Leveraging Twitter Using Artificial Intelligence to Explore Mental Health Insights in the UK During the COVID-19 Pandemic (Preprint)

2021 ◽  
Author(s):  
Christopher Marshall ◽  
Kate Lanyi ◽  
Rhiannon Green ◽  
Georgie Wilkins ◽  
Fiona Pearson ◽  
...  

BACKGROUND There is increasing need to explore the value of soft-intelligence, leveraged using the latest artificial intelligence (AI) and natural language processing (NLP) techniques, as a source of analysed evidence to support public health research activity and decision-making. OBJECTIVE The aim of this study was to further explore the value of soft-intelligence analysed using AI through a case study, which examined a large collection of UK tweets relating to mental health during the COVID-19 pandemic. METHODS A search strategy comprising a list of terms related to mental health, COVID-19, and lockdown restrictions was developed to prospectively collate relevant tweets via Twitter’s advanced search application programming interface over a 24-week period. We deployed a specialist NLP platform to explore tweet frequency and sentiment across the UK and identify key topics of discussion. A series of keyword filters were used to clean the initial data retrieved and also set up to track specific mental health problems. Qualitative document analysis was carried out to further explore and expand upon the results generated by the NLP platform. All collated tweets were anonymised RESULTS We identified and analysed 286,902 tweets posted from UK user accounts from 23 July 2020 to 6 January 2021. The average sentiment score was 50%, suggesting overall neutral sentiment across all tweets over the study period. Major fluctuations in volume and sentiment appeared to coincide with key changes to any local and/or national social-distancing measures. Tweets around mental health were polarising, discussed with both positive and negative sentiment. Key topics of consistent discussion over the study period included the impact of the pandemic on people’s mental health (both positively and negatively), fear and anxiety over lockdowns, and anger and mistrust toward the government. CONCLUSIONS Through the primary use of an AI-based NLP platform, we were able to rapidly mine and analyse emerging health-related insights from UK tweets into how the pandemic may be impacting people’s mental health and well-being. This type of real-time analysed evidence could act as a useful intelligence source that agencies, local leaders, and health care decision makers can potentially draw from, particularly during a health crisis.

2020 ◽  
Author(s):  
Franziska Knolle ◽  
Lisa Ronan ◽  
Graham K Murray

In March 2020 the SARS-CoV-2infection (COVID-19) was declared a pandemic. In response to its world-wide outbreak radical measures were taken by governments across the world including curfew, quarantine, travel bans, social distancing, work place and school closures, etc, to reduce the transmission of the virus. These measures led to dramatic social and economic changes for the general population, in addition to the fears and worries related to the disease and its contraction. First studies report the impact of the pandemic on mental well-being of the general population showing increased levels of anxiety, stress and depression. In this study, we compare the impact of the pandemic on two European countries: the UK and Germany, which reported their first cases within a week. 241 residents of the UK and 541 residents of Germany filled in an online survey, including questions on COVID-19 exposure, impact on financial situation and work, substance and media consumption, self-reported mental and physical health, as well as including two clinical questionnaires, the general mental health Symptom Check List-27 (SCL-27) and the Schizotypal Personality Questionnaire. Data collection was completed between 27/04/20-31/05/20. We found distinct differences between the two countries. UK responders reported a stronger direct impact on their health, financial situation and their families. UK responders had higher clinical scores on the SCL-27, with a higher percentage being above cut-off. Interestingly, however, we found that German responders were less hopeful for an end of the pandemic and more concerned about their life-stability. Generally, we found that a younger age, being female, lower education, poorer mental and physical health before the pandemic, as well as more social media and substance consumption was associated with a higher clinical risk. This research shows strong differences between two economically and culturally similar countries, but as 25% of both German and UK responders reported a subjective worsening of the general psychological symptoms and 20-50% of German and UK responders reached the clinical cut-off for depressive, dysthymic and anxieties, it specifically shows the need for health emergency tailored intervention systems to assist not only people vulnerable for mental health problems, but also large proportions of the general public.


