Prediction of employment and unemployment rates from Twitter daily rhythms in the US
Abstract By modeling macro-economical indicators using digital traces of human activities on mobile or social networks, we can provide important insights to processes previously assessed via paper-based surveys or polls only. We collected aggregated workday activity timelines of US counties from the...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2017-07-01
|
| Series: | EPJ Data Science |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1140/epjds/s13688-017-0112-x |
| _version_ | 1828888608378978304 |
|---|---|
| author | Eszter Bokányi Zoltán Lábszki Gábor Vattay |
| author_facet | Eszter Bokányi Zoltán Lábszki Gábor Vattay |
| author_sort | Eszter Bokányi |
| collection | DOAJ |
| description | Abstract By modeling macro-economical indicators using digital traces of human activities on mobile or social networks, we can provide important insights to processes previously assessed via paper-based surveys or polls only. We collected aggregated workday activity timelines of US counties from the normalized number of messages sent in each hour on the online social network Twitter. In this paper, we show how county employment and unemployment statistics are encoded in the daily rhythm of people by decomposing the activity timelines into a linear combination of two dominant patterns. The mixing ratio of these patterns defines a measure for each county, that correlates significantly with employment ( 0.46 ± 0.02 $0.46\pm0.02$ ) and unemployment rates ( − 0.34 ± 0.02 $-0.34\pm0.02$ ). Thus, the two dominant activity patterns can be linked to rhythms signaling presence or lack of regular working hours of individuals. The analysis could provide policy makers a better insight into the processes governing employment, where problems could not only be identified based on the number of officially registered unemployed, but also on the basis of the digital footprints people leave on different platforms. |
| first_indexed | 2024-12-13T12:25:40Z |
| format | Article |
| id | doaj.art-40eb3940550d487eb3f7e3be73e03e60 |
| institution | Directory Open Access Journal |
| issn | 2193-1127 |
| language | English |
| last_indexed | 2024-12-13T12:25:40Z |
| publishDate | 2017-07-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EPJ Data Science |
| spelling | doaj.art-40eb3940550d487eb3f7e3be73e03e602022-12-21T23:46:21ZengSpringerOpenEPJ Data Science2193-11272017-07-016111110.1140/epjds/s13688-017-0112-xPrediction of employment and unemployment rates from Twitter daily rhythms in the USEszter Bokányi0Zoltán Lábszki1Gábor Vattay2Department of Physics of Complex Systems, Eötvös Loránd UniversityDepartment of Physics of Complex Systems, Eötvös Loránd UniversityDepartment of Physics of Complex Systems, Eötvös Loránd UniversityAbstract By modeling macro-economical indicators using digital traces of human activities on mobile or social networks, we can provide important insights to processes previously assessed via paper-based surveys or polls only. We collected aggregated workday activity timelines of US counties from the normalized number of messages sent in each hour on the online social network Twitter. In this paper, we show how county employment and unemployment statistics are encoded in the daily rhythm of people by decomposing the activity timelines into a linear combination of two dominant patterns. The mixing ratio of these patterns defines a measure for each county, that correlates significantly with employment ( 0.46 ± 0.02 $0.46\pm0.02$ ) and unemployment rates ( − 0.34 ± 0.02 $-0.34\pm0.02$ ). Thus, the two dominant activity patterns can be linked to rhythms signaling presence or lack of regular working hours of individuals. The analysis could provide policy makers a better insight into the processes governing employment, where problems could not only be identified based on the number of officially registered unemployed, but also on the basis of the digital footprints people leave on different platforms.http://link.springer.com/article/10.1140/epjds/s13688-017-0112-xunemployment predictionTwittersocial mediaactivity patterns |
| spellingShingle | Eszter Bokányi Zoltán Lábszki Gábor Vattay Prediction of employment and unemployment rates from Twitter daily rhythms in the US EPJ Data Science unemployment prediction social media activity patterns |
| title | Prediction of employment and unemployment rates from Twitter daily rhythms in the US |
| title_full | Prediction of employment and unemployment rates from Twitter daily rhythms in the US |
| title_fullStr | Prediction of employment and unemployment rates from Twitter daily rhythms in the US |
| title_full_unstemmed | Prediction of employment and unemployment rates from Twitter daily rhythms in the US |
| title_short | Prediction of employment and unemployment rates from Twitter daily rhythms in the US |
| title_sort | prediction of employment and unemployment rates from twitter daily rhythms in the us |
| topic | unemployment prediction social media activity patterns |
| url | http://link.springer.com/article/10.1140/epjds/s13688-017-0112-x |
| work_keys_str_mv | AT eszterbokanyi predictionofemploymentandunemploymentratesfromtwitterdailyrhythmsintheus AT zoltanlabszki predictionofemploymentandunemploymentratesfromtwitterdailyrhythmsintheus AT gaborvattay predictionofemploymentandunemploymentratesfromtwitterdailyrhythmsintheus |