Which search queries are more powerful in tourism demand forecasting: searches via mobile device or PC?. Issue 6 (31st May 2021)

• Record Type: Journal Article
• Authors: Hu, Mingming; Xiao, Mengqing; Li, Hengyun
• Is Part Of: International journal of contemporary hospitality management. Volume 33:Issue 6(2021)
• Page Start: 2022
• Page End: 2043
• Publication Date: 2021-05-31
• Subjects: Mobile device -- Baidu Index -- PC -- Search query -- Tourism demand forecasting; Hospitality industry -- Management -- Periodicals; 647.94068
• DOI: 10.1108/IJCHM-06-2020-0559
• Languages: English
• ISSNs: 0959-6119

Abstract

Abstract : Purpose: While relevant research has considered aggregated data from mobile devices and personal computers (PCs), tourists' search patterns on mobile devices and PCs differ significantly. This study aims to explore whether decomposing aggregated search queries based on the terminals from which these queries are generated can enhance tourism demand forecasting. Design/methodology/approach: Mount Siguniang, a national geopark in China, is taken as a case study in this paper; another case, Kulangsu in China, is used as the robustness check. The authors decomposed the total Baidu search volume into searches from mobile devices and PCs. Weekly rolling forecasts were used to test the roles of decomposed and aggregated search queries in tourism demand forecasting. Findings: Search queries generated from PCs can greatly improve forecasting performance compared to those from mobile devices and to aggregate search volumes from both terminals. Models incorporating search queries generated via multiple terminals did not necessarily outperform those incorporating search queries generated via a single type of terminal. Practical implications: Major players in the tourism industry, including hotels, tourist attractions and airlines, can benefit from identifying effective search terminals to forecast tourism demand. Industry managers can also leverage search indices generated through effective terminals for more accurate demand forecasting, which can in turn inform strategic decision-making and operations management. Originality/value: This study represents one of the earliest attempts to apply decomposed search query data generated via different terminals in tourism demand forecasting. It also enriches the literature on tourism demand forecasting using search engine data.