The EuroCALL Review - Vol 32, No 2 (2025) Generative Artificial Intelligence in Foreign Language Learning and Teacher Education

Tabla de contenidos

Editorial

Editorial

Research papers

Higher Education Language Teachers' Attitudes and Approaches to AI Integration into their Work
Enhancing Inclusivity in Swedish ESL Classrooms: Integrating Generative Artificial Intelligence for Personalised Learning
DeepSeek’s Feedback on Short Essay-Writing in EFL: Pre-service Primary School Teachers’ Perceptions
Exploring AI as a Tool to Improve the English Pronunciation of Spanish-Catalan Teenagers
GenAI Models as Keyword Rankers: A Learner-centred Case Study for L2 Spanish
Comparing ChatGPT and Authentic Discourse as L2 Academic Speaking Partners: A Corpus-based Analysis and Exploration of Pedagogical Applicability
Technostress and English Language Learning in the Age of Generative AI
Intelligent (but artificial) Feedback in Spanish as a Foreign Language: Evaluation of ChatGPT and Claude as Text Correction Tools
Alexa – Teach me Spanish: A Study of Autonomous Use of Voice-activated Personal Assistants for Language Learning

Reflective practice papers

Interacting with AI in Creative Translation Teaching: Exploring Subjectivity and Developing Style
Automatically Generated Subtitles and Closed Captions: ESP Students’ Perceptions of Artificial Intelligence Hallucinations
Exploring the Role of GenAI Tools on Student Motivation and Communicative Competence in the Spanish Classroom

Research and development

Content Adaptation for Language Learning: A Hybrid AI Approach

Review paper

A Systematic Review of Generative Artificial Intelligence-based Tools to Improve Oral Skills in English as a Foreign Language

