Using Natural Language Processing to Explore Mental Health Insights From UK Tweets During the COVID-19 Pandemic: Infodemiology Study
BackgroundThere is need to consider the value of soft intelligence, leveraged using accessible natural language processing (NLP) tools, as a source of analyzed evidence to support public health research outputs and decision-making. ObjectiveThe aim of this study w...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
JMIR Publications
2022-03-01
|
| Series: | JMIR Infodemiology |
| Online Access: | https://infodemiology.jmir.org/2022/1/e32449 |
| _version_ | 1827858438470762496 |
|---|---|
| author | Christopher Marshall Kate Lanyi Rhiannon Green Georgina C Wilkins Fiona Pearson Dawn Craig |
| author_facet | Christopher Marshall Kate Lanyi Rhiannon Green Georgina C Wilkins Fiona Pearson Dawn Craig |
| author_sort | Christopher Marshall |
| collection | DOAJ |
| description |
BackgroundThere is need to consider the value of soft intelligence, leveraged using accessible natural language processing (NLP) tools, as a source of analyzed evidence to support public health research outputs and decision-making.
ObjectiveThe aim of this study was to explore the value of soft intelligence analyzed using NLP. As a case study, we selected and used a commercially available NLP platform to identify, collect, and interrogate a large collection of UK tweets relating to mental health during the COVID-19 pandemic.
MethodsA search strategy comprised of 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 readily and commercially available NLP platform to explore tweet frequency and sentiment across the United Kingdom 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. All collated tweets were anonymized.
ResultsWe identified and analyzed 286,902 tweets posted from UK user accounts from July 23, 2020 to January 6, 2021. The average sentiment score was 50%, suggesting overall neutral sentiment across all tweets over the study period. Major fluctuations in volume (between 12,622 and 51,340) and sentiment (between 25% and 49%) appeared to coincide with key changes to any local and/or national social distancing measures. Tweets around mental health were polarizing, 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.
ConclusionsUsing an NLP platform, we were able to rapidly mine and analyze 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 analyzed 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. |
| first_indexed | 2024-03-12T12:55:26Z |
| format | Article |
| id | doaj.art-37a0731da0924e73828c1a2219dc30de |
| institution | Directory Open Access Journal |
| issn | 2564-1891 |
| language | English |
| last_indexed | 2024-03-12T12:55:26Z |
| publishDate | 2022-03-01 |
| publisher | JMIR Publications |
| record_format | Article |
| series | JMIR Infodemiology |
| spelling | doaj.art-37a0731da0924e73828c1a2219dc30de2023-08-28T21:12:24ZengJMIR PublicationsJMIR Infodemiology2564-18912022-03-0121e3244910.2196/32449Using Natural Language Processing to Explore Mental Health Insights From UK Tweets During the COVID-19 Pandemic: Infodemiology StudyChristopher Marshallhttps://orcid.org/0000-0002-7970-681XKate Lanyihttps://orcid.org/0000-0002-3258-7286Rhiannon Greenhttps://orcid.org/0000-0001-6113-0675Georgina C Wilkinshttps://orcid.org/0000-0001-8800-3596Fiona Pearsonhttps://orcid.org/0000-0003-1626-0862Dawn Craighttps://orcid.org/0000-0002-5808-0096 BackgroundThere is need to consider the value of soft intelligence, leveraged using accessible natural language processing (NLP) tools, as a source of analyzed evidence to support public health research outputs and decision-making. ObjectiveThe aim of this study was to explore the value of soft intelligence analyzed using NLP. As a case study, we selected and used a commercially available NLP platform to identify, collect, and interrogate a large collection of UK tweets relating to mental health during the COVID-19 pandemic. MethodsA search strategy comprised of 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 readily and commercially available NLP platform to explore tweet frequency and sentiment across the United Kingdom 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. All collated tweets were anonymized. ResultsWe identified and analyzed 286,902 tweets posted from UK user accounts from July 23, 2020 to January 6, 2021. The average sentiment score was 50%, suggesting overall neutral sentiment across all tweets over the study period. Major fluctuations in volume (between 12,622 and 51,340) and sentiment (between 25% and 49%) appeared to coincide with key changes to any local and/or national social distancing measures. Tweets around mental health were polarizing, 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. ConclusionsUsing an NLP platform, we were able to rapidly mine and analyze 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 analyzed 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.https://infodemiology.jmir.org/2022/1/e32449 |
| spellingShingle | Christopher Marshall Kate Lanyi Rhiannon Green Georgina C Wilkins Fiona Pearson Dawn Craig Using Natural Language Processing to Explore Mental Health Insights From UK Tweets During the COVID-19 Pandemic: Infodemiology Study JMIR Infodemiology |
| title | Using Natural Language Processing to Explore Mental Health Insights From UK Tweets During the COVID-19 Pandemic: Infodemiology Study |
| title_full | Using Natural Language Processing to Explore Mental Health Insights From UK Tweets During the COVID-19 Pandemic: Infodemiology Study |
| title_fullStr | Using Natural Language Processing to Explore Mental Health Insights From UK Tweets During the COVID-19 Pandemic: Infodemiology Study |
| title_full_unstemmed | Using Natural Language Processing to Explore Mental Health Insights From UK Tweets During the COVID-19 Pandemic: Infodemiology Study |
| title_short | Using Natural Language Processing to Explore Mental Health Insights From UK Tweets During the COVID-19 Pandemic: Infodemiology Study |
| title_sort | using natural language processing to explore mental health insights from uk tweets during the covid 19 pandemic infodemiology study |
| url | https://infodemiology.jmir.org/2022/1/e32449 |
| work_keys_str_mv | AT christophermarshall usingnaturallanguageprocessingtoexplorementalhealthinsightsfromuktweetsduringthecovid19pandemicinfodemiologystudy AT katelanyi usingnaturallanguageprocessingtoexplorementalhealthinsightsfromuktweetsduringthecovid19pandemicinfodemiologystudy AT rhiannongreen usingnaturallanguageprocessingtoexplorementalhealthinsightsfromuktweetsduringthecovid19pandemicinfodemiologystudy AT georginacwilkins usingnaturallanguageprocessingtoexplorementalhealthinsightsfromuktweetsduringthecovid19pandemicinfodemiologystudy AT fionapearson usingnaturallanguageprocessingtoexplorementalhealthinsightsfromuktweetsduringthecovid19pandemicinfodemiologystudy AT dawncraig usingnaturallanguageprocessingtoexplorementalhealthinsightsfromuktweetsduringthecovid19pandemicinfodemiologystudy |