AfriSenti: A Twitter Sentiment Analysis Benchmark for African Languages

TL;DR

This paper introduces AfriSenti, a comprehensive sentiment analysis benchmark dataset of over 110,000 tweets in 14 African languages, aiming to advance NLP research for Africa's diverse linguistic landscape.

Contribution

It provides the first large-scale, annotated sentiment dataset for multiple African languages, along with data collection, annotation methodology, and baseline experiments.

Findings

Over 200 participants in the shared task.

Baseline models show varying performance across languages.

The dataset facilitates future NLP research on African languages.

Abstract

Africa is home to over 2,000 languages from more than six language families and has the highest linguistic diversity among all continents. These include 75 languages with at least one million speakers each. Yet, there is little NLP research conducted on African languages. Crucial to enabling such research is the availability of high-quality annotated datasets. In this paper, we introduce AfriSenti, a sentiment analysis benchmark that contains a total of >110,000 tweets in 14 African languages (Amharic, Algerian Arabic, Hausa, Igbo, Kinyarwanda, Moroccan Arabic, Mozambican Portuguese, Nigerian Pidgin, Oromo, Swahili, Tigrinya, Twi, Xitsonga, and Yor\`ub\'a) from four language families. The tweets were annotated by native speakers and used in the AfriSenti-SemEval shared task (The AfriSenti Shared Task had over 200 participants. See website at https://afrisenti-semeval.github.io). We describe the data collection methodology, annotation process, and the challenges we dealt with when curating each dataset. We further report baseline experiments conducted on the different datasets and discuss their usefulness.