Comparing Native and Non-native English Speakers' Behaviors in Collaborative Writing through Visual Analytics

2025-02-25

AI Summary

This study investigates behavioral differences between native (NS) and non-native (NNS) English speakers in collaborative writing to enhance collaboration quality and team inclusivity. Addressing the challenges of cross-linguistic data complexity and analytical uncertainty, we introduce COALA—a novel visual analytics tool integrating uncertainty-aware visualization, LLM-driven behavioral summarization, and multi-granularity modeling of writing actions—based on 162 real-world collaborative writing sessions. An expert user study (N=12) reveals systematic disparities between NS and NNS participants in editing tempo, feedback response latency, and textual restructuring strategies. Our work advances model interpretability and cross-linguistic collaboration insights, while identifying critical functional requirements for AI-augmented writing tools: dynamic adaptation to linguistic backgrounds and equitable support for diverse contributors.

Technology Category

• Humans and AI: Human-AI Collaboration / Human-AI Teaming
• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search

Abstract

Understanding collaborative writing dynamics between native speakers (NS) and non-native speakers (NNS) is critical for enhancing collaboration quality and team inclusivity. In this paper, we partnered with communication researchers to develop visual analytics solutions for comparing NS and NNS behaviors in 162 writing sessions across 27 teams. The primary challenges in analyzing writing behaviors are data complexity and the uncertainties introduced by automated methods. In response, we present extsc{COALA}, a novel visual analytics tool that improves model interpretability by displaying uncertainties in author clusters, generating behavior summaries using large language models, and visualizing writing-related actions at multiple granularities. We validated the effectiveness of extsc{COALA} through user studies with domain experts (N=2+2) and researchers with relevant experience (N=8). We present the insights discovered by participants using extsc{COALA}, suggest features for future AI-assisted collaborative writing tools, and discuss the broader implications for analyzing collaborative processes beyond writing.

Problem

• Analyzing NS and NNS collaborative writing behaviors
• Developing visual analytics for writing dynamics
• Enhancing model interpretability in collaborative writing

Innovation

• Visual analytics for behavior comparison
• COALA enhances model interpretability
• Multi-granular writing action visualization