Gonzalo Martínez, Javier Conde, Pedro Reviriego, Marc Brysbaert
{"title":"AI-generated estimates of familiarity, concreteness, valence, and arousal for over 100,000 Spanish words.","authors":"Gonzalo Martínez, Javier Conde, Pedro Reviriego, Marc Brysbaert","doi":"10.1177/17470218241306694","DOIUrl":null,"url":null,"abstract":"<p><p>This study investigates whether estimates of familiarity, valence, arousal, and concreteness based on artificial intelligence (AI) are useful alternatives to word counts and human ratings in Spanish. We replicate and extend previous findings in English and show that GPT-4o is effective in estimating these word features. Validity checks even suggest that AI-generated estimates sometimes outperform traditional measurements. The ability to generate AI estimates for large numbers of words at low cost simplifies the process of obtaining word features and provides a new resource for researchers working in Spanish. We provide Excel lists of the collected word features, which can be freely used for research and teaching.</p>","PeriodicalId":20869,"journal":{"name":"Quarterly Journal of Experimental Psychology","volume":" ","pages":"17470218241306694"},"PeriodicalIF":1.5000,"publicationDate":"2024-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Quarterly Journal of Experimental Psychology","FirstCategoryId":"102","ListUrlMain":"https://doi.org/10.1177/17470218241306694","RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"PHYSIOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
This study investigates whether estimates of familiarity, valence, arousal, and concreteness based on artificial intelligence (AI) are useful alternatives to word counts and human ratings in Spanish. We replicate and extend previous findings in English and show that GPT-4o is effective in estimating these word features. Validity checks even suggest that AI-generated estimates sometimes outperform traditional measurements. The ability to generate AI estimates for large numbers of words at low cost simplifies the process of obtaining word features and provides a new resource for researchers working in Spanish. We provide Excel lists of the collected word features, which can be freely used for research and teaching.
期刊介绍：
Promoting the interests of scientific psychology and its researchers, QJEP, the journal of the Experimental Psychology Society, is a leading journal with a long-standing tradition of publishing cutting-edge research. Several articles have become classic papers in the fields of attention, perception, learning, memory, language, and reasoning. The journal publishes original articles on any topic within the field of experimental psychology (including comparative research). These include substantial experimental reports, review papers, rapid communications (reporting novel techniques or ground breaking results), comments (on articles previously published in QJEP or on issues of general interest to experimental psychologists), and book reviews. Experimental results are welcomed from all relevant techniques, including behavioural testing, brain imaging and computational modelling.
QJEP offers a competitive publication time-scale. Accepted Rapid Communications have priority in the publication cycle and usually appear in print within three months. We aim to publish all accepted (but uncorrected) articles online within seven days. Our Latest Articles page offers immediate publication of articles upon reaching their final form.
The journal offers an open access option called Open Select, enabling authors to meet funder requirements to make their article free to read online for all in perpetuity. Authors also benefit from a broad and diverse subscription base that delivers the journal contents to a world-wide readership. Together these features ensure that the journal offers authors the opportunity to raise the visibility of their work to a global audience.
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
