Prediction of employment and unemployment rates from Twitter daily rhythms in the US

Eszter Bokányi, Zoltán Lábszki, G. Vattay

Research output: Contribution to journalArticle

7 Citations (Scopus)

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) and unemployment rates (− 0.34 ± 0.02). 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.

Original languageEnglish
Article number14
JournalEPJ Data Science
Volume6
Issue number1
DOIs
Publication statusPublished - Dec 1 2017

Fingerprint

Unemployment
Prediction
Social Networks
Macros
Mobile Networks
Statistics
Correlate
Linear Combination
Trace
Modeling

Keywords

  • activity patterns
  • social media
  • Twitter
  • unemployment prediction

ASJC Scopus subject areas

  • Modelling and Simulation
  • Computer Science Applications
  • Computational Mathematics

Cite this

Prediction of employment and unemployment rates from Twitter daily rhythms in the US. / Bokányi, Eszter; Lábszki, Zoltán; Vattay, G.

In: EPJ Data Science, Vol. 6, No. 1, 14, 01.12.2017.

Research output: Contribution to journalArticle

@article{4962b9920de74dcd8e73638838e66eaa,
title = "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 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) and unemployment rates (− 0.34 ± 0.02). 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.",
keywords = "activity patterns, social media, Twitter, unemployment prediction",
author = "Eszter Bok{\'a}nyi and Zolt{\'a}n L{\'a}bszki and G. Vattay",
year = "2017",
month = "12",
day = "1",
doi = "10.1140/epjds/s13688-017-0112-x",
language = "English",
volume = "6",
journal = "EPJ Data Science",
issn = "2193-1127",
publisher = "Springer Science + Business Media",
number = "1",

}

TY - JOUR

T1 - Prediction of employment and unemployment rates from Twitter daily rhythms in the US

AU - Bokányi, Eszter

AU - Lábszki, Zoltán

AU - Vattay, G.

PY - 2017/12/1

Y1 - 2017/12/1

N2 - 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) and unemployment rates (− 0.34 ± 0.02). 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.

AB - 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) and unemployment rates (− 0.34 ± 0.02). 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.

KW - activity patterns

KW - social media

KW - Twitter

KW - unemployment prediction

UR - http://www.scopus.com/inward/record.url?scp=85023764650&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85023764650&partnerID=8YFLogxK

U2 - 10.1140/epjds/s13688-017-0112-x

DO - 10.1140/epjds/s13688-017-0112-x

M3 - Article

AN - SCOPUS:85023764650

VL - 6

JO - EPJ Data Science

JF - EPJ Data Science

SN - 2193-1127

IS - 1

M1 - 14

ER -