Detection of Loanwords in Angolan Portuguese: A Text Mining Approach

Angola is characterized by many different languages and social, cultural political realities, which had a marked effect on Angolan Portuguese (AP). Consequently, AP diatopic variation. One of the effects in loanwords imported from other languages. Our objective to analyze texts, lexical forms used conduct comparative study with European Portuguese, whose aim identify possible Angolan. This process was automated, as well identification cotexts all loanwords. In addition, we determine class each loanword language origin. Most come Kimbundu, although includes some languages, too. serves basis for preparation an regionalism dictionary. We note that more than 700 identified do not figure existing dictionaries.