Personalized Real-time Jargon Support for Online Meetings

2025-08-13

AI Summary

Domain-specific jargon in interdisciplinary conferences significantly impedes comprehension, participation, and peer recognition. Method: We propose and implement ParseJargon—the first large language model–based, personalized real-time jargon parsing system, integrating user profiling with lightweight interactive techniques to enable dynamic, context-aware term identification and explanation. Departing from generic approaches, we establish the “background-customized” paradigm, validated through a three-phase evaluation: diary studies, controlled experiments, and real-world deployment at academic conferences. Results: Personalized support significantly improves comprehension accuracy (+32%) and willingness to participate (p < 0.01), while demonstrating high usability and practical utility in authentic conference settings. Our core contribution lies in empirically establishing that jargon support must be individualized—and providing a scalable, technically grounded implementation pathway.

Technology Category

• Natural Language Processing: Discourse, Pragmatics & Argument Mining
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• User Modeling, Personalization and Recommendation: Practical large-scale studies of user experience
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Semantics and Knowledge: Applications of semantic technologies for improving search, browsing, recommendation, personalization

Abstract

Effective interdisciplinary communication is frequently hindered by domain-specific jargon. To explore the jargon barriers in-depth, we conducted a formative diary study with 16 professionals, revealing critical limitations in current jargon-management strategies during workplace meetings. Based on these insights, we designed ParseJargon, an interactive LLM-powered system providing real-time personalized jargon identification and explanations tailored to users' individual backgrounds. A controlled experiment comparing ParseJargon against baseline (no support) and general-purpose (non-personalized) conditions demonstrated that personalized jargon support significantly enhanced participants' comprehension, engagement, and appreciation of colleagues' work, whereas general-purpose support negatively affected engagement. A follow-up field study validated ParseJargon's usability and practical value in real-time meetings, highlighting both opportunities and limitations for real-world deployment. Our findings contribute insights into designing personalized jargon support tools, with implications for broader interdisciplinary and educational applications.

Problem

• Addressing jargon barriers in interdisciplinary online meetings
• Providing real-time personalized jargon identification and explanations
• Enhancing comprehension and engagement through tailored support

Innovation

• LLM-powered real-time jargon identification
• Personalized explanations based on individual backgrounds
• Interactive system for meeting comprehension enhancement