IA y evaluación

Detalles Cerrar ✕

Tipo: artículo

Metodología: estudio empírico

Temas: inteligencia artificial tecnología educativa evaluación

Temas IA: IA y evaluación IA y aprendizaje estudio empírico

Resumen:

This study developed an interactive test dashboard with diagnosis and feedback mechanisms (ITD-DFM) that can generate visualized, rich, and high-quality test feedback for each learner’s learning reflection and review based on simultaneously considering test response time and correctness to assist students’ learning. A quasi-experimental research was conducted with 50 Grade 8 students from two classes in a public junior high school in Taiwan to assess the learning performance of ITD-DFM. One class with 26 students was assigned to the experimental group using the ITD-DFM to support learning, whereas the other class with 24 students was assigned to the control group using the traditional test...

Assessing students’ DRIVE: A framework to evaluate learning through interactions with generative AI

Manuel Oliveira, Carlos Zednik, Gunter Bombaerts (2025)

Detalles Cerrar ✕

Tipo: artículo

Metodología: trabajo teórico

Temas: inteligencia artificial evaluación educación superior

Temas IA: IA y evaluación

Resumen:

As generative AI (GenAI) transforms how students learn and work, higher education must rethink its assessment strategies. This paper introduces a conceptual framework, DRIVE, and a taxonomy to help educators evaluate student learning based on their interactions with GenAI chatbots. Although existing research maps student-GenAI interactions to writing outcomes, practice-oriented tools for assessing evidence of domain-specific learning beyond general AI literacy skills or general writing skills remain underexplored. We propose that GenAI interactions can serve as a valid indicator of learning by revealing how students steer the interaction (Directive Reasoning Interaction) and articulate...

Fairness perceptions of AI in grading systems: Examining how discontent with the status quo and outcome favorability reduce AI reluctance

S. Mo Jones-Jang, Myojung Chung, Jihyang Choi (2025)

Detalles Cerrar ✕

Tipo: artículo

Metodología: estudio empírico

Temas: inteligencia artificial evaluación creencias y actitudes de los estudiantes

Temas IA: IA y evaluación ética de la IA estudio empírico

Resumen:

This study investigates students' aversion to AI grading systems compared to human professors, focusing on how dissatisfaction with the current evaluation system and grade outcomes affect fairness perceptions. Drawing from 228 college students in South Korea, the experiment tested three hypotheses: (1) students show AI reluctance, (2) dissatisfaction with the current system mitigates the AI reluctance, and (3) this mitigation is contingent on whether students receive high or low grades. Results confirm a general aversion to AI graders. Yet, students who are dissatisfied with the status quo system displayed increased preference for AI graders, especially when receiving low grades. In...

Applying large language models and chain-of-thought for automatic scoring

Gyeong-Geon Lee, Ehsan Latif, Xuansheng Wu (2024)

Detalles Cerrar ✕

Tipo: artículo

Metodología: estudio empírico

Temas: inteligencia artificial evaluación grandes modelos de lenguaje

Temas IA: IA y evaluación modelos de lenguaje (LLM) prompts

Resumen:

This study investigates the application of large language models (LLMs), specifically GPT-3.5 and GPT-4, with Chain-of-Though (CoT) in the automatic scoring of student-written responses to science assessments. We focused on overcoming the challenges of accessibility, technical complexity, and lack of explainability that have previously limited the use of artificial intelligence-based automatic scoring tools among researchers and educators. With a testing dataset comprising six assessment tasks (three binomial and three trinomial) with 1,650 student responses, we employed six prompt engineering strategies to automatically score student responses. The six strategies combined zero-shot or few-...

Automatic proficiency scoring for early-stage writing

Michael Riis Andersen, Kristine Kabel, Jesper Bremholm (2023)

Detalles Cerrar ✕

Tipo: artículo

Metodología: estudio empírico

Temas: inteligencia artificial expresión escrita evaluación

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

Resumen:

In this work, we study the feasibility of using machine learning and natural language processing methods for assessing writing proficiency in Danish with respect to text construction, sentence construction, and use of modifiers. Our work is based on the analytical framework for scoring early writing proposed by Kabel et al. (2022), where each text is first annotated by a human expert according to a predefined coding scheme and subsequently scored using statistical Rasch modeling (Rasch, 1960). We investigate two different strategies for estimating these scores automatically: 1) we propose a system for identifying the central linguistic features automatically mimicking the role of the human...