URI permanente para esta colecciónhttps://riunet.upv.es/handle/10251/232075

Examinar

Mostrando 1 - 15 de 15

Access status: Abierto ,
Alexa Teach me Spanish: A Study of Autonomous Use of Voice-activated Personal Assistants for Language Learning
(Universitat Politècnica de València, 2025-12-26) Rosell-Aguilar, Fernando
[EN] Voice-activated Personal Assistants (VAPAs), such as Alexa or Siri, can be utilised for autonomous language learning purposes ranging from asking simple questions about the culture of the target language to interaction in the target language with the intelligent assistant. These technologies can help with tasks such as looking up words, spelling, and pronunciation checking, as well as motivating learners to produce output in their target language. However, VAPAs are primarily designed to be utilised in the user s first language rather than a second language, and learners often overlook their potential to assist in their language learning process. This paper reports on a study to gather data on university student use of VAPAs. The research questions asked students taking Spanish language modules at a UK Higher Education institution about their use of VAPAs for language learning. The results show that most participants own a device with a VAPA, and some use it for language learning purposes, although this is a relatively small proportion. They also identify potential further user engagement. The paper concludes that the potential of VAPAs for language learning needs to be included in the range of resources that students are directed to for autonomous language learning study and practice.
Access status: Abierto ,
Editorial
(2025-12-26) Gimeno-Sanz, Ana; Casañ-Núñez, Juan Carlos; Departamento de Lingüística Aplicada; Escuela Técnica Superior de Ingeniería Aeroespacial y Diseño Industrial; Grupo de Investigación para la Enseñanza de lenguas Asistida por Ordenador (CAMILLE)
Access status: Abierto ,
Higher Education Language Teachers' Attitudes and Approaches to AI Integration into their Work
(Universitat Politècnica de València, 2025-12-26) Korkealehto, Kirsi; Ohinen-Salvén, Maarit
[EN] This study investigates how language teachers at a Finnish higher education institution perceive and integrate artificial intelligence (AI) into their work. As AI technologies rapidly transform education, understanding language teachers' experiences provides crucial insights into the challenges and opportunities of AI adoption in language learning contexts. The data were collected through an online questionnaire with response rate of 81.82%. The questionnaire comprises multiple-choice questions and open-ended questions exploring AI usage and perceptions. The key findings are that teachers perceive AI as potentially beneficial for supporting learners with a good proficiency level, analysing text, and for grammar correction as well as individualised learning. However, teachers are concerned about AI making students too reliant on technology which reduces motivation to learn independently which in turn leads to superficial learning causing students to overestimate their proficiency level. Three categories of teacher type emerged in terms of teachers attitudes and frequency of AI use in their work: novice (33%), intermediate (40%), and advanced (27%) AI users with varying levels of integration and attitudes toward AI applications. This study suggests that teachers regard AI as having the potential to be a valuable tool in language learning, but teacher training and support are crucial for its effective implementation.
Access status: Abierto ,
Enhancing Inclusivity in Swedish ESL Classrooms: Integrating Generative Artificial Intelligence for Personalised Learning
(Universitat Politècnica de València, 2025-12-26) Mohammad Ali, Abrar
[EN] This study investigates the impact of Generative Artificial Intelligence (GAI), specifically ChatGPT, on personalised grammar instruction in English as a Second Language (ESL) settings. Using a 2x2 factorial design and a mixed-methods approach, the research examines how two dimensions of personalisation content (based on language proficiency) and topic (based on learner interests) affect student motivation, engagement, and perceived task suitability. A sample of 140 Swedish students was divided into four experimental groups to explore the independent and combined effects of these personalisation strategies. Results from MANOVA and observational data show that combining content and topic personalisation significantly enhances motivation and task completion rates, supporting the theoretical basis in Self-Determination Theory (SDT). The study introduces the Personalization-Motivation Integration Framework (PMIF), which conceptualizes how relevance and autonomy jointly drive engagement in AI-mediated learning. These findings suggest that GAI tools can play a pivotal role in inclusive, individualized education by aligning instructional content with learner needs and interests.
Access status: Abierto ,
DeepSeek' s Feedback on Short Essay-Writing in EFL: Pre-service Primary School Teachers' Perceptions
(Universitat Politècnica de València, 2025-12-26) Cerveró-Carrascosa, Abraham; Di Sarno-García, Sofia
