Forecasting Consumer Spending from Purchase Intentions Expressed on Social Media

• Viktor Pekar ^[1] ; Jane Binner ^[1]
  1. [1] University of Birmingham

     University of Birmingham

     Reino Unido

     
• Localización: 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis WASSA 2017: Proceedings of the Workshop / Alexandra Balahur Dobrescu (ed. lit.), Saif M. Mohammad (ed. lit.), Erik van der Goot (ed. lit.), 2017, ISBN 978-1-945626-95-1, págs. 92-101
• Idioma: inglés
• Enlaces
  • Texto completo (pdf)
• Resumen

  • Consumer spending is a vital macroeco- nomic indicator. In this paper we present a novel method for predicting future con- sumer spending from social media data. In contrast to previous work that largely re- lied on sentiment analysis, the proposed method models consumer spending from purchase intentions found on social media. Our experiments with time series analy- sis models and machine-learning regres- sion models reveal utility of this data for making short-term forecasts of consumer spending: for three- and seven-day hori- zons, prediction variables derived from so- cial media help to improve forecast ac- curacy by 11% to 18% for all the three models, in comparison to models that used only autoregressive predictors.