Nowcasting unemployment rate during the COVID-19 pandemic using Twitter data: The case of South Africa
The global economy has been hard hit by the COVID-19 pandemic. Many countries are experiencing a severe and destructive recession. A significant number of firms and businesses have gone bankrupt or been scaled down, and many individuals have lost their jobs. The main goal of this study is to support...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-12-01
|
| Series: | Frontiers in Public Health |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpubh.2022.952363/full |
| _version_ | 1798014296402165760 |
|---|---|
| author | Zahra Movahedi Nia Ali Asgary Nicola Bragazzi Bruce Mellado James Orbinski Jianhong Wu Jude Kong |
| author_facet | Zahra Movahedi Nia Ali Asgary Nicola Bragazzi Bruce Mellado James Orbinski Jianhong Wu Jude Kong |
| author_sort | Zahra Movahedi Nia |
| collection | DOAJ |
| description | The global economy has been hard hit by the COVID-19 pandemic. Many countries are experiencing a severe and destructive recession. A significant number of firms and businesses have gone bankrupt or been scaled down, and many individuals have lost their jobs. The main goal of this study is to support policy- and decision-makers with additional and real-time information about the labor market flow using Twitter data. We leverage the data to trace and nowcast the unemployment rate of South Africa during the COVID-19 pandemic. First, we create a dataset of unemployment-related tweets using certain keywords. Principal Component Regression (PCR) is then applied to nowcast the unemployment rate using the gathered tweets and their sentiment scores. Numerical results indicate that the volume of the tweets has a positive correlation, and the sentiments of the tweets have a negative correlation with the unemployment rate during and before the COVID-19 pandemic. Moreover, the now-casted unemployment rate using PCR has an outstanding evaluation result with a low Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), Symmetric MAPE (SMAPE) of 0.921, 0.018, 0.018, respectively and a high R2-score of 0.929. |
| first_indexed | 2024-04-11T15:16:15Z |
| format | Article |
| id | doaj.art-bd8f44a91bd04e0f8d96c33c8c86d9ed |
| institution | Directory Open Access Journal |
| issn | 2296-2565 |
| language | English |
| last_indexed | 2024-04-11T15:16:15Z |
| publishDate | 2022-12-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Public Health |
| spelling | doaj.art-bd8f44a91bd04e0f8d96c33c8c86d9ed2022-12-22T04:16:29ZengFrontiers Media S.A.Frontiers in Public Health2296-25652022-12-011010.3389/fpubh.2022.952363952363Nowcasting unemployment rate during the COVID-19 pandemic using Twitter data: The case of South AfricaZahra Movahedi Nia0Ali Asgary1Nicola Bragazzi2Bruce Mellado3James Orbinski4Jianhong Wu5Jude Kong6Africa-Canada Artificial Intelligence and Data Innovation Consortium (ACADIC), Laboratory for Industrial and Applied Mathematics, York University, Toronto, ON, CanadaAfrica-Canada Artificial Intelligence and Data Innovation Consortium (ACADIC), The Advanced Disaster, Emergency and Rapid Response Program, York University, Toronto, ON, CanadaAfrica-Canada Artificial Intelligence and Data Innovation Consortium (ACADIC), Laboratory for Industrial and Applied Mathematics, York University, Toronto, ON, CanadaAfrica-Canada Artificial Intelligence and Data Innovation Consortium (ACADIC), Schools of Physics, Institute for Collider Particle Physics, University of the Witwatersrand, Johannesburg, South AfricaAfrica-Canada Artificial Intelligence and Data Innovation Consortium (ACADIC), The Dahdaleh Institute for Global Health Research, York University, Toronto, ON, CanadaAfrica-Canada Artificial Intelligence and Data Innovation Consortium (ACADIC), Laboratory for Industrial and Applied Mathematics, York University, Toronto, ON, CanadaAfrica-Canada Artificial Intelligence and Data Innovation Consortium (ACADIC), Laboratory for Industrial and Applied Mathematics, York University, Toronto, ON, CanadaThe global economy has been hard hit by the COVID-19 pandemic. Many countries are experiencing a severe and destructive recession. A significant number of firms and businesses have gone bankrupt or been scaled down, and many individuals have lost their jobs. The main goal of this study is to support policy- and decision-makers with additional and real-time information about the labor market flow using Twitter data. We leverage the data to trace and nowcast the unemployment rate of South Africa during the COVID-19 pandemic. First, we create a dataset of unemployment-related tweets using certain keywords. Principal Component Regression (PCR) is then applied to nowcast the unemployment rate using the gathered tweets and their sentiment scores. Numerical results indicate that the volume of the tweets has a positive correlation, and the sentiments of the tweets have a negative correlation with the unemployment rate during and before the COVID-19 pandemic. Moreover, the now-casted unemployment rate using PCR has an outstanding evaluation result with a low Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), Symmetric MAPE (SMAPE) of 0.921, 0.018, 0.018, respectively and a high R2-score of 0.929.https://www.frontiersin.org/articles/10.3389/fpubh.2022.952363/fullsentiment analysissocial mediaTwitter dataGoogle Mobility Indexunemployment ratelabor market |
| spellingShingle | Zahra Movahedi Nia Ali Asgary Nicola Bragazzi Bruce Mellado James Orbinski Jianhong Wu Jude Kong Nowcasting unemployment rate during the COVID-19 pandemic using Twitter data: The case of South Africa Frontiers in Public Health sentiment analysis social media Twitter data Google Mobility Index unemployment rate labor market |
| title | Nowcasting unemployment rate during the COVID-19 pandemic using Twitter data: The case of South Africa |
| title_full | Nowcasting unemployment rate during the COVID-19 pandemic using Twitter data: The case of South Africa |
| title_fullStr | Nowcasting unemployment rate during the COVID-19 pandemic using Twitter data: The case of South Africa |
| title_full_unstemmed | Nowcasting unemployment rate during the COVID-19 pandemic using Twitter data: The case of South Africa |
| title_short | Nowcasting unemployment rate during the COVID-19 pandemic using Twitter data: The case of South Africa |
| title_sort | nowcasting unemployment rate during the covid 19 pandemic using twitter data the case of south africa |
| topic | sentiment analysis social media Twitter data Google Mobility Index unemployment rate labor market |
| url | https://www.frontiersin.org/articles/10.3389/fpubh.2022.952363/full |
| work_keys_str_mv | AT zahramovahedinia nowcastingunemploymentrateduringthecovid19pandemicusingtwitterdatathecaseofsouthafrica AT aliasgary nowcastingunemploymentrateduringthecovid19pandemicusingtwitterdatathecaseofsouthafrica AT nicolabragazzi nowcastingunemploymentrateduringthecovid19pandemicusingtwitterdatathecaseofsouthafrica AT brucemellado nowcastingunemploymentrateduringthecovid19pandemicusingtwitterdatathecaseofsouthafrica AT jamesorbinski nowcastingunemploymentrateduringthecovid19pandemicusingtwitterdatathecaseofsouthafrica AT jianhongwu nowcastingunemploymentrateduringthecovid19pandemicusingtwitterdatathecaseofsouthafrica AT judekong nowcastingunemploymentrateduringthecovid19pandemicusingtwitterdatathecaseofsouthafrica |