2021 ◽  
Vol 12 ◽  
Author(s):  
Gökmen Arslan ◽  
Murat Yıldırım ◽  
Mega M. Leung

Research Problem: The onset of the COVID-19 pandemic has triggered a multi-faceted crisis worldwide. Researchers and health authorities in various parts of the world echoed the dire condition of the public's mental health. This study sought to examine the mediating effect of personal meaning on the association between coronavirus (COVID-19)-related suffering, mental health problems, and life satisfaction. Participants included 231 adults (mean age = 46.65 ± 13.98; 68% female) and completed measures of suffering related to COVID-19, meaning, life satisfaction, and mental health problems online.Results: Findings from mediation analysis showed that suffering had significant associations with personal meaning, mental health, and well-being. Furthermore, personal meaning was significantly associated with adults' mental health and well-being and mediated the negative effect of suffering on mental health and well-being.Discussion: Overall, results from this study indicate that personal meaning is an important promotive factor that may help to understand the negative effect of coronavirus-related suffering on mental health and well-being amid the public health crisis.


2020 ◽  
Vol 42 (5) ◽  
pp. 421-427 ◽  
Author(s):  
Viswa Chaitanya Chandu ◽  
Yamuna Marella ◽  
Gnana Sarita Panga ◽  
Srinivas Pachava ◽  
Viswanath Vadapalli

Background: The coronavirus disease (COVID-19) pandemic, associated with the economic consequences of non-pharmaceutical interventions such as lockdown, has led to mental health consequences among people worldwide. Protecting the mental well-being of populations is an imperative component of fighting the COVID-19 pandemic. This scoping review attempts to present an overview of the existing tools to measure COVID-19-related mental health problems. Methods: Literature search was conducted in the PubMed electronic database using developed key search terms. Reference lists of the identified eligible articles were reviewed to locate relevant articles missed from the electronic database search. Fifteen scales measuring COVID-19-associated mental health problems, validated among diverse populations across the world, were included in this review. Results: The majority of these scales were validated among middle-aged adults in Turkey. Only a few validated scales encompass the negative socioeconomic consequences of COVID-19. None of the available scales focused on the aspects of suicidal ideation or behavioral responses/coping strategies, neither were they inclusive of participants from diverse age, geographic, and COVID-19 exposure groups. Conclusion: This scoping review highlights the need for future research to develop and validate comprehensive psychometric tools to assess COVID-19-associated mental health problems. Also, in view of the vulnerable nature of healthcare professionals for developing mental health concerns in the course of providing services for COVID-19-affected individuals, future psychometric research needs to concentrate on the development of measures specific for these professionals.


2014 ◽  
Vol 22 (2) ◽  
pp. 62-70 ◽  
Author(s):  
Ailsa Cameron ◽  
Lisa Bostock ◽  
Rachel Lart

Purpose – The purpose of this paper is to provide an update to a review of the joint working literature in the field of health and social care for adults, with particular emphasis given to the experiences of users and carers. Design/methodology/approach – The aims of the literature review remained largely the same as those of the original, they were to identify: models of joint working, evidence of effectiveness and cost-effectiveness and the factors promoting or hindering the models. However, to reflect the growing interest in the experiences of users and carers a fourth aim was added to map these experiences. Given their prominence in terms of policy debates about integration, the review focused on jointly organised services for older people and people with mental health problems in the UK only. Findings – The review demonstrates tentative signs that some initiatives designed to join-up or integrate services can deliver outcomes desired by government. Importantly some studies that report the experiences of users of services and carers suggest that they perceive benefits from efforts to join-up or integrate services. However it is our contention that the evidence is less than compelling and does not justify the faith invested in the strategy by current or previous governments. Originality/value – The study updates our knowledge of the impact of joint working in the field of health and social care for adults. Importantly the paper highlights what is known about the experiences of users and carers of joint/integrated services.


2020 ◽  
Author(s):  
Dirk Richter ◽  
Steffi Riedel-Heller ◽  
Simeon Zuercher

BackgroundThe SARS-Cov-2 pandemic and the lockdown response have increased mental health problems in general populations compared to pre-pandemic times. The course of mental health problems during and after the first lockdown phase has not yet been reviewed.MethodsWe conducted a rapid review of multi-wave studies in general populations with time points during and after the first lockdown phase. Repeated cross-sectional and longitudinal studies were included. The main outcome assessed was whether indicators of mental health problems have changed during and after the first lockdown phase. The study was registered with PROSPERO No. CRD42020218640Findings23 studies with 56 indicators were included in the qualitative review. Studies that reported data from pre-pandemic assessments through lockdown indicated an increase in mental health problems. During lockdown no uniform trend could be identified. After lockdown mental health problems decreased slightly.InterpretationAs mental health care utilization indicators and data on suicides do not suggest an increase in demand during the first lockdown phase, we regard the increase in mental health problems as general distress that is to be expected during a global health crisis. Several methodological, pandemic-related, response-related and health policy-related factors need to be considered when trying to gain a broader perspective on the impact of the first wave of the pandemic and the first phase of lockdown on general populations’ mental health.


