IA y enseñanza-aprendizaje de lenguas

Detalles Cerrar ✕

Tipo: artículo

Metodología: estudio empírico

Temas: inteligencia artificial chatbots grandes modelos de lenguaje

Temas IA: IA y enseñanza-aprendizaje de lenguas chatbots modelos de lenguaje (LLM)

Resumen:

This study investigates the effectiveness, affordances, limitations, and family perceptions of conversational AI for home literacy learning vs. human. We developed a large language model (LLM)-powered conversational AI system, named Vovo, to teach children vocabulary and co-construct stories using structured literacy pedagogy. The system was tested in home environments over six weeks with 10 families and their children aged 3–7 (M = 5.4). Across 150 learning sessions, Vovo delivered structured literacy instruction as effectively as parents, though children achieved higher learning outcomes when learning with parents. Video analysis revealed Vovo's advantages in pedagogical consistency,...

Using ChatGPT for second language writing: Experiences and perceptions of EFL learners in Thailand and Vietnam

Joel C. Meniado, Duong Thi Thu Huyen, Nopparat Panyadilokpong (2024)

Detalles Cerrar ✕

Tipo: artículo

Metodología: estudio empírico

Temas: inteligencia artificial ChatGPT expresión escrita

Temas IA: IA y enseñanza-aprendizaje de lenguas chatGPT estudio empírico

Resumen:

This study explored the experiences and perceptions of Thai and Vietnamese EFL learners regarding the use of ChatGPT for second language (L2) writing. It aimed to contribute to the ongoing discourse on using generative Artificial Intelligence (GAI) tools to enhance L2 writing skills. Utilizing a mixed-methods research design with quantitative data gathered from 357 survey respondents from three educational institutions in Thailand and Vietnam and qualitative data from 16 interviewees from the same group of respondents, this study found that ChatGPT was perceived positively for L2 writing. Participants in the study found it a valuable tool for L2 writing, where its ability to generate ideas...

Exploring generative artificial intelligence preparedness among university language instructors: A case study

Lucas Kohnke, Benjamin Luke Moorhouse, Di Zou (2023)

Detalles Cerrar ✕

Tipo: artículo

Metodología: estudio empírico

Temas: inteligencia artificial creencias y actitudes de los profesores profesorado

Temas IA: IA y enseñanza-aprendizaje de lenguas estudio empírico

Resumen:

The integration of generative artificial intelligence (AI) in English language teaching presents opportunities and challenges for instructors. This study explores the attitudes of higher education English language instructors towards generative AI tools, their intentions to use them and the institutional support and professional development necessary to teach and learn with them. As the field continues to evolve rapidly, it is essential to comprehend the readiness of front-line language instructors. This qualitative interpretive study seeks to identify the digital competencies and pedagogical knowledge required to implement generative AI in education and provide guidance for the design of...

Impact of AI-generated storytelling vs. gamified learning on vocabulary retention and engagement in CALL environments

Ehsan Namaziandost, Fidel Çakmak (2025)

Detalles Cerrar ✕

Tipo: artículo

Metodología: estudio empírico

Temas: inteligencia artificial enseñanza/aprendizaje de vocabulario storytelling/narración

Temas IA: IA y enseñanza-aprendizaje de lenguas IA y creación de materiales estudio empírico

Resumen:

Artificial Intelligence (AI) and gamified learning have attracted interest from language educators and researchers in the field of teaching English as a Foreign Language (EFL) for their potential to enhance vocabulary acquisition outcomes. However, the relative effectiveness of AI-generated storytelling and gamified learning in EFL vocabulary acquisition has been underexplored. This study examines the influence of AI-generated storytelling and gamified learning on the vocabulary retention and engagement of intermediate-level EFL learners. Ninety participants were allocated among three groups: a control group that employed conventional vocabulary methods (e.g., rote memorization using...

A design-based approach to analysing student engagement with a GenAI-Enabled brainstorming app

Joanne Chia, Angela Frattarola (2025)

Detalles Cerrar ✕

Tipo: artículo

Metodología: estudio empírico

Temas: inteligencia artificial expresión escrita aprendizaje autónomo

Temas IA: IA y enseñanza-aprendizaje de lenguas IA y aprendizaje estudio empírico

Resumen:

While there are several “writing buddy” Generative Artificial Intelligence (GenAI) apps that check grammar and language usage, not many focus exclusively on enhancing the brainstorming process for writing across disciplines. To fill this gap, a team of staff and student assistants with programming and User Interface (UI) and User Experience (UX) expertise designed and prototyped a web app named “Waai,” which rhymes with ‘why,’ that could assist students throughout the writing process for a first-year general writing module for all undergraduate students at a Singaporean university.Utilising surveys, focus group discussions, and app data that shows the nature and type of student engagement...

