Towards Comprehensive Argument Analysis in Education: Dataset, Tasks, and Method

TL;DR

This paper introduces a comprehensive dataset and method for detailed argument analysis in education, emphasizing fine-grained relations and multi-dimensional structures to improve understanding and assessment of argumentative writing.

Contribution

It presents 14 new relation types for argument analysis and evaluates their effectiveness across three tasks, advancing beyond simplistic argument relation models.

Findings

Fine-grained annotations improve argument component detection.

Multi-dimensional analysis enhances understanding of argument structures.

Writing quality significantly impacts argument relation prediction.

Abstract

Argument mining has garnered increasing attention over the years, with the recent advancement of Large Language Models (LLMs) further propelling this trend. However, current argument relations remain relatively simplistic and foundational, struggling to capture the full scope of argument information, particularly when it comes to representing complex argument structures in real-world scenarios. To address this limitation, we propose 14 fine-grained relation types from both vertical and horizontal dimensions, thereby capturing the intricate interplay between argument components for a thorough understanding of argument structure. On this basis, we conducted extensive experiments on three tasks: argument component detection, relation prediction, and automated essay grading. Additionally, we explored the impact of writing quality on argument component detection and relation prediction, as well as the connections between discourse relations and argumentative features. The findings highlight the importance of fine-grained argumentative annotations for argumentative writing quality assessment and encourage multi-dimensional argument analysis.