Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 4
Encontrada(s) 1 página(s)

RODIN. Repositorio de Objetos de Docencia e Investigación de la Universidad de Cádiz
Publicación Artículo científico (JournalArticle)

Exploring the possibilities of CoSpaces to create Virtual Reality environments for foreign language learning

  • Berns, Anke
  • Valero Franco, Concepción
  • Sánchez-Reyes, Salvador
The recent Covid-19 pandemic has presented teachers with new challenges, high- lighting the need for innovation, renovation, and increased digitisation across all areas of education, including foreign language learning. At the same time, the increasing advances in Extended Reality (XR) together with the availability of authoring tools have created new opportunities to support the teaching/learning process. However, research suggests that many educators are still reluctant to integrate such technologies into their teaching syllabus. In this context and with the idea of encouraging especially language teachers at A1/A2 level to explore the possibilities of creating novel learning environments using technologies such as Virtual Reality (VR), in the current study we will share our experience regarding the use of authoring tools and the design and implementation of a VR language learning app created with CoSpaces. The latter is a freely available authoring tool which allows teachers with no specific programming skills to easily create VR environments in line with their teaching needs. The study consists of two main parts: the first focuses on describing CoSpaces as an authoring tool and our expe- rience as developers of a VR app. The second shows the tool’s functioning and offers those unfamiliar with it a short introduction. It concludes with evaluating the app’s implementation and analysing teachers' and students' feedback., pp. 54-71
RODIN. Repositorio de Objetos de Docencia e Investigación de la Universidad de Cádiz
Publicación Capítulo o parte de un libro (BookPart)

Explainable Artificial Intelligence for Audio-based Detection of Emergency Vehicles

  • Balderas Díaz, Sara
  • Guerrero Contreras, Gabriel José
  • Muñoz Ortega, Andrés
  • Durães, Dalila
  • Novais, Paulo
With the increasing adoption of AI in safety-critical applications within urban environments, the interpretability of these systems is paramount. This study explores the application of Explainable Artificial Intelligence (XAI) techniques to enhance transparency in audio-based detection of emergency vehicle sirens, a crucial component in urban sound management. Adopting methods such as SHAP (SHapley Additive exPlanations) values, Permutation Feature Importance, and model-specific feature scores, this research identifies key audio features, including mid-frequency spectral contrasts and targeted chroma components, which significantly help in distinguishing siren sounds among urban noise. The study examines various machine learning models, identifying K-Nearest Neighbors (KNN) and XGBoost as top performers; KNN excelled in class-specific precision, while XGBoost demonstrated strong cross-class discrimination. The findings highlight the potential of XAI in improving both accuracy and accountability for sound detection systems in safety-critical urban applications, advancing the deployment of transparent AI within smart city infrastructures.
RODIN. Repositorio de Objetos de Docencia e Investigación de la Universidad de Cádiz
Publicación Contribución de congreso (ConferenceOutput)

Embracing transition: The impact of emerging technologies on language learning pedagogies

  • Berns, Anke
  • Valero Franco, Concepción
Rapid technological advances require constant innovation and the creation of new products and services, the improvement of processes and the optimisation of resources. This constant evolution in all areas of society, including education, poses a persistent challenge to educators and institutions, requiring continuous adaptation of pedagogical models to accommodate technological advances while ensuring ethical and inclusive development. This paper outlines our journey as researchers, language teachers and instructional designers, focusing on the adoption of Extended Reality (XR) technologies and the development of several XR resources for our language learning courses. The resources were developed using two distinct end-user development (EUD) tools (e.g., CoSpaces, ARTutor) designed for non-programmers. This allowed for the creation of several apps specifically tailored to the needs of our language learners. Prior to their incorporation into the established corpus of learning materials, learners were provided with guidance on the technical and pedagogical functions of the apps. Subsequently, learners were encouraged to utilise them for their regular learning outside the classroom. Feedback was gathered using an adapted Technology Acceptance Model (TAM) questionnaire and several language assessment tests, which revealed a positive perception of the usability and usefulness of the resources for language learning. Data analysis using SPSSv27 highlighted the effectiveness of the resources, particularly in improving oral comprehension and production, although less impact was noted on writing skills. In addition, the study findings of the study highlight both the motivational and facilitative power of XR technologies to overcome traditional learning constraints and provide effective and engaging language learning experiences, as well as the transformative potential of XR and EUD tools in language teaching. The study advocates that teachers move from being passive users to proactive creators of XR-enhanced learning materials, and emphasises the importance of a balanced integration of digital and traditional resources tailored to learners’ needs.
RODIN. Repositorio de Objetos de Docencia e Investigación de la Universidad de Cádiz
Publicación Capítulo o parte de un libro (BookPart)

Enhancing Sentiment Analysis on Social Media: Integrating Text and Metadata for Refined Insights

  • Guerrero Contreras, Gabriel José
  • Balderas Díaz, Sara
  • Serrano Fernández, Alejandro
  • Muñoz Ortega, Andrés
Sentiment analysis has gained prominence in the digital era, particularly within social media contexts. This study explores the integration of metadata, such as reposts, favorites, or followers, alongside textual information for sentiment analysis. A dataset of posts in Spanish is created, filtering by a set of keywords (a total of 17) of interest to us. A total of 3,962 posts were collected along with their metadata. Then, they have been manually classified as positive, negative, and neutral, and processed. The research studies and compares different models like LightGBM, BERT, and a hybrid model combining BERT outputs with metadata. Evaluation metrics, such as F1-score and precision, were employed, revealing that the hybrid model achieved the highest F1-score of 69.4%, showcasing the effectiveness of merging text comprehension capabilities with contextual metadata. While the incorporation of metadata enhanced overall sentiment classification, precision varied across sentiment classes, with notable improvements in neutral and positive sentiments, over 16% and 8% respectively.