“ChatGPT is the companion, not enemies”: EFL learners’ perceptions and experiences in using ChatGPT for feedback in writing

Mark Feng Teng (2024)

Detalles Cerrar ✕

Tipo: artículo

Metodología: estudio empírico

Temas: inteligencia artificial ChatGPT expresión escrita

Temas IA: IA y enseñanza-aprendizaje de lenguas chatGPT IA y evaluación

Resumen:

The present research was to bridge a research gap in comprehensively understanding students’ perceptions and experiences in utilizing ChatGPT for their writing process in English as a foreign language (EFL) context. The participants were 45 EFL learners in Macau. The study aimed to explore the potential impact of ChatGPT on writing, as well as their perceptions and experiences of ChatGPT in generating feedback for writing. A mixed-methods approach was employed, with quantitative data collected from a questionnaire and qualitative insights drawn from interviews conducted after a semester-long writing course. The findings supported the significant positive effects of AI assistance on writing...

LLMs do not grade essays like humans

Jerin George Mathew, Sumayya Taher, Anindita Kundu (2026)

Detalles Cerrar ✕

Tipo: artículo

Metodología: estudio empírico

Temas: inteligencia artificial expresión escrita evaluación

Temas IA: IA y enseñanza-aprendizaje de lenguas IA y evaluación modelos de lenguaje (LLM)

Resumen:

Large language models have recently been proposed as tools for automated essay scoring, but their agreement with human grading remains unclear. In this work, we evaluate how LLM-generated scores compare with human grades and analyze the grading behavior of several models from the GPT and Llama families in an out-of-the-box setting, without task-specific training. Our results show that agreement between LLM and human scores remains relatively weak and varies with essay characteristics. In particular, compared to human raters, LLMs tend to assign higher scores to short or underdeveloped essays, while assigning lower scores to longer essays that contain minor grammatical or spelling errors. We...

Transforming language education: A systematic review of AI-powered chatbots for English as a foreign language speaking practice

Jinming Du, Ben Kei Daniel (2024)

Detalles Cerrar ✕

Tipo: artículo

Metodología: revisión bibliográfica

Temas: inteligencia artificial chatbots expresión oral

Temas IA: IA y enseñanza-aprendizaje de lenguas chatbots revisión de bibliografía

Resumen:

Artificial intelligence chatbots recently caused a stir in the world by promising to transform education systems in a multitude of ways. To analyze pertinent publications in the SSCI journals, a systematic review was conducted for this study, which investigates the trends of chatbots in education studies, with a focus on English speaking skills. Despite the increasing use of AI-powered chatbots in education, limited research has explored how to develop the merits of AI-powered chatbots in English-speaking teaching or learning. The empirical evidence of chatbot applications from 24 research studies conducted in an English-speaking learning environment and published between 2017 and 2023 was...

Teacher feedback and ChatGPT feedback on Chinese university EFL learners’ English essay revision: A mixed-methods study

Feifei Han, Zehua Wang (2026)

Detalles Cerrar ✕

Tipo: artículo

Metodología: estudio empírico

Temas: inteligencia artificial feedback/retroalimentación ChatGPT

Temas IA: IA y enseñanza-aprendizaje de lenguas chatGPT IA y evaluación

Resumen:

Adopting mixed methods, the study compared teacher feedback and ChatGPT feedback on 35 Chinese university EFL learners’ essay revision, their Perceived Usefulness (PU) and Perceived Ease of Use (PEOU) and their perceived benefits and drawbacks of the feedback. Students wrote two English essays and received writing feedback from their English teacher and ChatGPT respectively. They revised one essay using teacher feedback and another using ChatGPT feedback. Upon revision, students responded to a 5-point Likert-scale questionnaire regarding PU and PEOU of the two types of feedback. The results showed that students obtained significantly higher scores on the revised essays using ChatGPT...

Assessing reading fluency in elementary grades: A machine learning approach

Gabriel Candido da Silva, Rodrigo Lins Rodrigues, Américo N. Amorim (2025)

Detalles Cerrar ✕

Tipo: artículo

Metodología: estudio empírico

Temas: inteligencia artificial comprensión lectora alfabetización

Temas IA: IA y enseñanza-aprendizaje de lenguas IA y evaluación estudio empírico

Resumen:

This study compares eleven widely used machine learning algorithms to identify the most accurate and comprehensive method for assessing children's reading fluency. Our fluency framework integrates three key dimensions: accuracy in word decoding, reading speed (words per minute), and prosody, which captures appropriate pausing and intonation during reading. Audio recordings from 2nd and 3rd grade students across 144 Brazilian schools were transcribed using the advanced Whisper ASR system, enabling automated extraction of fluency features. The research objective was to determine which algorithm best predicts fluency, considering diverse evaluation setups including binary classification (...