Abstract

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 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, aiming at identifying the possible loanwords in Angolan Portuguese. This process was automated, as well as the identification of all loanwords' cotexts. In addition, we determine the lexical class of each loanword and the Angolan language of its 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 preparing an Angolan regionalism dictionary. We noticed that more than 700 identified loanwords do not figure in the existing dictionaries.

Abstract
This paper describes two different approaches to sentiment analysis. The first is a form of symbolic approach that exploits a sentiment lexicon together with a set of shifter patterns and rules. The sentiment lexicon includes single words (unigrams) and is developed automatically by exploiting labeled examples. The shifter patterns include intensification, attenuation/downtoning and inversion/reversal and are developed manually. The second approach exploits a deep neural network, which uses a pre-trained language model. Both approaches were applied to texts on economics and finance domains from newspapers in European Portuguese. We show that the symbolic approach achieves virtually the same performance as the deep neural network. In addition, the symbolic approach provides understandable explanations, and the acquired knowledge can be communicated to others. We release the shifter patterns to motivate future research in this direction.

Abstract

Abstract
Sentiment analysis is one of the most widely studied applications in NLP, but most work focuses on languages with large amounts of data. We introduce the first large-scale human-annotated Twitter sentiment dataset for the four most widely spoken languages in Nigeria-Hausa, Igbo, Nigerian-Pidgin, and Yoruba-consisting of around 30,000 annotated tweets per language, including a significant fraction of code-mixed tweets. We propose text collection, filtering, processing, and labeling methods that enable us to create datasets for these low-resource languages. We evaluate a range of pre-trained models and transfer strategies on the dataset. We find that language-specific models and language-adaptive fine-tuning generally perform best. We release the datasets, trained models, sentiment lexicons, and code to incentivize research on sentiment analysis in under-represented languages.