Measures ANOVA to compare the differences in attitudes in three periods. Results: Results show that stigma was mild with 2.46% of related posts being stigmatizing. The percentages of stigmatizing posts differed significantly in 3 periods (F (2,66) = 5.60, p <.01, η2= 0.15). The percentages of ‘Infectious’ posts (F (2,66) = 3.69, p <.05, η2 = 0.10) and ‘Stupid’ posts (F (2,66) = 3.65, p <.05, η2 = 0.10) are significantly different in 3 periods. The percentages of ‘Irresponsible’ posts is not significant different in 3 periods (F (2,66) = 0.63, p =.53, η2 = 0.02). After government interventions, stigma didn’t reduce significantly, and stigma with ‘Infectious’ attitude even increased. It was until the government interventions took effect that stigma significantly reduced. Conclusions: This study found that stigma towards Wuhan people included diverse attitudes and changed at different periods. After government interventions but before they took effect, stigma with ‘Infectious’ attitude increased. After government interventions took effect, general stigma, and stigma with ‘Infectious’ and ‘Stupid’ attitudes decreased. This study constitutes an important endeavor to understand the stigma towards Wuhan people in China during the COVID-19 epidemic. Implications for stigma reduction and improvement of the public’s perception in different periods of epidemic control are discussed.

show abstract

Measuring attitudes towards mental health using social media: investigating stigma and trivialisation

Cited by 163 publications

References 24 publications

A computational study of mental health awareness campaigns on social media

A computational study of mental health awareness campaigns on social media

Perla: A Conversational Agent for Depression Screening in Digital Ecosystems. Design, Implementation and Validation

Stigma Towards Wuhan People During the COVID-19 Epidemic: An Exploratory Study Based on Social Media

Contact Info

Product

Resources

About