Language-Independent Sentiment Labelling with Distant Supervision: A Case Study for English, Sepedi and Setswana

TL;DR

This paper introduces a language-independent sentiment labelling method using emojis and words, effectively reducing manual labelling effort across English, Sepedi, and Setswana with promising accuracy.

Contribution

The study presents a novel automatic sentiment labelling approach that leverages emojis and words, applicable across multiple languages, especially low-resource African languages.

Findings

Achieved 66% accuracy for English tweets

Achieved 69% accuracy for Sepedi tweets

Achieved 63% accuracy for Setswana tweets

Abstract

Sentiment analysis is a helpful task to automatically analyse opinions and emotions on various topics in areas such as AI for Social Good, AI in Education or marketing. While many of the sentiment analysis systems are developed for English, many African languages are classified as low-resource languages due to the lack of digital language resources like text labelled with corresponding sentiment classes. One reason for that is that manually labelling text data is time-consuming and expensive. Consequently, automatic and rapid processes are needed to reduce the manual effort as much as possible making the labelling process as efficient as possible. In this paper, we present and analyze an automatic language-independent sentiment labelling method that leverages information from sentiment-bearing emojis and words. Our experiments are conducted with tweets in the languages English, Sepedi and Setswana from SAfriSenti, a multilingual sentiment corpus for South African languages. We show that our sentiment labelling approach is able to label the English tweets with an accuracy of 66%, the Sepedi tweets with 69%, and the Setswana tweets with 63%, so that on average only 34% of the automatically generated labels remain to be corrected.