2021 ◽  
Author(s):  
Jen Murphy ◽  
Mark Elliot

Introduction: In March 2020 in response to the COVID pandemic the UK government declared a national lockdown where citizens were required to stay at home. The impact of this lockdown on levels of well-being has been a source of concern for citizens and mental health professionals.Objectives: We investigated the trajectory of well-being over the course of the ?first wave and sought to determine whether the change in well-being is distributed equally across the population. Speci?fically we investigated pre-existing medical conditions, social isolation, ?financial stress and deprivation as a predictor for well-being and whether there were community level characteristics which protect against poorer well-being.Methods: Using online survey responses from the COVID19 modules of Understanding society, we linked 8,379 English cases across ?five waves of data collection to location based deprivation statistics. We used ordinary least squares regression to estimate the association between deprivation, pre-existing conditions and socio-demographic factors and the change in well-being scores over time, as measured by the GHQ-12 questionnaire.Results: A decline in well-being was observed at the beginning of the fi?rst lock down period at the beginning of March 2020. This was matched with a corresponding recovery between April and July as restrictions were gradually lifted. There was no association between the decline and deprivation, nor between deprivation and recovery. The strongest predictor of well-being during the lockdown, was the baseline score, with the counterintuitive finding that for those will pre-existing poor well-being, the impact of pandemic restrictions on mental health were minimal, but for those who had previously felt well, the restrictions and the impact of the pandemic on well-being were much greater.Conclusion: These data show no evidence of a social gradient in well-being related to the pandemic. In fact, wellbeing was shown to be highly elastic in this period indicating a national level of resilience which cut across the usually observed health inequalities.


2021 ◽  
Author(s):  
Honor Scarlett ◽  
Camille Davisse-Paturet ◽  
Cecile Longchamps ◽  
Tarik El Aarbaoui ◽  
Cecile Allaire ◽  
...  

Background: Accumulating evidence suggests that the COVID–19 pandemic has negatively affected global mental health and well–being. However, the impact amongst homeless persons has not been fully evaluated. The ECHO study reports factors associated with depression amongst the homeless population living in shelters in France during the Spring of 2020. Methods: Interview data were collected from 527 participants living in temporary and/or emergency accommodation following France's first lockdown (02/05/20 – 07/06/20), in the metropolitan regions of Paris (74%), Lyon (19%) and Strasbourg (7%). Interviews were conducted in French, English, or with interpreters (33% of participants, ~20 languages). Presence of depression was ascertained using the Patient Health Questionnaire (PHQ–9). Results: Amongst ECHO study participants, 30% had symptoms of moderate to severe depression (PHQ–9≥ 10). Multivariate analysis revealed depression to be associated with being female (aOR: 2.15; CI: 1.26–3.69), being single (aOR: 1.60; CI: 1.01–2.52), having a chronic illness (aOR: 2.32; CI: 1.43–3.78), facing food insecurity (aOR: 2.12; CI: 1.40–3.22) and participants' region of origin. Persons born in African and Eastern Mediterranean regions showed levels of depression comparable to those of French participants (30–33%) but higher than migrants from European countries (14%). Reduced rates of depression were observed amongst participants aged 30–49 (aOR: 0.60; CI: 0.38–0.95) and over 50 (aOR: 0.28; CI: 0.13–0.64), compared to 18–29–year–olds. Conclusions: Our results indicate high levels of depression among homeless persons during the COVID–19 pandemic. The value of these findings extends beyond the health crisis, as predicted future instability and economic repercussions could particularly impact the mental health of this vulnerable group.


2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Nicola Morant ◽  
Alyssa Milton ◽  
Eleanor Gilbert ◽  
Sonia Johnson ◽  
Nicholas Parsons ◽  
...  

Abstract Background Employment within social firms in the UK is under-developed and under-researched, but a potentially beneficial route to vocational rehabilitation for people with mental health problems. This study explores the views and experiences of employees with mental ill-health, managers of social firms and mental health clinicians, in order to understand the potential value of social firms for the vocational rehabilitation, employment and well-being of people with mental health problems. Methods Semi-structured interviews were conducted with 23 employees with mental health problems in 11 social firms in England. A focus group and individual interviews were conducted with 12 managers of social firms. Two focus groups were held with 16 mental health clinicians. Data were analysed using thematic analysis. Results Most employees expressed very positive views about working in a social firm. In responses from both employees and social firm managers, an overarching theme regarding the supportive ethos of social firms encompassed several related features: openness about mental health issues; peer, team and management support; flexibility; and support to progress and develop skills over time. Managers identified benefits of employing people with mental health problems who were sufficiently recovered. Knowledge of social firms within clinician focus groups was very limited, although clinicians thought they could be a welcome additional vocational resource. Conclusions High levels of job satisfaction among social firm employees may be explained by the supportive ethos of these working environments. Social firms have potential to be a helpful addition to the range of vocational pathways available for people with mental ill-health. Further mixed methods investigations of experiences and outcomes in order to understand who engages with and benefits from this form of vocational rehabilitation would be valuable in informing decisions about scaling up the model.


