This paper aims to identify the intellectual structure of four leading hospitality journals over 40 years by applying mixed-method approach, using both machine learning and traditional statistical analyses.
Abstracts from all 4,139 articles published in four top hospitality journals were analyzed using the structured topic modeling and inferential statistics. Topic correlation and community detection were applied to identify strengths of correlations and sub-groups of topics. Trend visualization and regression analysis were used to quantify the effects of the metadata (i.e. year of publication and journal) on topic proportions.
The authors found 50 topics and eight subgroups in the hospitality journals. Different evolutionary patterns in topic popularity were demonstrated, thereby providing the insights for popular research topics over time. The significant differences in topical proportions were found across the four leading hospitality journals, suggesting different foci in research topics in each journal.
Combining machine learning techniques with traditional statistics demonstrated potential for discovering valuable insights from big text data in hospitality and tourism research contexts. The findings of this study may serve as a guide to understand the trends in the research field as well as the progress of specific areas or subfields.
It is the first attempt to apply topic modeling to academic publications and explore the effects of article metadata with the hospitality literature.
Park, E.(O)., Chae, B. and Kwon, J. (2018), "Toward understanding the topical structure of hospitality literature: Applying machine learning and traditional statistics", International Journal of Contemporary Hospitality Management, Vol. 30 No. 11, pp. 3386-3411. https://doi.org/10.1108/IJCHM-11-2017-0714
Emerald Publishing Limited
Copyright © 2018, Emerald Publishing Limited