Going Back in Time to Predict the Future - The Complex Role of the Data Collection Period in Social Media Analytics

Stefan Stieglitz, Christian Meske, Björn Ross, Milad Mirbabaie

Research output: Contribution to journalArticlepeer-review

Abstract

In the context of events that involve public voting, such as televised competitions or elections, it has increasingly been recognized that communication data from social media is related to the outcome. Existing studies mainly analyse the number of messages and their sentiment, yet the role of different data collection periods has not been examined sufficiently. We collected Twitter data in 2015 and 2016 to examine the relationship between the audience voting of the Eurovision Song Contest and predictors based on quantity and emotions, and compared the results of using data from before and during the event. We found that the choice of time period greatly affected the results obtained. Data collected prior to the event exhibited a much stronger association with the final ranking than data collected during the event. In addition, the model based on pre-event data in 2015 showed considerable accuracy in predicting the 2016 results, illustrating the usefulness of social media data for predicting the outcomes of events outside social media.
Original languageEnglish
Pages (from-to)395-409
Number of pages15
JournalInformation Systems Frontiers
Volume22
Issue number2
Early online date8 Jun 2018
DOIs
Publication statusPublished - 30 Apr 2020

Keywords

  • Social media analytics
  • Time period
  • Predictive analytics
  • Eurovision
  • Twitter

Fingerprint Dive into the research topics of 'Going Back in Time to Predict the Future - The Complex Role of the Data Collection Period in Social Media Analytics'. Together they form a unique fingerprint.

Cite this