ASC analyzer: A Python package for measuring argument structure construction usage in English texts

2025-10-11

AI Summary

Current research on argument structure constructions (ASCs) in second-language (L2) English writing lacks scalable, systematic measurement tools. Method: This study develops a Python-based automated analytical framework integrating dependency parsing and constructional annotation to compute—fully automatically—50 fine-grained quantitative metrics, including ASC diversity, frequency, proportional distribution, and verb-construction association strength. Contribution/Results: The framework substantially enhances analytical reproducibility and scalability over manual coding. Empirical validation demonstrates robust correlations between the extracted ASC metrics and human L2 writing scores, confirming their predictive validity for writing quality. This work advances both theoretical linguistics and applied NLP by providing a methodologically rigorous, empirically grounded tool for ASC analysis in L2 writing research and automated writing assessment.

Technology Category

Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument MiningKnowledge Representation and Reasoning: ArgumentationMachine Learning: Evaluation and Analysis

Application Category

Search and Retrieval-Augmented AI: Web evaluation methodologies and metricsSecurity and Privacy: Large-scale security measurementsWeb Mining and Content Analysis: Web measurements

Abstract

Argument structure constructions (ASCs) offer a theoretically grounded lens for analyzing second language (L2) proficiency, yet scalable and systematic tools for measuring their usage remain limited. This paper introduces the ASC analyzer, a publicly available Python package designed to address this gap. The analyzer automatically tags ASCs and computes 50 indices that capture diversity, proportion, frequency, and ASC-verb lemma association strength. To demonstrate its utility, we conduct both bivariate and multivariate analyses that examine the relationship between ASC-based indices and L2 writing scores.

Problem

• Measuring argument structure construction usage in English texts
• Addressing limited tools for analyzing L2 proficiency systematically
• Automatically tagging ASCs and computing linguistic indices

Innovation

• Python package for automatic ASC tagging
• Computes 50 indices for diversity and frequency
• Analyzes relationships between ASC indices and proficiency