[EN] Over the past few years, there has been a growing use of generative Artificial Intelligence (AI) tools to support the development of writing skills among language learners. However, limited attention has been given to the potential of AI in pre-service teacher (PST) education, and specifically, the tool DeepSeek has yet to be examined. This study, therefore, aims to investigate PSTs perceptions of the usefulness of DeepSeek's feedback on the production of a text following a task-based teaching intervention. Thirty-nine primary education pre-service teachers took part, they were first-year students from a Spanish university whose English proficiency ranged from A2 to B2. The task required them to write a short essay. Data were collected using a pre- and post-test with open-ended questions adapted from Di Sarno-García and Argüelles-Álvarez (in press), along with a focus group discussion, thus adopting a mixed-methods approach that triangulates quantitative and qualitative data. The results of the Wilcoxon signed-rank test indicated a statistically significant decline in some items, as well as a slight decrease in mean scores from pre- to post-test which are aligned with the participants contributions from the open-ended questionnaire and focus group. These findings suggest that DeepSeek may not have been as effective as anticipated in providing feedback on content and text organisation for this particular task. Nevertheless, participants reported that they found the tool helpful for improving grammar, vocabulary, and spelling in their texts.
Access status: Abierto ,
Exploring AI as a Tool to Improve the English Pronunciation of Spanish-Catalan Teenagers
(Universitat Politècnica de València, 2025-12-26) Palomo Martín, Marina; Romero Gallego, Joaquín
[EN] This study investigates how artificial intelligence (AI) can be used to improve the pronunciation skills of English as a foreign language (EFL) learners, with a specific focus on American English vowel sounds. After a brief introduction to AI concepts, the research discusses the importance of teaching and learning pronunciation, the complexities of the English vowel system, and the specific difficulties encountered by Spanish-Catalan speakers. Furthermore, the possible use of AI in second language acquisition (SLA) and in the language classroom is also addressed. To assess the efficacy of AI tools, Siri and the Speakometer app were tested with 24 Spanish-Catalan teenagers, divided into a control group using traditional methods and an experimental group using the Speakometer app. Both groups received identical explicit instruction on English vowel sounds over four sessions. All participants interacted with Siri before and after the intervention to assess AI s speech perception while being recorded for later analysis of the participants speech production. Since there were no significant differences between the groups in perception or production results before and after the intervention, the findings imply that, for this sample, current AI applications do not significantly help learners improve their English pronunciation. Additionally, the study found that stimulus type, as well as specific vowel sounds, affects AI comprehension, suggesting that existing AI tools have not yet reached the efficiency level needed to be used in EFL pronunciation practice.
Access status: Abierto ,
GenAI Models as Keyword Rankers: A Learner-centred Case Study for L2 Spanish
(Universitat Politècnica de València, 2025-12-26) Degraeuwe, Jasper
[EN] Frequency-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 ? and Kendall s weighted ? 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 potential for use in the real-life creation of domain-specific vocabulary lists for L2 learning purposes.
Access status: Abierto ,
Comparing ChatGPT and Authentic Discourse as L2 Academic Speaking Partners: A Corpus-based Analysis and Exploration of Pedagogical Applicability
(Universitat Politècnica de València, 2025-12-26) Sekitani, Koki; Ogura, Masaaki; Sato, Takeshi
[EN] This study examines the extent to which spoken academic English produced by the ChatGPT-4o model (ChatGPT) aligns with authentic discourse and is applicable for use in L2 speaking materials. As generative AI tools gain popularity among L2 learners for speaking practice, it is essential to assess the linguistic and discourse-level validity of such output. Ten dialogues generated by ChatGPT were compared with an authentic transcript of a doctoral dissertation defence from the Michigan Corpus of Academic Spoken English (MICASE) using a corpus linguistic and content analysis approach. Quantitative analyses revealed that ChatGPT produced language with higher lexical diversity, greater use of advanced vocabulary, and more complex syntax than the MICASE sample, but with lower readability. Content analysis showed that while ChatGPT simulated turn-taking and appropriate question answer sequences, it lacked features of spontaneous interaction such as clarification requests, topic shifts, and overlapping speech. Speaker roles in the generated texts were consistent but followed more scripted and idealized patterns. These findings suggest that ChatGPT can serve as a useful supplementary tool for academic speaking practice, especially in providing structured, high-level input. However, its limitations in simulating authentic interaction highlight the need for guided integration alongside real human dialogue. The study is expected to contribute to the growing body of research on AI-assisted language learning.
Access status: Abierto ,
Technostress and English Language Learning in the Age of Generative AI
(Universitat Politècnica de València, 2025-12-26) Dizon, Gilbert; Gold, Jason; Barnes, Ryan
