Nowcasting unemployment rate during the COVID-19 pandemic using Twitter data: The case of South Africa

Nia, Zahra Movahedi; Asgary, Ali; Bragazzi, Nicola Luigi; Mellado, B.; Orbinski, James; Wu, Jianhong; Kong, Jude Dzevela

doi:10.3389/fpubh.2022.952363

Cited by 4 publications

(2 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While both stance detection and sentiment analysis have been extensively used in analyzing social media posts, there is a need to evaluate the performance of automated labeling approaches, especially in the domain of stance detection [ 2 , 3 ]. Traditionally, sentiment analysis and stance detection models were developed using hand-labeled data, which is labor-intensive and time-consuming.…”

Section: Introductionmentioning

confidence: 99%

Evaluating automatic annotation of lexicon-based models for stance detection of M-pox tweets from May 1st to Sep 5th, 2022

Perikli,

Bhattacharya,

Ogbuokiri

et al. 2024

PLOS Digit Health

View full text Add to dashboard Cite

Manually labeling data for supervised learning is time and energy consuming; therefore, lexicon-based models such as VADER and TextBlob are used to automatically label data. However, it is argued that automated labels do not have the accuracy required for training an efficient model. Although automated labeling is frequently used for stance detection, automated stance labels have not been properly evaluated, in the previous works. In this work, to assess the accuracy of VADER and TextBlob automated labels for stance analysis, we first manually label a Twitter, now X, dataset related to M-pox stance detection. We then fine-tune different transformer-based models on the hand-labeled M-pox dataset, and compare their accuracy before and after fine-tuning, with the accuracy of automated labeled data. Our results indicated that the fine-tuned models surpassed the accuracy of VADER and TextBlob automated labels by up to 38% and 72.5%, respectively. Topic modeling further shows that fine-tuning diminished the scope of misclassified tweets to specific sub-topics. We conclude that fine-tuning transformer models on hand-labeled data for stance detection, elevates the accuracy to a superior level that is significantly higher than automated stance detection labels. This study verifies that automated stance detection labels are not reliable for sensitive use-cases such as health-related purposes. Manually labeled data is more convenient for developing Natural Language Processing (NLP) models that study and analyze mass opinions and conversations on social media platforms, during crises such as pandemics and epidemics.

show abstract

Section: Introductionmentioning

confidence: 99%

Evaluating automatic annotation of lexicon-based models for stance detection of M-pox tweets from May 1st to Sep 5th, 2022

Perikli,

Bhattacharya,

Ogbuokiri

et al. 2024

PLOS Digit Health

View full text Add to dashboard Cite

show abstract

“…Therefore, social media is broadly used in different areas of research, especially the COVID-19 pandemic [ 14 ]. Although social media has widely been studied for different aspects of the COVID-19 pandemic such as macroeconomic consequences [ 15 ], indicator prediction [ 16 ], mental health problems [ 17 ], misinformation [ 18 ], and vaccine hesitancy [ 19 ], few papers have used it to understand mass opinions on ivermectin. Diaz et al [ 20 ] have studied ivermectin from a political point of view.…”

Section: Introductionmentioning

confidence: 99%

Off-label drug use during the COVID-19 pandemic in Africa: topic modelling and sentiment analysis of ivermectin in South Africa and Nigeria as a case study

Movahedi Nia,

Bragazzi,

Ahamadi

et al. 2023

J. R. Soc. Interface.

View full text Add to dashboard Cite

Although rejected by the World Health Organization, the human and even veterinary formulation of ivermectin has widely been used for prevention and treatment of COVID-19. In this work we leverage Twitter to understand the reasons for the drug use from ivermectin supporters, their source of information, their emotions, their gender demographics, and location information, in Nigeria and South Africa. Topic modelling is performed on a Twitter dataset gathered using keywords ‘ivermectin’ and ‘ivm’. A model is fine-tuned on RoBERTa to find the stance of the tweets. Statistical analysis is performed to compare the stance and emotions. Most ivermectin supporters either redistribute conspiracy theories posted by influencers, or refer to flawed studies confirming ivermectin efficacy in vitro . Three emotions have the highest intensity, optimism, joy and disgust. The number of anti-ivermectin tweets has a significant positive correlation with vaccination rate. All the provinces in South Africa and most of the provinces of Nigeria are pro-ivermectin and have higher disgust polarity. This work makes the effort to understand public discussions regarding ivermectin during the COVID-19 pandemic to help policy-makers understand the rationale behind its popularity, and inform more targeted policies to discourage self-administration of ivermectin. Moreover, it is a lesson to future outbreaks.

show abstract

News media in crisis: a sentiment and emotion analysis of US news articles on unemployment in the COVID-19 pandemic

Yu,

Yang

2024

Humanit Soc Sci Commun

View full text Add to dashboard Cite

News media play an indispensable role in disseminating information and shaping public perception during times of crisis. This study, integrating sentiment, emotion, discourse, and timeline analyses together, conducts a corpus-based sentiment analysis of the news articles on unemployment from the New York Times in 2020 to capture the emotional dynamics conveyed by the newspaper as the pandemic-induced unemployment developed in the US. The results reveal that positive sentiment in the news articles on unemployment is significantly higher than negative sentiment. In emotion analysis, “trust” and “anticipation” rank the first and second among the eight emotions, while “fear” and “sadness” top the negative emotions. Complemented with a discourse analysis approach, the study reveals that the change of the sentiments and emotions over time is linked with the evolution of the pandemic and unemployment, the policy response as well as the protests against ethnic inequalities. This study highlights the important role mainstream news media play in information dissemination and solution-focused reportage at the time of severe crisis.

show abstract

Nowcasting unemployment rate during the COVID-19 pandemic using Twitter data: The case of South Africa

Cited by 4 publications

References 57 publications

Evaluating automatic annotation of lexicon-based models for stance detection of M-pox tweets from May 1st to Sep 5th, 2022

Evaluating automatic annotation of lexicon-based models for stance detection of M-pox tweets from May 1st to Sep 5th, 2022

Off-label drug use during the COVID-19 pandemic in Africa: topic modelling and sentiment analysis of ivermectin in South Africa and Nigeria as a case study

News media in crisis: a sentiment and emotion analysis of US news articles on unemployment in the COVID-19 pandemic

Contact Info

Product

Resources

About