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

2025-11-24

AI Summary

To address the severe scarcity of manually annotated data for sentiment analysis in low-resource African languages (e.g., Sepedi, Setswana) and English, this paper proposes a language-agnostic distant supervision approach that automatically assigns coarse-grained sentiment labels to tweets using only emoji and multilingual sentiment lexicons. This method is the first to be systematically applied across English, Sepedi, and Setswana, enabling the construction of SAfriSenti—the first publicly available multilingual sentiment corpus covering all three languages. Experimental evaluation shows automatic labeling accuracy of 66%, 69%, and 63% for English, Sepedi, and Setswana, respectively; on average, only 34% of labels require manual correction, substantially reducing annotation effort. The core contribution is a lightweight, cross-lingual distant supervision paradigm that requires no parallel corpora or language-specific resources, providing a scalable and deployable annotation infrastructure for low-resource language sentiment analysis.

Technology Category

• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining
• Machine Learning: Semi-Supervised Learning
• Humans and AI: Crowd Sourcing and Human Computation

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

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.

Problem

• Developing language-independent sentiment analysis for low-resource languages
• Reducing manual labeling effort through automatic distant supervision
• Evaluating emoji-based sentiment labeling accuracy across multiple languages

Innovation

• Language-independent sentiment labelling using distant supervision
• Leveraging sentiment-bearing emojis and words automatically
• Applied to English, Sepedi and Setswana tweets