[EN] The purpose of this study is to examine the effects of generative AI on technostress among second language (L2) English students at two Japanese universities. While the use of generative AI technologies in education is rapidly increasing, research on how these tools impact learners' psychological well-being particularly in L2 learning contexts remains limited. This study primarily aimed to explore students experiences of generative AI related technostress. In addition, a secondary analysis examining whether technostress levels varied by students language proficiency was conducted, although no significant differences were observed. A total of 100 L2 English students, 60 beginner learners and 40 intermediate-advanced learners, fully completed the survey, which consisted of Likert-scale and open-ended written response items. While the quantitative results indicated that the participants did not exhibit high levels of technostress, the qualitative findings suggested a more nuanced picture of the impact of AI-related technostress on university L2 students. Namely, the students were concerned about the accuracy of AI output and thus desired explicit training and guidance. These results indicate that while generative AI may not cause significant levels of technostress, the emerging technology still presents specific challenges that must be addressed. The article concludes with practical suggestions for language teachers and institutions so that they can better support L2 students AI literacy and reduce the risks of technostress.
Access status: Abierto ,
Intelligent (but artificial) Feedback in Spanish as a Foreign Language: Evaluation of ChatGPT and Claude as Text Correction Tools
(Universitat Politècnica de València, 2025-12-26) Brosa Rodríguez, Antoni
[EN] This research analyses the potential and limitations of two artificial intelligence models (ChatGPT 4 and Claude 3.7) as feedback tools for texts written by students of Spanish as a foreign language. Using selected texts from the CEDEL2 corpus, the study evaluates these models' ability to provide pedagogically appropriate corrections. The qualitative analysis focuses on four criteria: accuracy in error detection, clarity of explanations, pedagogical adequacy, and potential problems. Results reveal that both models show high precision in detecting basic errors but present significant limitations such as overcorrection and difficulties adapting explanations to the student's level. Claude stands out for its systematic structure, while ChatGPT excels in humanizing feedback. Based on these findings, we propose an integrated model to implement these tools in the Spanish language classroom, where the teacher maintains a crucial role as mediator, and we offer practical recommendations to maximize their benefits while minimizing their risks.
Access status: Abierto ,
Interacting with AI in Creative Translation Teaching: Exploring Subjectivity and Developing Style
(Universitat Politècnica de València, 2025-12-26) Greaves, Sara; Rangheard, Léo
[EN] This article presents two experiments with Artificial Intelligence (AI) in the context of creative translation, an English Studies course subject at Aix-Marseille University in France. The use of creative writing and translating exercises (culturally relocated texts, plurilingual writing, self-translation ), aims to enhance students subjective appropriation of their second language and to help them develop their own style. The first experiment uses multilingual text embeddings for self-assessment of a translated text. The second uses generative AI, which produces text. Since we are interested in subjective appropriation of a second language, the article reflects on the kind of language AI uses, with reference to psycholinguistic theory. While generative AI produces rapid outcomes, creative translation teaching focuses on process what if AI were harnessed as part of the process? The article suggests ways of building on current creative practice in translation teaching as we face the challenges of AI.
Access status: Abierto ,
Automatically Generated Subtitles and Closed Captions: ESP Students' Perceptions of Artificial Intelligence Hallucinations
(Universitat Politècnica de València, 2025-12-26) Bumber, Ana; Toffoli, Denyze
[EN] This article is an exploratory study which re-evaluates the use of automatically generated subtitles and closed captions inside and outside the classroom with the help of questionnaire responses from twenty-eight students of Chemical and Process Engineering who were learning English for Specific Purposes (ESP) as part of their compulsory classes. By focusing on AI errors in closed captions and subtitles this research explores an area that is presently absent from the literature. This article gives an insight into how students perceive the AI errors or hallucinations they encounter and establishes three learner profiles based on their answers. The findings show a large degree of autonomy in students use of captions and subtitles while at the same time giving insight into their beliefs about generative AI.
Access status: Abierto ,
Exploring the Role of GenAI Tools on Student Motivation and Communicative Competence in the Spanish Classroom
(Universitat Politècnica de València, 2025-12-26) García-Allén, Ana; Devo Colis, Alba; Martinez Loyola, Richard; Martinez Loyola, Gabriela
