NEU-ESC: A Comprehensive Vietnamese dataset for Educational Sentiment analysis and topic Classification toward multitask learning

TL;DR

This paper introduces NEU-ESC, a comprehensive Vietnamese educational dataset for sentiment and topic classification, and demonstrates the effectiveness of multitask learning with BERT, achieving high accuracy and benchmarking various models.

Contribution

The paper presents a new Vietnamese educational dataset with diverse and rich samples and explores multitask learning with BERT for improved classification performance.

Findings

Achieved up to 83.7% accuracy in sentiment classification.

Achieved up to 79.8% accuracy in topic classification.

Benchmark results show BERT-based models outperform other approaches.

Abstract

In the field of education, understanding students' opinions through their comments is crucial, especially in the Vietnamese language, where resources remain limited. Existing educational datasets often lack domain relevance and student slang. To address these gaps, we introduce NEU-ESC, a new Vietnamese dataset for Educational Sentiment Classification and Topic Classification, curated from university forums, which offers more samples, richer class diversity, longer texts, and broader vocabulary. In addition, we explore multitask learning using encoder-only language models (BERT), in which we showed that it achieves performance up to 83.7% and 79.8% accuracy for sentiment and topic classification tasks. We also benchmark our dataset and model with other datasets and models, including Large Language Models, and discuss these benchmarks. The dataset is publicly available at: https://huggingface.co/datasets/hung20gg/NEU-ESC.