Tipo: artículo

Metodología: estudio empírico

Temas: CALL/ELAO

Resumen:

Texto completo

Word sense awareness is a feature which has not yet been implemented in most Computer-Assisted Language Learning (CALL) environments or in computer-readable resources for pedagogical purposes such as graded word lists. The current study aims to contribute to filling this gap by presenting a word sense disambiguation (WSD) method which relies on a tailor-made sense inventory, exploits readily available large language models, and only requires a limited number of prototypical examples sentences as manually curated data. The methodology is evaluated on a set of 74 lexically ambiguous items, with a Spanish language for specific purposes course as the target setting. With weighted F1 scores up to...

Ver ficha completa

Tipo: artículo

Metodología: estudio empírico

Temas: inteligencia artificial

Resumen:

Texto completo

Even before the age of artificial intelligence, automated scoring received considerable attention in educational measurement. However, its application to constructed response (CR) items in international large-scale assessments (ILSAs) has remained a challenge, primarily due to the difficulty of handling multilingual responses spanning many languages. This study addresses this challenge by investigating two machine learning approaches — supervised and unsupervised learning — for scoring multilingual responses. We explored various scoring methods to assess three science CR items from TIMSS 2023 across all participating countries and 42 languages. The results showed that the supervised...

Ver ficha completa

Tipo: artículo

Metodología: estudio empírico

Temas: inteligencia artificial

Resumen:

Texto completo

Feedback is a crucial element of a student's learning process. It enables students to identify weaknesses and improve self-regulation. However, studies show this to be an area of great dissatisfaction in higher education. With ever-growing course participation numbers, delivering effective feedback is becoming an increasingly challenging task. The efficacy of feedback will depend on four levels of feedback; namely, feedback about the self, task, process or self-regulation. Hence, this paper explores the use of automated content analysis to examine feedback provided by instructors for feedback practices measured on self, task, process, and self-regulation levels. For this purpose, four...

Ver ficha completa

Tipo: artículo

Metodología: estudio empírico

Temas: inteligencia artificial

Resumen:

Texto completo

This study presents an innovative solution for evaluating university-level teaching quality using artificial intelligence (AI), focusing on key aspects such as clarity of explanation and lecture structure. Traditional student surveys, while valuable, are often subject to biases and lack the necessary granularity, creating a need for objective, scalable solutions that provide consistent results. We propose an automated framework utilizing advanced natural language processing (NLP) models to assess teaching quality based on lecture transcripts. The methodology combines AI-driven transcription, machine learning-based assessments, and correlation with institutional student evaluations to...

Ver ficha completa

Tipo: artículo

Metodología: estudio empírico

Temas: inteligencia artificial

Resumen:

Texto completo

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...

Ver ficha completa

Tipo: artículo

Metodología: estudio empírico

Temas: inteligencia artificial

Resumen:

Texto completo en HTML

Online learning and teaching increased in 2020, driven by the COVID-19 pandemic. As many researchers attempted to understand the impact stress had on the emotional behaviours and academic performance of students, most studies explored these pre- and during-COVID behaviours in the context of brick and mortar institutions transitioning to online delivery. There is an opportunity to compare the experiences of students in the MOOC environment in this period, particularly in terms of the difference of engagement, semantics and sentiment/stress behaviours in 2019 and 2020. In this study, we use a dataset from AdelaideX between this time period to identify the most significant features...

Ver ficha completa

Tipo: artículo

Metodología: estudio empírico

Temas: inteligencia artificial

Resumen:

Texto completo

Student feedback on teaching at the end of the semester is an important source of information for instructors to gain insights into the effectiveness of their teaching. There are usually two forms of student feedback: quantitative scores and qualitative feedback. Quantitative scores can usually be easily summarized, while the analysis of qualitative feedback is usually effort-intensive as it deals with text. To help instructors glean insights from students' qualitative feedback, many previous studies used unsupervised approaches (i.e., topic modelling) for topic extraction in student feedback. Although topic modelling enables automated detection of previously unseen topics with minimal...

Ver ficha completa

Tipo: artículo

Metodología: estudio empírico

Temas: inteligencia artificial

Resumen:

Texto completo

In primary schools, Lesen durch Schreiben (LdS; “reading through writing”, known internationally as inventive spelling) is a prevalent didactic method of reading and spelling instruction. In LdS, pupils learn writing through prolonged inventive spelling, meaning that only phonological but not orthographic spelling errors are corrected. Rigorous studies of the effectiveness of LdS are scarce and have delivered inconsistent results, casting doubt on the suitability of LdS for primary school instruction. Empirical investigations of writing acquisition methods are time-consuming, costly, and are plagued by methodological evaluation difficulties, such as separating method effects from other...

Ver ficha completa

Tipo: artículo

Metodología: estudio empírico

Temas: inteligencia artificial

Resumen:

Texto completo

Student course evaluations contain rich qualitative feedback in the form of comments written in response to open-ended questions. However, this qualitative data, which may be more nuanced and detailed than quantitative ratings, is often unexamined in both administrative and research settings due to the labor-intensive nature of manual analysis. We investigate whether large language models (LLMs), including BERT, RoBERTa, and OpenAI model variants, can accurately replicate human judgments of sentiment in these comments. We compare masked and generative language models, using both naïve and fine-tuned approaches, to analyze a curated dataset of 1000 de-identified course evaluation responses....

Ver ficha completa

Tipo: artículo

Metodología: revisión bibliográfica

Temas: inteligencia artificial

Resumen:

Texto completo

Text-based open-ended questions in academic formative and summative assessments help students become deep learners and prepare them to understand concepts for a subsequent conceptual assessment. However, grading text-based questions, especially in large (>50 enrolled students) courses, is tedious and time-consuming for instructors. Text processing models continue progressing with the rapid development of Artificial Intelligence (AI) tools and Natural Language Processing (NLP) algorithms. Especially after breakthroughs in Large Language Models (LLM), there is immense potential to automate rapid assessment and feedback of text-based responses in education. This systematic review adopts a...

Ver ficha completa