On the logistical difficulties and findings of Jopara Sentiment Analysis
Domain:
natural language processingRecord type:
paperdataset
Creator:
AgüVilLóp
Host:
This paper addresses the problem of sentiment analysis for Jopara, a code-switching language between Guarani and Spanish. We first collect a corpus of Guarani-dominant tweets and discuss on the difficulties of finding quality data for even relatively easy-to-annotate tasks, such as sentiment analysis. Then, we train a set of neural models, including pre-trained language models, and explore whether they perform better than traditional machine learning ones in this low-resource setup. Transformer architectures obtain the best results, despite not considering Guarani during pre-training, but traditional machine learning models perform close due to the low-resource nature of the problem. Accepted in the CALCS 2021 (co-located with NAACL 2021) - Fifth Workshop on Computational Approaches to Linguistic Code Switching, to appear (June 2021)
Similar
TwitterBan: A Sentiment Analysis of the Impact on NigeriansInfluence of ICT Support Practices and Logistical Management on the Performance of Oil Companies in KenyaANALYSIS OF LEARNING DIFFICULTIES WITH FRACTIONS IN THREE AFRICAN COUNTRIES: FOCUSING ON THE SCOPE, SEQUENCE AND MODELS OF FRACTIONS« Jopara : una metáfora guarani del mestizaje »MwangiMwaniki/Kenya-Power-Sentiment-Analysis-Model-on-the-TwitterInformation filtering of social media Amharic texts Based on Sentiment Analysis Information filtering of social media Amharic texts Based on Sentiment Analysis