Search results

This study aims to provide a systematic review of the existing literature on the applications of deep learning (DL) in hospitality, tourism and travel as well as an agenda for future research.

Covering a five-year time span (2017–2021), this study systematically reviews journal articles archived in four academic databases: Emerald Insight, Springer, Wiley Online Library and ScienceDirect. All 159 articles reviewed were characterised using six attributes: publisher, year of publication, country studied, type of value created, application area and future suggestions (and/or limitations).

Five application areas and six challenge areas are identified, which characterise the application of DL in hospitality, tourism and travel. In addition, it is observed that DL is mainly used to develop novel models that are creating business value by forecasting (or projecting) some parameter(s) and promoting better offerings to tourists.

Although a few prior papers have provided a literature review of artificial intelligence in tourism and hospitality, none have drilled-down to the specific area of DL applications within the context of hospitality, tourism and travel.

To the best of the authors’ knowledge, this paper represents the first theoretical review of academic research on DL applications in hospitality, tourism and travel. An integrated framework is proposed to expose future research trajectories wherein scholars can contribute significant value. The exploration of the DL literature has significant implications for industry and practice, given that this, as far as the authors know, is the first systematic review of existing literature in this research area.

The global food industry is faced with the dilemma of finding a balance between food wastage and food shortage. Approximately one-third of food produced globally goes to waste, while about 800 million people suffer from undernourishment. Given this context, the purpose of this study is to investigate the unresolved challenges related to enhancing transparency associated with products of high perishability and low shelf life.

The authors conducted 25 interviews with global agri-food supply chains (AFSCs) experts to ask what impedes the progress of the current technologies, such as blockchain, to enable transparency and traceability (T&T) in AFSCs.

The findings indicate barriers at the individual, firm and supply chain levels. Based on these barriers, the authors propose an interconnected framework to explain technologically-driven T&T and guide on barrier removal from AFSCs. The authors conclude that by applying technology (i.e. blockchain) the authors can resolve the tension of supporting T&T in AFSCs. This can enable the efficient and transparent tracking of goods, reduction of food waste and loss, as well as promotion of the use of recyclable packaging and further sustainable practices and materials, all of which are aligned with a range of UN Sustainable Development Goals (2, 8, 10 and 12). Moreover, the authors see that some factors are interrelated. Based on these factors, the authors build an interconnected framework to guide on barrier removal from AFSCs. Managers in AFSC would find the findings especially relevant.

Drawing on industrial network theory and signalling theory, the authors propose an interconnected framework for explaining barriers (challenges) and potential solutions (opportunities) to T&T in AFSCs. This framework is developed by examining the interconnections of barriers at micro, meso and macro levels and applying signalling theory to explain how solutions address these barriers. The specific contributions of this study are: the list of barriers that impede the implementation of technological solutions for T&T in AFSCs; and a three-stage framework that explains how to remove the barriers for T&T. The study is limited by the focus on blockchain, which calls for future research once the next decentralised technology becomes available.