Detection of Loanwords in Angolan Portuguese: A Text Mining Approach

Abstract

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

Analyzing Character Networks in Portuguese-language Literary Works

“…Even so, the number of works considering content in other languages is increasing. The Portuguese language is widely spoken in the world, with over 230 million native speakers, 1 and NLP methods have been used for several applications using Portuguese-language content, including regional reading preferences discovery [Silva et al 2021a], detection of loanwords [Muhongo et al 2022], and genre classification [Scofield et al 2022].…”