Defining an Integrated and Computed Methodology Approach for Sentiment and Psychographic Analysis in Tourism Research

Abstract

High-performance computational resources and artificial intelligence-based tools can enhance tourism research and marketing. However, a formal methodological approach using digital technologies in this field is still missing. This research work presents the preliminary results of defining an integrated computational methodology in tourism research and marketing. In addition, the paper aims to provide guidelines for a methodological approach leveraging technological resources and Big Data. The proposed research method is based on online User-Generated Content (UGC) analysis through a psychographic approach based on the Big Five Model, Sentiment Analysis, and Machine Learning techniques. The study is supported by high-performance computing resources, artificial intelligence-based tools, and open-source Python-based software for data collection, text analysis, and psychographic attribution. Results show a remarkable performance of the BFF prediction model and confirm the role of personality in the tourists’ decision-making and appreciation of a site. Future developments of this project involve using the acquired structured dataset labeled with sentiment and psychographic attribution to create a further prediction model on tourist segments and appreciation as part of a marketing strategy in tourism management. Future research should push forward the development of further integrated and performing computer-based methodology in tourism research and marketing, leveraging the massive amount of data and the potential of high-performance computing techniques. The main contribution of this research effort is twofold: the definition of a general-purpose BFF/Sentiment Analysis methodology and the development of a prediction model from online UGC based on the Big Five personality traits in the tourism research scenario.