Cross-lingual Investigation of User Evaluations for Global Restaurants

Abstract

Twitter, as one of the most popular social network services, is now widely used to query public opinions. In this research, Twitter data, along with the reviews collected from review websites is used to carry out some basic, sentimental, and culture-based analysis, so as to figure out the cultural effects on user evaluations for global restaurants. This research is based on the authors’ previous work, which only considers posts and reviews written in English. In this research, a language expansion is carried out that more than 30 languages are taken into account. By using a range of new and standard features, a series of classifiers are trained and applied in the later steps of sentiment analysis, through which some informative results are obtained considering the relationship between user evaluations and cultural backgrounds.