A Computational Approach to the Study of Portuguese Newspapers Published in Macau

This paper investigates the application of text classification methods to investigate diatopic variation in Portuguese journalistic texts. We compare the language used in Portuguese newspapers written in Brazil, Macau, and Portugal under the assumption that the more similar language varieties are, the more difficult it is for algorithms to discriminate between them. We present two sets of experiments: in the first one we use original texts and in the second one we use texts with blinded named entities to remove country-specific expressions. Our results indicate that the language of Portuguese newspapers published in Macau is substantially more similar to the language used in European newspapers than that used in Brazilian newspapers.