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...

Effects of adaptive feedback generated by a large language model: A case study in teacher education

Annette Kinder, Fiona J. Briese, Marius Jacobs (2025)

Detalles Cerrar ✕

Tipo: artículo

Metodología: estudio empírico

Temas: inteligencia artificial feedback/retroalimentación grandes modelos de lenguaje

Temas IA: IA y evaluación modelos de lenguaje (LLM) chatGPT

Resumen:

This study investigates the effects of adaptive feedback generated by large language models (LLMs), specifically ChatGPT, on performance in a written diagnostic reasoning task among German pre-service teachers (n = 269). Additionally, the study analyzed user evaluations of the feedback and feedback processing time. Diagnostic reasoning, a critical skill for making informed pedagogical decisions, was assessed through a writing task integrated into a teacher preparation course. Participants were randomly assigned to receive either adaptive feedback generated by ChatGPT or static feedback prepared in advance by a human expert, which was identical for all participants in that condition, before...

La influencia de la IAGen en el proceso de evaluación: perspectivas actuales y futuras

Antonio Chenoll (2024)

Doblele. Revista de lengua y literatura

Detalles Cerrar ✕

Tipo: artículo

Metodología: trabajo teórico

Temas: inteligencia artificial evaluación tecnología educativa

Temas IA: IA y evaluación

Resumen:

En el campo de la evaluación didáctica, la popularización de la Inteligencia Artificial y la generación automática de textos ha comenzado a desempeñar un papel cada vez más relevante. Estas tecnologías tienen el potencial de transformar la manera en que se produce el proceso de evaluación tanto desde la perspectiva del alumno, como desde la perspectiva docente ofreciendo nuevas posibilidades y desafíos.

Se explora la influencia crucial de la IAGen en el proceso de evaluación, analizando tanto las perspectivas y aplicaciones actuales como las futuras implicaciones de este elemento interviniente del proceso de aprendizaje

Dynamic Feedback Mechanisms in Technology-Enhanced Language Learning: Examining Learner Engagement and Second Language Writing Outcomes

Li Sun, Chris Jordan (2026)

Language Teaching Research

Detalles Cerrar ✕

Tipo: artículo

Metodología: estudio empírico

Temas: feedback/retroalimentación expresión escrita inteligencia artificial

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

Resumen:

This 8-week randomized controlled experiment tested the different effects of adaptive artificial intelligence-based feedback versus static rule-based feedback on learner engagement and the acquisition of second language writing in 216 undergraduate students of English as a foreign language. The respondents were randomly divided into a control group that used standard automated feedback and an artificial intelligence-adaptive feedback group in which the responses were customized according to individual proficiency levels and error patterns. Validated analytical rubrics (intraclass correlation coefficient = 0.89) were used to evaluate the writing quality, and the involvement was assessed through self-reports and system logs weekly. The multilevel analysis of the growth curve revealed that there were high treatment effects, in that the...

Comparing Teacher and Artificial Intelligence Scoring in Writing Assessment: A Generalizability Theory Analysis

Burak Asma (2026)

Language Teaching Research

Detalles Cerrar ✕

Tipo: artículo

Metodología: estudio empírico

Temas: evaluación expresión escrita inteligencia artificial

Temas IA: IA y evaluación estudio empírico

Resumen:

This study examined the use of artificial intelligence tools, which have garnered significant attention in recent years, in the assessment and evaluation processes of language education. For this purpose, student essays were scored by Turkish middle school teachers and artificial intelligence tools both with and without the use of a rubric, and the findings were evaluated based on generalizability theory. Additionally, the research findings were shared with participants to gather qualitative data, which were analysed using the inductive thematic analysis method to support the research results. The findings revealed that in evaluations conducted without a rubric, teachers were limited in their...