2021 ◽  
Vol 6 ◽  
pp. 176
Author(s):  
Chloe Fawns-Ritchie ◽  
Drew M. Altschul ◽  
Archie Campbell ◽  
Charlotte Huggins ◽  
Clifford Nangle ◽  
...  

CovidLife is a longitudinal observational study designed to investigate the impact of the COVID-19 pandemic on mental health, well-being and behaviour in adults living in the UK. In total, 18,518 participants (mean age = 56.43, SD = 14.35) completed the first CovidLife questionnaire (CovidLife1) between April and June 2020. To date, participants have completed two follow-up assessments. CovidLife2 took place between July and August 2020 (n = 11,319), and CovidLife3 took place in February 2021 (n = 10,386). A range of social and psychological measures were administered at each wave including assessments of anxiety, depression, well-being, loneliness and isolation. Information on sociodemographic, health, and economic circumstances was also collected. Questions also assessed information on COVID-19 infections and symptoms, compliance to COVID-19 restrictions, and opinions on the UK and Scottish Governments’ handling of the pandemic. CovidLife includes a subsample of 4,847 participants from the Generation Scotland cohort (N~24,000, collected 2006-2011); a well-characterised cohort of families in Scotland with pre-pandemic data on mental health, physical health, lifestyle, and socioeconomic factors, along with biochemical and genomic data derived from biological samples. These participants also consented to their study data being linked to Scottish health records. CovidLife and Generation Scotland data can be accessed and used by external researchers following approval from the Generation Scotland Access Committee. CovidLife can be used to investigate mental health, well-being and behaviour during COVID-19; how these vary according to sociodemographic, health and economic circumstances; and how these change over time. The Generation Scotland subsample with pre-pandemic data and linkage to health records can be used to investigate the predictors of health and well-being during COVID-19 and the future health consequences of the COVID-19 pandemic.


2020 ◽  
Author(s):  
Aida Suárez-González ◽  
Emma Harding ◽  
Nikki Zimmerman ◽  
Zoe Hoare ◽  
Emilie Brotherhood ◽  
...  

AbstractIntroductionThe public health measures imposed to contain Covid-19 during the first UK lockdown resulted in significant changes in the provision of community support and care for people with dementia. People with low prevalence and young-onset dementias often experience non-memory, behavioural or neuropsychiatric symptoms that require specialised support.ObjectiveWe explored the impact of the first Covid-19 lockdown on people living with low prevalence and young-onset dementia and their carers in the UK.MethodAn online survey, including eleven questions about the impact of the lockdown on both the person with dementia and their family caregivers was conducted. Participants were people living with dementia and caregivers who are members of the UK national-reach organisation Rare Dementia Support.Results184 carers and 24 people with dementia completed the survey. People with dementia experienced worsening of cognitive symptoms (70%), ability to do things (62%) and well-being (57%) according to their carers. Carers also reported a reduction in the support received for caring (55%). 93% of carers of people living in care homes reported a reduction in their ability to provide care. 26% of carers reported changes in the medication of the person with dementia during the lockdown. 74% of people with dementia reported decreased ability to connect with people socially.ConclusionsPeople with dementia experienced a worsening of dementia symptoms, removal of support and increased difficulty to connect with other people socially during the 1st wave of Covid-19. Carers encountered barriers to both receiving and providing support and a decline in their own mental health and well-being.Key points70 % of carers reported cognitive symptoms getting worse during the lockdown (e.g., the person with dementia being more disoriented and finding it more difficult to communicate).26 % of carers reported a change (initiation or increase) in medication in the person with dementia during the lockdown.79 % carers reported their own physical or mental health getting worse due to the lockdown. This increased to 93% when considering responses only from family carers of people living in care homes.93 % of family carers of people living in care homes found it harder to continue providing care and support for their relative due to Covid-19.


Sign in / Sign up

Export Citation Format

Share Document