Destination image: a consumer-based, big data-enabled approach

Abstract

Purpose This study aims to use a bottom-up, inductive approach to derive destination image attributes from large quantities of online consumer narratives and establish a destination classification system based on relationships among attributes and places. Design/methodology/approach Content and social network analyses were used to explore the consumer image structure for destinations based on online narratives. Cluster analysis was then used to group destinations by attributes, and ANOVA provided comparisons. Findings Twenty-two attributes were identified and combined into three groups (core, expected, latent). Destinations were classified into three clusters (comprehensive urban, scenic and lifestyle) based on their network centralities. Using data on Chinese tourism, the most mentioned (core) attributes were determined to be landscape, traffic within the destination, food and beverages and resource-based attractions. Social life was meaningful in consumer narratives but often overlooked by researchers. Practical implications Destinations should determine into which category they belong and then appeal to the real needs of tourists. Destination management organizations should provide the essential attributes while paying greater attention to highlighting the destinations’ social life atmosphere. Originality/value This research produced empirical work on Chinese tourism by combining a bottom-up, inductive research design with big data. It divided the 49 destinations into three categories and established a new system based on rich data to classify travel destinations.

New insights into hotel customer’s revisiting intentions, based on big data

“…One of these accepted and widely used segmentation methods in marketing literature is K-means (Zhong et al , 2023). Segmentation with the K-means method gives researchers the freedom to choose an appropriate number of segments according to the interpretability of results and managerial purposes (Park and Yoon, 2009).…”

“…After clustering, the accuracy of this step was measured by statistical tests. Following Zhong et al (2023), we performed the analysis of variance test separately on all features. The results of this test showed that for all properties, the p -value is less than 0.001, and that there is a significant difference between the different partitions, so it can be concluded that the partitions are different.…”

“…With the development of machine learning methods and an increase in their accuracy, the use of these methods in identifying hotel features has also become common (Francesco and Roberta, 2019). Zhong et al (2023) analyzed Chinese travelers' IJCHM 36,1 comments and divided hotel attributes into different segments. They found that landscape, traffic, food and attractions are core attributes of the hotels from travelers' point of view.…”

Charting the progress of technology adoption in tourism and hospitality in the era of industry 4.0

“…These provide the opportunity to process, store and access knowledge while being connected through mobile devices (Iranmanesh et al, 2022). Technological breakthroughs like Artificial Intelligence (AI), robotics, the Internet of Things (IoT), autonomous vehicles, Blockchain, Big Data, cloud computing, speech, facial recognition (Jabeen et al, 2022;Li et al, 2021;G€ ossling, 2020;Filimonau and Naumova, 2020;Huang and Rust, 2021;€ Onder and Gunter, 2020;Zaman et al, 2022), social media, intelligent service desks, Metaverse (Buhalis et al, 2023b), Virtual Reality (VR) and Augmented Reality (AR) (Cranmer et al, 2021), multiply these opportunities for both consumers and businesses (Zhong et al, 2023;Chen et al, 2022). Some technologies have disrupted and transformed the operation of tourism and hospitality businesses by changing entire business models (Abou Kamar et al, 2024;Fennell, 2021).…”

“…Technological breakthroughs like Artificial Intelligence (AI), robotics, the Internet of Things (IoT), autonomous vehicles, Blockchain, Big Data, cloud computing, speech, facial recognition (Jabeen et al ., 2022; Li et al ., 2021; Gössling, 2020; Filimonau and Naumova, 2020; Huang and Rust, 2021; Önder and Gunter, 2020; Zaman et al ., 2022), social media, intelligent service desks, Metaverse (Buhalis et al. , 2023b), Virtual Reality (VR) and Augmented Reality (AR) (Cranmer et al ., 2021), multiply these opportunities for both consumers and businesses (Zhong et al ., 2023; Chen et al ., 2022).…”