[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-582240-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-582240-en":130},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","the-eurocall-review-volume-32-no-2-research-paper","The EuroCALL Review - Volume 32 - No. 2 - Research Paper","","Frequency-based word lists support general-purpose vocabulary learning for beginner and lower-intermediate L2 learners, but do not adequately serve advanced or specific-purpose learners. This study investigates Generative Artificial Intelligence (GenAI) models for automatically ranking topic-typical Spanish vocabulary. A dataset with four domain-specific subsets of 200 items (economics, health, law, migration) is created and ranked via zero-shot prompting. Rankings are correlated with gold-standard human judgments, using Kullback-Leibler divergence as a keyness baseline. Results show GenAI models (Gemma, Llama, Mistral) substantially outperform the baseline.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/the-eurocall-review-volume-32-no-2-research-paper/582240/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/the-eurocall-review-volume-32-no-2-research-paper/582240.png","ImageObject",300,407,{"name":42,"@type":43},"Ophelia","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-02","2026-10-15",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",6,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What research question does the paper address?","Question",{"text":63,"@type":64},"The paper examines whether GenAI models can automatically rank Spanish vocabulary items by topic typicality in a way that aligns with L2 learner judgments.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How is performance evaluated in the study?",{"text":68,"@type":64},"Evaluation is based on correlation between GenAI-based rankings and gold-standard human rankings, with Kullback-Leibler divergence used as the baseline keyness metric.",{"name":70,"@type":61,"acceptedAnswer":71},"Which GenAI models and topics are included?",{"text":72,"@type":64},"The study tests Gemma, Llama, and Mistral, using domain-specific vocabulary subsets for economics, health, law, and migration.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},582240,1792061702,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,105,110,114,119,122,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":102,"show_sort_weight":103,"slug":104},"Technology",50,"technology",{"id":106,"doc_module":4,"doc_module_name":25,"category_name":107,"show_sort_weight":108,"slug":109},7,"Healthcare",40,"healthcare",{"id":111,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":112,"slug":113},8,30,"research-report",{"id":115,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":111,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":139,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":144,"read_time":145,"preview_page_count":4},7971461741311,"https://ap-avatar.wpscdn.com/avatar/74000253aff267980c6?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779345379180704826","The EuroCALL Review  \nVolume 32, No. 2, 2025, 63-74 ISSN: 1695-2618  \n[https://doi.org/10.4995/eurocall.2025.23935](https://doi.org/10.4995/eurocall.2025.23935)  \nRESEARCH PAPER  \nGenAI Models as Keyword Rankers: A Learner-centred Case Study for L2 Spanish  \nJasper Degraeuwe   \nGhent University, Belgium  \n[Jasper.Degraeuwe@UGent.be](Jasper.Degraeuwe@UGent.be)  \nHow to cite this article:  \nDegraeuwe, J. (2025) . GenAI Models as Keyword Rankers: A Learner-centred Case Study for L2 Spanish. The EuroCALL Review, 32 (2), 63-74.  \n[https://doi.org/10.4995/eurocall.2025.23935](https://doi.org/10.4995/eurocall.2025.23935)  \nAbstract  \nFrequency-based word lists form an important part of general-purpose vocabulary learning courses aimed at beginner and (lower-)intermediate learners of a foreign/second language (L2) . For advanced learners and/or specific purposes, however, relying exclusively on these general word lists will be unlikely to lead to an adequate selection of vocabulary. As research in this latter area remains scarce (especially for languages other than English), the present study aims to fill (part of) the gap by investigating the use of Generative Artificial Intelligence (GenAI) models to automatically rank vocabulary items based on how typical they are of a given topic, focusing on Spanish as the target language. I compile a dataset containing four domain-specific subsets of 200 vocabulary items (for the topics economics, health, law, and migration) and analyse how well GenAI-based rankings of these vocabulary items (using zero-shot prompting) correlate with gold standard human rankings (provided by L2 learners) . As the evaluation baseline, I use the rankings obtained by means of the Kullback-Leibler divergence (i.e. , a statistical keyness measure based on word frequencies) . With a top average Spearman’s ρ and Kendall’s weighted τ of 0.73, this first-of-its-kind study demonstrates that the tested GenAI models (Gemma, Llama, and Mistral) outperform the baseline by a large margin, showing great  \npotential for use in the real-life creation of domain-specific vocabulary lists for L2 learning purposes.  \nKeywords  \nGenerative artificial intelligence; L2 Spanish; vocabulary learning; word lists  \n1. Introduction  \nDesigning vocabulary learning courses for foreign/second language (L2) learners is a multifaceted endeavour. Next to ensuring the course fits into the L2 learning course as a whole (e.g., using the LIST framework; Nation, 2022) and diversifying activity types (e.g., based on the four strands framework; Nation, 2007), course designers also need to decide on (1) which vocabulary items to include and (2) in which order they should be presented to the learners. For general-purpose vocabulary learning courses aimed at beginner or (lower-)intermediate L2 learners, there is a broad consensus that word frequency and range of occurrence (also called dispersion) should be used as the main selection criteria (Gries, 2021; Nation, 2022) . As a basis for this frequency-based selection, several wordlists have been created based on large corpora (e.g., West, 1953, for English and Davies and Hayward Davies, 2018, for Spanish) .  \nFor advanced learners and/or in a language for specific purposes setting, however, relying exclusively on these kinds of general word lists will be unlikely to result in a suitable selection of vocabulary items. To overcome this limitation, tailored-made vocabulary lists adapted to the purpose and target audience in question need to be created, for example based on specialised corpora (Coxhead, 2000) . In the present study, I analyse the potential of Generative Artificial Intelligence (GenAI) to rank vocabulary items according to their keyness (i.e. typicality) for a given semantic domain. I use raw word lists from specialised corpora as input data and apply my method to Spanish as the target language. Performance will be evaluated in terms of correlation with L2 learner judgements and compared against","cbCaim9jlzVRpzU8","https://ap.wps.com/l/cbCaim9jlzVRpzU8","pdf",397289,13,"English","# Abstract\n# 1. Introduction\n# 2. Related research\n## 2.1. Vocabulary learning and the role of word lists\n## 2.2. GenAI models as machine learning classifiers\n## 2.3. Keyness analysis","[{\"question\":\"What research question does the paper address?\",\"answer\":\"The paper examines whether GenAI models can automatically rank Spanish vocabulary items by topic typicality in a way that aligns with L2 learner judgments.\"},{\"question\":\"How is performance evaluated in the study?\",\"answer\":\"Evaluation is based on correlation between GenAI-based rankings and gold-standard human rankings, with Kullback-Leibler divergence used as the baseline keyness metric.\"},{\"question\":\"Which GenAI models and topics are included?\",\"answer\":\"The study tests Gemma, Llama, and Mistral, using domain-specific vocabulary subsets for economics, health, law, and migration.\"}]","The EuroCALL Review - Volume 32 - No. 2 - Research Paper | PDF",1792042878,33]