Neologism Learning Study Design Overview for NNS Writers
Рис. 1: Overview of our study design. We set up the communication scenario by having NNS participants learn neologisms and write messages to a hypothetical NS friend, Jo . During the main task, for each of the eight neologisms, they complete a three-stage procedure: ➊ Learning: Learn the neologism within a social media post with one of five randomly assigned support types (one control and four treatment); ➋ Production: Write a scenario and a message to Jo using the learned neologism; ➌ Comprehension: Rate the contextual appropriateness of the neologism in two provided writing samples. Each NNS
Paper context
Paper title: Reheat Nachos for Dinner? Evaluating AI Support for Cross-Cultural Communication of Neologisms 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. Passages referencing this figure: s this gap, we conduct a between-subjects human study with 234 NNS participants whose native languages are Spanish, German, or Chinese, along with 144 NS evaluators residing in the United States. We simulate a real-world scenario in which an NNS encounters a neologism in a social media post, learns the term with different types of support conditions, and uses it to communicate with an NS friend ( Figure 1 ). Motivated by how users typically employ AI tools when encountering new words (Xiao and Zhi, 2023 ; Klimova et al. , 2024 ) , we design four support conditions: (1) AI Definition: providing a dictionary-style definition; (2) AI Rewrite: rewriting the social media post into simpler English; (3) AI Explanation: requesting an explanation of meaning and usage; and (4) Non-AI Dictionary: con der-neutral name to avoid implicit assumptions; https://en.wikipedia.org/wiki/Jo_(given_name) . They first complete a practice session and then rate their familiarity with each neologism on a five-point Likert scale (1:Not at all, 5:Very well) (Asahara, 2019 ; Zheng, 2024 ) . For each neologism, they then complete a three-stage procedure to learn and perform tasks assessing their learning goals ( Figure 1 ): ➊ Learning stage. NNS participants learn a neologism presented in a social media post under a randomly assigned support condition. ➋ Production stage. Participants write (1) a brief scenario and (2) a message using the learned neologism to their NS friend, Jo . To support understanding, NS-produced writing samples are shown during the practice session, and four keywords per neologism,