[EN] This study explores the integration of Generative Artificial Intelligence (GenAI) in an advanced Spanish language course, with a focus on learner motivation and communicative competence. Although GenAI tools, such as chatbots and adaptive feedback systems, have been increasingly implemented in higher education, their application in Spanish as a Foreign Language (SFL) classroom remains under-researched. The research involved 41 students from two sections of an advanced Spanish course at a Canadian university, one for foreign language learners and one for heritage speakers. Participants completed a pre-task questionnaire, engaged in a GenAI supported collaborative task, and reflected on their experiences through a post-task survey. The primary task involved using ChatGPT to gather cultural information about a Spanish-speaking country and create a promotional campaign. Data were collected using both quantitative (Likert-scale surveys) and qualitative (open-ended reflections) methods. Findings indicate that most students felt comfortable and motivated when using GenAI tools and perceived them as useful for accessing real-time feedback and supporting personalized learning. The task was described as engaging and well-organized, although some students found it too simple to fully challenge their language abilities. Participants also identified limitations, including concerns about content accuracy, overreliance, and the lack of cultural and emotional nuance in GenAI outputs. The study underscores the importance of task design, GenAI literacy, and the instructor s role when implementing GenAI tools in language instruction. It advocates for a hybrid approach that combines human expertise with GenAI capabilities to foster motivation, learner autonomy, and communicative competence, addressing an underexplored gap in the literature.
Access status: Abierto ,
Content Adaptation for Language Learning: A Hybrid AI Approach
(Universitat Politècnica de València, 2025-12-26) Arora, Jatin; Elgort, Irina; Zhao, Junhong
[EN] In learning a foreign language, access to comprehensible input is a critical success factor. However, at early stages, when learners are still below an intermediate-proficiency level, finding level-appropriate and engaging materials is highly problematic. Although the Internet abounds in text and multimedia materials in many languages, most of them are too difficult to be useful for lower-proficiency language learners. The present project aimed to establish whether the affordances of large language models (LLMs) can be harnessed to turn authentic audio, video, and text materials into comprehensible input for independent elementary-level language learners. The present article reports on the outcomes of a research and development project that adopts a hybrid approach to simplifying authentic materials, combining affordances of LLMs with careful prompt engineering and rule-based refinement. The article details the hybrid sequential pipeline system and the results of two rounds of evaluation: language teacher ratings and automated text analysis indices. Based on the outcome of these evaluations, it is concluded that the proposed approach can provide an efficient way of simplifying authentic content for and by lower-proficiency language learners. Directions for future research and development are also proposed.
Access status: Abierto ,
A Systematic Review of Generative Artificial Intelligence-based Tools to Improve Oral Skills in English as a Foreign Language
(Universitat Politècnica de València, 2025-12-26) López-Molines, Lola
[EN] The emergence of artificial intelligence (AI) and chatbots has completely revolutionised language teaching practices. The power AI holds in EFL language instruction is evident: supporting students through material creation, providing continuous feedback, and facilitating tailored learning pathways, offering greater autonomy, creativity, and confidence. Through scaffolding, student-centred strategies, and inquiry-based approaches, AI facilitates and ensures an inclusive, adapted educational experience for all students, regardless of their levels, needs, or interests (Dennis, 2024; Lee et al., 2024; Mai & Carson-Berndsen, 2024; Sayed et al., 2024). Chatbots play a vital and multifaceted role in the development of EFL oral skills, enabling tailored and targeted instruction in pronunciation, vocabulary, grammar, and other communicative aspects essential for successfully navigating real-life communicative situations (Fathi et al., 2024; Tai & Chen; 2024). They provide instant feedback, continuous accessibility and personalised learning strategies, contributing not only to enhanced language accuracy but also to fostering learners' confidence, motivation, and autonomy in communicative situations, helping students address and overcome specific linguistic challenges (Zou et al., 2024). Nonetheless, despite their potential, AI tools also present various challenges and complexities that must be considered to ensure their effective use, such as a lack of context, coherence, or meaningful interaction (Shikun et al., 2024). Thus, this paper presents a systematic review of 14 relevant studies from the Web of Science (WOS) and Scopus databases, focusing on AI and EFL oral skills. It examines the impact of AI chatbots on the oral skill acquisition process, identifying key areas for further exploration. Consequently, the following study aims to contribute to current research in the field by exploring the multiple possibilities of these advanced tools, enhancing ELT practices and providing learners with a more holistic and higher-quality education.

Examinar

Envíos recientes