Exploring the predictive abilityof LIKES of posts on the Facebook pages of four majorcity DMOs in Austria

• Ulrich Gunter ^[1] ; Irem Önder ^[1] ; Stefan Gindl ^[1]
  1. [1] MODUL University Vienna

     MODUL University Vienna

     Innere Stadt, Austria

     
• Localización: Tourism economics: the business and finance of tourism and recreation, ISSN 1354-8166, Vol. 25, Nº. Extra 3, 2019 (Ejemplar dedicado a: Tourism forecasting – New trends and issues), págs. 375-401
• Idioma: inglés
• Texto completo no disponible (Saber más ...)
• Resumen

  • Using data for the period 2010M06–2017M02, this study investigates the possibility of predictingtotal tourist arrivals to four Austrian cities (Graz, Innsbruck, Salzburg, and Vienna) from LIKES ofposts on the Facebook pages of the destination management organizations of these cities. GoogleTrends data are also incorporated in investigating whether forecast models with LIKES and/or withGoogle Trends deliver more accurate forecasts. To capture the dynamics in the data, the auto-regressive distributed lag (ADL) model class is employed. Taking into account the daily frequency ofthe original LIKES data, the mixed data sampling (MIDAS) model class is employed as well. Whiletime-series benchmarks from the naive, error–trend–seasonal, and autoregressive moving averagemodel classes perform best for Graz and Innsbruck across forecast horizons and forecast accuracymeasures, ADL models incorporating only LIKES or both LIKES and Google Trends generally out-perform their competitors for Salzburg. For Vienna, the MIDAS model including both LIKES andGoogle Trends produces the smallest forecast accuracy measure values for most forecast horizons.