In the last few years thousands of scientific papers have investigated sentiment analysis, several startups that measure opinions on real data have emerged and a number of innovative products related to this theme have been developed. There are multiple methods for measuring sentiments, including lexical-based and supervised machine learning methods. Despite the vast interest on the theme and wide popularity of some methods, it is unclear which one is better for identifying the polarity (i.e., positive or negative) of a message. Accordingly, there is a strong need to conduct a thorough apple-to-apple comparison of sentiment analysis methods, as they are used in practice, across multiple datasets originated from different data sources. Such a comparison is key for understanding the potential limitations, advantages, and disadvantages of popular methods. This article aims at filling this gap by presenting a benchmark comparison of twenty-four popular sentiment analysis methods (which we call the state-of-the-practice methods). Our evaluation is based on a benchmark of eighteen labeled datasets, covering messages posted on social networks, movie and product reviews, as well as opinions and comments in news articles. Our results highlight the extent to which the prediction performance of these methods varies considerably across datasets. Aiming at boosting the development of this research area, we open the methods' codes and datasets used in this article, deploying them in a benchmark system, which provides an open API for accessing and comparing sentence-level sentiment analysis methods.
Migration has been proposed as one of the factors that shape cultural similarities across countries. However, studying the relationship between culture and migration has been challenging, in part because culture is difficult to quantify. The traditionally used survey questionnaires have a number of drawbacks, including that they are costly and difficult to scale to a large number of countries. To complement survey data, we propose the use of passively-collected digital traces from social media. We focus on food and drink as markers of a country’s culture. We then measure similarities between countries in terms of food and drink interests using aggregated data from the Facebook Advertising Platform. Methodologically, we offer approaches to measure the similarity between countries with both symmetric and asymmetric indices. Substantively, we assess the association between migration cultural similarity between countries by comparing our measure of cultural similarity with international migration data. In most countries, larger immigrant populations are associated with more similar food and drink preferences between their country of origin and the country of destination. Our results suggest that immigrants contribute to bringing the culture of their home countries to new countries. Moreover, our study identifies considerable variability in this pattern across countries.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.