Date Published: June 14, 2018
Publisher: Public Library of Science
Author(s): Jose J. Padilla, Hamdi Kavak, Christopher J. Lynch, Ross J. Gore, Saikou Y. Diallo, Frank Emmert-Streib.
In this paper, we propose a sentiment-based approach to investigate the temporal and spatiotemporal effects on tourists’ emotions when visiting a city’s tourist destinations. Our approach consists of four steps: data collection and preprocessing from social media; visitor origin identification; visit sentiment identification; and temporal and spatiotemporal analysis. The temporal and spatiotemporal dimensions include day of the year, season of the year, day of the week, location sentiment progression, enjoyment measure, and multi-location sentiment progression. We apply this approach to the city of Chicago using over eight million tweets. Results show that seasonal weather, as well as special days and activities like concerts, impact tourists’ emotions. In addition, our analysis suggests that tourists experience greater levels of enjoyment in places such as observatories rather than zoos. Finally, we find that local and international visitors tend to convey negative sentiment when visiting more than one attraction in a day whereas the opposite holds for out of state visitors.
Tourism is one of the most important source of economic activities in cities and a significant item in the global economy . For many cities and countries tourism is crucial for economic sustainability and development . For instance, US cities like Las Vegas and Orlando have become some of the fastest developing metropolitan areas and many other cities are following suit . As of January 2018, the US Bureau of Labor and Statistics states that  Las Vegas area employment numbers are 29% leisure- and hospitality-related followed by 17% Trade/Transportation/Utilities and 14% Professional/Business Services, which are indirectly impacted by tourism.
The proposed approach consists of four major steps summarized in Fig 1. The first step is data collection and preprocessing in which attraction and visit datasets for the selected city are constructed and cleaned. The second step is the identification of visitors’ origins based on their self-reported locations. The third step is sentiment assessment that identifies positive and negative emotions in all tweets pertaining to attraction visits. The last step investigates attraction visit tweets according to several temporal and spatiotemporal dimensions and reports on the identified insights.
In this paper, we presented an approach using Twitter data to investigate the relationship between tourists’ feelings on their attraction visits in a city by investigating the temporal and spatiotemporal dimensions of their tweets. The approach comprises four major steps. First, data collection and preprocessing create an attraction dataset and capture and clean a visit dataset from Twitter for a selected city. Second, visitor identification takes place that labels users’ origin categories based on their self-reported locations. Third, positive and negative emotions in tweets pertaining to attraction visits are assessed and assigned numerical scores. Fourth, attraction visit tweet sentiments are investigated based on their temporal and spatiotemporal dimensions and insights from these investigations are reported. The temporal and spatiotemporal dimensions include: day of the year; meteorological season; day of the week; location sentiment progression; enjoyment measure; and multi-location sentiment progression.