Search Conferences

Type in any word, words or author name. This searchs through the abstract title, keywords and abstract text and authors. You may search all conferences or just select one conference.

 All Conferences
 EMAC 2019 Annual Conference
 EMAC 2020 Annual Conference
 EMAC 2020 Regional Conference
 EMAC 2021 Annual Conference
 EMAC 2021 Regional Conference
 EMAC 2022 Annual
 EMAC 2022 Regional Conference
 EMAC 2023 Annual
 EMAC 2023 Regional Conference

EMAC 2022 Annual

Exploring the Twitter Myth: The Value of Twitter-generated Variables on Forecasting Tourist Arrivals

Published: May 24, 2022


Yuanming Qiu, University of Edinburgh Business School; Jake Ansell,; Ewelina Lacka, University of Edinburgh Business School


A growing body of research suggests that demand forecasts are efficient tools to help attractions formulate crowd management strategies and maintain competitiveness. Meanwhile, social media data are claimed to facilitate short-term and high-frequency demand forecasts quite well. However, only a handful of studies have explored the application of social media data in modeling tourism demand thus far. Applying Granger-causality analysis and dynamic modeling strategies to the case of the British Museum, this study aims to investigate if Twitter-generated variables can add value to accurate tourism demand forecasts. In this regard, we draw on research analyzing dynamics among Twitter-generated variables and various outcome variables from different disciplines to construct our potential predictors and further apply them in the practice of attraction-level tourism demand forecasts. Findings indicate a bidirectional relationship between the volume of tweets fetched under the name of the British Museum and tourist arrivals to the site. As regard model performance, the best fit is achieved with the autoregressive and distributed lag model that incorporates data from multisource (i.e., Twitter and Google Trends). This study contributes to tourism demand forecasting research by adding evidence to the value of dynamic models and multi-sourced high-frequency Internet data on accurate tourism demand forecasts at the attraction level and indicating directions for future research. Implications of this research for destination management are two-fold. First, an attraction can seek accurate forecasts of tourist arrivals through the utilization of Twitter data and especially the volume of tweets referred to the attraction’s name. Second, attractions would benefit from engaging with individuals on Twitter on a broader level, that is, not only through content posted on an attraction’s official account but also all related tweets that are publicly available.