Reheat Nachos for Dinner? Evaluating AI Support for Cross-Cultural Communication of Neologisms

2026-04-26

AI Summary

This study addresses the challenges non-native English speakers face in cross-cultural communication due to difficulties in accurately comprehending and appropriately using emerging English slang and neologisms. It presents the first systematic comparison of various AI-assisted support modalities—namely definition, rewriting, and paraphrasing—against traditional dictionary use in enhancing non-native speakers’ pragmatic competence with novel lexical items. Employing a human-factors experimental design, the research integrates native speaker evaluations of communicative quality with non-native speaker judgment tasks assessing contextual appropriateness. Results indicate that AI-generated paraphrasing significantly improves communication quality as rated by native speakers, whereas no significant differences emerge across support types in contextual appropriateness judgments. Furthermore, non-native speakers exhibit markedly weaker writing performance compared to native speakers and consistently overestimate their own abilities.

Technology Category

• Humans and AI: AI for Accessibility
• Natural Language Processing: Discourse, Pragmatics & Argument Mining
• Application Domains: Humanities & Computational Social Science

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• User Modeling, Personalization and Recommendation: Practical large-scale studies of user experience

Abstract

Neologisms and emerging slang are central to daily conversation, yet challenging for non-native speakers (NNS) to interpret and use appropriately in cross-cultural communication with native speakers (NS). NNS increasingly make use of Artificial Intelligence (AI) tools to learn these words. We study the utility of such tools in mediating an informal communication scenario through a human-subjects study (N=234): NNS participants learn English neologisms with AI support, write messages using the learned word to an NS friend, and judge contextual appropriateness of the neologism in two provided writing samples. Using both NS evaluator-rated communicative competence of NNS-produced writing and NNS' contextual appropriateness judgments, we compare three AI-based support conditions: AI Definition, AI Rewrite into simpler English, AI Explanation of meaning and usage, and Non-AI Dictionary for comparison. We show that AI Explanation yields the largest gains over no support in NS-rated competence, while contextual appropriateness judgments show indifference across support. NNS participants' self-reported perceptions tend to overestimate NS ratings, revealing a mismatch between perceived and actual competence. We further observe a significant gap between NNS- and NS-produced writing, highlighting the limitations of current AI tools and informing design for future tools.

Problem

• neologisms
• cross-cultural communication
• non-native speakers
• AI support
• communicative competence

Innovation

• AI-mediated communication
• neologisms
• cross-cultural communication
• human-subjects study
• communicative competence