Sentiment Analysis Across Multiple African Languages: A Current Benchmark

TL;DR

This paper benchmarks transformer models for sentiment analysis across 14 African languages, highlighting the importance of language-specific data and models, and exploring cross-lingual transfer capabilities.

Contribution

It provides the first comprehensive benchmark of sentiment analysis models on African languages, comparing single-language and multilingual approaches, and analyzing cross-lingual transfer.

Findings

Language-specific models outperform general models.

More data improves per-language model performance.

No single model suits all languages; larger multilingual models can help smaller datasets.

Abstract

Sentiment analysis is a fundamental and valuable task in NLP. However, due to limitations in data and technological availability, research into sentiment analysis of African languages has been fragmented and lacking. With the recent release of the AfriSenti-SemEval Shared Task 12, hosted as a part of The 17th International Workshop on Semantic Evaluation, an annotated sentiment analysis of 14 African languages was made available. We benchmarked and compared current state-of-art transformer models across 12 languages and compared the performance of training one-model-per-language versus single-model-all-languages. We also evaluated the performance of standard multilingual models and their ability to learn and transfer cross-lingual representation from non-African to African languages. Our results show that despite work in low resource modeling, more data still produces better models on a per-language basis. Models explicitly developed for African languages outperform other models on all tasks. Additionally, no one-model-fits-all solution exists for a per-language evaluation of the models evaluated. Moreover, for some languages with a smaller sample size, a larger multilingual model may perform better than a dedicated per-language model for sentiment classification.