Using machine learning methods to avoid the pitfall of cognates and false friends in Spanish-Portuguese word pairs

The fact that 85% of the Portuguese lexicon contains Spanish cognates and that the linguistic structures of both languages are highly coincident is believed to be an advantage for the Spanish speaker who learns Portuguese. However, these similarities have some negative aspects in the learning of Portuguese, such as, the pitfall of false friends, since about 20% of cognates are false. The aim of this article is to identify cognates and false friends between Spanish and Portuguese automatically to build dictionaries of these words. One of the uses for these dictionaries is to support scientific writing tools, which can help lower barriers for Spanish speakers when they write in Portuguese.