EduRABSA: An Education Review Dataset for Aspect-based Sentiment Analysis Tasks
Yan Cathy Hua, Paul Denny, Jörg Wicker, Katerina Taskova
2025-09-01
Summary
This paper introduces a new dataset and tool designed to help computers understand student feedback about courses, teachers, and universities. It focuses on a specific type of analysis called Aspect-Based Sentiment Analysis, which goes beyond just saying if feedback is positive or negative to pinpoint *what* students like or dislike.
What's the problem?
Analyzing student feedback is really hard to do automatically. While schools get tons of comments, turning those comments into useful information requires a lot of manual reading. Existing computer programs that try to do this are usually built for things like product reviews, not education, and there’s a lack of good, publicly available data specifically for training these programs in the education context. Plus, student data is sensitive, making it difficult to create and share datasets.
What's the solution?
The researchers created EduRABSA, a dataset containing student reviews labeled with specific aspects (like 'course content' or 'teacher's explanation') and the sentiment expressed towards those aspects. They also built a tool, ASQE-DPT, that makes it easier for people to create similar labeled datasets. This tool allows annotators to label data for multiple tasks at once, streamlining the process.
Why it matters?
This work is important because it removes a major roadblock for researchers trying to use computers to analyze student feedback. By providing a public dataset and a helpful annotation tool, it encourages more research in this area, potentially leading to better insights into student experiences and improvements in education. It also promotes transparency and allows others to build upon their work.
Abstract
Every year, most educational institutions seek and receive an enormous volume of text feedback from students on courses, teaching, and overall experience. Yet, turning this raw feedback into useful insights is far from straightforward. It has been a long-standing challenge to adopt automatic opinion mining solutions for such education review text data due to the content complexity and low-granularity reporting requirements. Aspect-based Sentiment Analysis (ABSA) offers a promising solution with its rich, sub-sentence-level opinion mining capabilities. However, existing ABSA research and resources are very heavily focused on the commercial domain. In education, they are scarce and hard to develop due to limited public datasets and strict data protection. A high-quality, annotated dataset is urgently needed to advance research in this under-resourced area. In this work, we present EduRABSA (Education Review ABSA), the first public, annotated ABSA education review dataset that covers three review subject types (course, teaching staff, university) in the English language and all main ABSA tasks, including the under-explored implicit aspect and implicit opinion extraction. We also share ASQE-DPT (Data Processing Tool), an offline, lightweight, installation-free manual data annotation tool that generates labelled datasets for comprehensive ABSA tasks from a single-task annotation. Together, these resources contribute to the ABSA community and education domain by removing the dataset barrier, supporting research transparency and reproducibility, and enabling the creation and sharing of further resources. The dataset, annotation tool, and scripts and statistics for dataset processing and sampling are available at https://github.com/yhua219/edurabsa_dataset_and_annotation_tool.