El artículo Exploiting Semantic Similarity for Named Entity Disambiguation in Knowledge Graphs, Ganggao Zhu & Carlos A. ha sido aceptado y publicado en Expert Systems with Applications, 101, 8-24. July 2018. This journal is indexed in JCR 2016 3.928 (Q1)
Esta semana tenemos lectura de TFGs y TFMs, estáis todos invitados. Puede ser muy interesante para los que estáis ahora comenzando el TFG o el TFM.
Antes de la lectura subiremos al canal de YouTube los videos.
El Grupo de Innovación Educativa del GSI "Un Enfoque de Aprendizaje basado en Retos para Técnicas en Análisis de Datos", cuyo objetivo es el desarrollo de competiciones de análisis de datos para las asignaturas de Máster en que participa en docencia. Como resultado del proyecto se generarán varios conjuntos de datos etiquetados para docencia así como un sistema de recogida de datos.
Este lunes 15 de enero de 2018 se ha celebrado la entrega de premios en el Paraninfo de la Universidad Politécnica de la Cátedra Ingeniero General. D. Antonio Remón y Zarco del Valle.
Felicidades a David García, que ha recibido el segundo premio al mejor Trabajo Fin de Grado por sul TFG titulado "Diseño e implementación de un modelo social de redes terroristas basado en agentes y técnicas de análisis de redes sociales".
The recent publication Enhancing deep learning sentiment analysis with ensemble techniques in social applications (Araque O., Corcuera-Platas I., Sanchez-Rada J.F., Iglesias C.A.) has reached the Most Downladed category in the journal Expert Systems with Applications (JCR, Q1, Impact Factor 3.928 in 2016).
Abstract
Deep learning techniques for Sentiment Analysis have become very popular. They provide automatic feature extraction and both richer representation capabilities and better performance than traditional feature based techniques (i.e., surface methods). Traditional surface approaches are based on complex manually extracted features, and this extraction process is a fundamental question in feature driven methods. These long-established approaches can yield strong baselines, and their predictive capabilities can be used in conjunction with the arising deep learning methods. In this paper we seek to improve the performance of deep learning techniques integrating them with traditional surface approaches based on manually extracted features. The contributions of this paper are sixfold. First, we develop a deep learning based sentiment classifier using a word embeddings model and a linear machine learning algorithm. This classifier serves as a baseline to compare to subsequent results. Second, we propose two ensemble techniques which aggregate our baseline classifier with other surface classifiers widely used in Sentiment Analysis. Third, we also propose two models for combining both surface and deep features to merge information from several sources. Fourth, we introduce a taxonomy for classifying the different models found in the literature, as well as the ones we propose. Fifth, we conduct several experiments to compare the performance of these models with the deep learning baseline. For this, we use seven public datasets that were extracted from the microblogging and movie reviews domain. Finally, as a result, a statistical study confirms that the performance of these proposed models surpasses that of our original baseline on F1-Score.
