How loneliness is talked about in social media during COVID-19 pandemic: Text mining of 4,492 Twitter feeds

Koh, Jing Xuan; Liew, Tau Ming

doi:10.1016/j.jpsychires.2020.11.015

Cited by 99 publications

(94 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The purposes of loneliness across various cultures were described in this article and the expression of loneliness was determined by Twitter during the pandemic period. This study identified key features of machine learning tools through Twitter feeds [27]. The key purpose of this analysis is to investigate pandemic-related debates, fears and feelings shared by Twitter users.…”

Section: Related Workmentioning

confidence: 99%

Prediction on Domestic Violence in Bangladesh during the COVID-19 Outbreak Using Machine Learning Methods

Hossain¹,

Asadullah²,

Rahaman³

et al. 2021

Preprint

View full text Add to dashboard Cite

In Southern Asia, Bangladesh is a well-known developing country. Because of COVID-19, we continuously face challenges. Not only can these issues occur beyond economic or health concerns, but they also generate dangerous social problems, such as family abuse. Since the inception of this epidemic, multiple social crimes are looming. Remaining home during the lockout period enhances divorce rates. This research presents a customized forecast of family violence during the COVID-19 outbreak by using machine learning methods. In this paper, we have applied Random Forest, Logistic Regression, and Naive Bayes machine learning classifiers to predict family violence and discovered the feature importance. The performance of the classifiers is evaluated based on accuracy, precision, recall, and F-score. We have employed an oversampling strategy named synthetic minority oversampling technique (SMOTE) to solve the imbalance problem of our data. Even, we have tried to compare three machine learning model performances before and after balancing of normalization data. Finally, ROC analyses and confusion matrices were developed and analyzed by using data augmentation. Our proposed system with the random forest classifier performed better with 77% accuracy in comparison with other two machine learning classifiers.

show abstract

Section: Related Workmentioning

confidence: 99%

Prediction on Domestic Violence in Bangladesh during the COVID-19 Outbreak Using Machine Learning Methods

Hossain¹,

Asadullah²,

Rahaman³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Furthermore, our findings confirm the general public concerns regarding the adverse health effects of the pandemic, especially those expressed through the social media since early 2020. These include, for example, the published accounts of the COVID-19 epidemic in New York City [ 49 ] or lockdown in Turkey [ 18 ], as well discussion of the specific mental health problems [ 6 , 23 ]; psychological reactions [ 7 , 8 , 9 ]; and the effects on obesity and cardiovascular diseases [ 3 , 10 ].…”

Section: Discussionmentioning

confidence: 99%

“…In general, Twitter is a valuable asset for enabling the investigation of public health issues during the COVID-19 pandemic. Koh and Liew [ 23 ] classified 4492 tweets into three themes based on the level of loneliness, and investigated temporal variations among themes over time. The results showed that tweets do express public sentiments on loneliness during the current pandemic.…”

Section: Literature Reviewmentioning

confidence: 99%

A Study of the Effects of the COVID-19 Pandemic on the Experience of Back Pain Reported on Twitter® in the United States: A Natural Language Processing Approach

Fiok

Karwowski

Gutiérrez

et al. 2021

IJERPH

View full text Add to dashboard Cite

The COVID-19 pandemic has changed our lifestyles, habits, and daily routine. Some of the impacts of COVID-19 have been widely reported already. However, many effects of the COVID-19 pandemic are still to be discovered. The main objective of this study was to assess the changes in the frequency of reported physical back pain complaints reported during the COVID-19 pandemic. In contrast to other published studies, we target the general population using Twitter as a data source. Specifically, we aim to investigate differences in the number of back pain complaints between the pre-pandemic and during the pandemic. A total of 53,234 and 78,559 tweets were analyzed for November 2019 and November 2020, respectively. Because Twitter users do not always complain explicitly when they tweet about the experience of back pain, we have designed an intelligent filter based on natural language processing (NLP) to automatically classify the examined tweets into the back pain complaining class and other tweets. Analysis of filtered tweets indicated an 84% increase in the back pain complaints reported in November 2020 compared to November 2019. These results might indicate significant changes in lifestyle during the COVID-19 pandemic, including restrictions in daily body movements and reduced exposure to routine physical exercise.

show abstract

“…First, linguistic methods were the most frequently used (n=26), such as the presence of keywords generated by the study authors (e.g., 'loneliness' and synonyms in Koh & Liew, 2020), applying established dictionaries (e.g., the Linguistic Inquiry and Word Count (LIWC) dictionary in Lin et al, 2017)), or pre-trained language models (e.g., SKEP in Da & Yang, 2020). Second, human assessment was used in 18 studies, with 11 using human annotators to conduct qualitative coding, typically for nuanced mental health information (e.g., type of social support received in Glasgow et al 2016), and 7 studies interpreting a mental health topic from a topic modeling analysis.…”

Section: Disaster Mental Health Methodsmentioning

confidence: 99%

Social media monitoring of mental health during disasters: A scoping review of methods and applications

Teague¹,

Abr²,

Fuller‐Tyszkiewicz³

et al. 2021

Preprint

View full text Add to dashboard Cite

BackgroundDifficulties in deploying mental health assessments during disasters have resulted in emerging research examining the use of social media as a population mental health monitoring tool. This review synthesises this literature, with particular focus on research methods and applications.MethodsThe field of social media monitoring of mental health during disasters was rapidly mapped using a scoping review methodology. Six interdisciplinary research databases were searched for relevant articles, with data extracted on the articles’ applications and data collection and analysis methods. Articles were then synthesised via narrative review.ResultsForty-seven papers were identified. Three application themes emerged, including: (i) estimating mental health burden; (ii) planning or evaluating interventions and policies, and (iii) knowledge discovery, where theories of human behaviour and mental health were evaluated. Applications across 30 mental health issues were identified, with mental health typically assessed using established linguistic dictionaries. Features extracted from social media data included linguistic, psycholinguistic, behavioural, and demographic features. Analytic techniques involved machine learning, statistical modelling, and qualitative analyses.ConclusionsThe application of social media monitoring has considerable potential for measuring the mental health impact on populations during disasters. As an emerging field, opportunities for further work were identified to improve mental health assessment methods, examine specific mental health conditions, and trial tools in real-world settings. Platforms integrated with such techniques may offer significant benefits for monitoring mental health in contexts where formal assessments are difficult to deploy, and may potentially be harnessed to monitor the impact of response efforts and intervention delivery.

show abstract

How loneliness is talked about in social media during COVID-19 pandemic: Text mining of 4,492 Twitter feeds

Cited by 99 publications

References 35 publications

Prediction on Domestic Violence in Bangladesh during the COVID-19 Outbreak Using Machine Learning Methods

Prediction on Domestic Violence in Bangladesh during the COVID-19 Outbreak Using Machine Learning Methods

A Study of the Effects of the COVID-19 Pandemic on the Experience of Back Pain Reported on Twitter® in the United States: A Natural Language Processing Approach

Social media monitoring of mental health during disasters: A scoping review of methods and applications

Contact Info

Product

Resources

About