AnnoABSA: A Web-Based Annotation Tool for Aspect-Based Sentiment Analysis with Retrieval-Augmented Suggestions
This tool addresses the problem of efficient and accurate data annotation for researchers and practitioners in sentiment analysis, though it is incremental as it builds on existing annotation and LLM methods.
The authors tackled the challenge of annotating data for Aspect-Based Sentiment Analysis by developing AnnoABSA, a web-based tool that offers customizable annotation and retrieval-augmented suggestions, resulting in a freely accessible open-source system that improves suggestion accuracy over time.
We introduce AnnoABSA, the first web-based annotation tool to support the full spectrum of Aspect-Based Sentiment Analysis (ABSA) tasks. The tool is highly customizable, enabling flexible configuration of sentiment elements and task-specific requirements. Alongside manual annotation, AnnoABSA provides optional Large Language Model (LLM)-based retrieval-augmented generation (RAG) suggestions that offer context-aware assistance in a human-in-the-loop approach, keeping the human annotator in control. To improve prediction quality over time, the system retrieves the ten most similar examples that are already annotated and adds them as few-shot examples in the prompt, ensuring that suggestions become increasingly accurate as the annotation process progresses. Released as open-source software under the MIT License, AnnoABSA is freely accessible and easily extendable for research and practical applications.