GSI participates in SALLD-1 Workshop on Sentiment Analysis & Linguistic Linked Data hold  held in conjunction with LDK 2021 – 3rd Conference on Language, Data and Knowledge in Zaragoza.

the invited talk is titled "Sentiment Analysis meets Linguistic Linked Data: An overview of the state-of-the-art". More  information at

El pasado martes 15 de junio se llevó a cabo la actividad del proyecto Gamusino con alumnos de tercero de la ESO del colegio Comunidad Infantil Villaverde.

El proyecto Gamusino (GAMUSINO - Técnicas de Gamificación y Datos Enlazados para fomentar el aprendizaje en espacios museísticos. Aprende acerca de los sistemas inteligentes jugando.) tiene por objetivo prestar un servicio de formación en el campo de la Inteligencia Artificial. Para ello, se ha desarrollado una plataforma de gamificación que consiste en una aplicación móvil que brinda acceso a un juego de preguntas sobre Inteligencia Artificial para poner a prueba los conocimientos adquiridos, así como un servicio web API REST que da soporte a la aplicación y alberga las preguntas y estadísticas de juego de los usuarios.

Durante el desarrollo de la actividad con los alumnos del centro Comunidad Infantil Villaverde, se realizó una presentación sobre los conceptos básicos y más importantes de la Inteligencia Artificial. Al finalizar la presentación, los alumnos utilizaron sus terminales móviles para acceder al juego de preguntas confeccionadas para ellos.

La actividad fue recibida con gran entusiasmo e interés por parte de los alumnos.

The conference article "The Language of Liberty: A preliminary study", by Oscar Araque, Lorenzo Gatti, and Kyriaki Kalimeri, has been published in the Companion Proceedings of the Web Conference 2021 (WWW ’21 Companion).


Quantifying the moral narratives expressed in the user-generated text, news, or public discourses is fundamental for understanding individuals’ concerns and viewpoints and preventing violent protests and social polarisation. The Moral Foundation Theory (MFT) was developed precisely to operationalise morality in a five-dimensional scale system. Recent developments of the theory urged for the introduction of a new foundation, liberty. Being only recently added to the theory, there are no available linguistic resources to assess liberty from text corpora. Given its importance to current social issues such as the vaccination debate, we propose a data-driven approach to derive a liberty lexicon based on aligned documents from online encyclopedias with different worldviews. Despite the preliminary nature of our study, we show proof of the concept that large encyclopedia corpora can point out differences in the way people with contrasting viewpoints express themselves. Such differences can be used to derive a novel lexicon, identifying linguistic markers of the liberty foundation.

The article is available at

The article "An Ensemble Method for Radicalization and Hate Speech Detection Online Empowered by Sentic Computing" by Oscar Araque and Carlos A. Iglesias has been published in the Cognitive Computation journal (4.307 impact factor, JCR Q1 2019).

The paper can be found at this URL.


The dramatic growth of the Web has motivated researchers to extract knowledge from enormous repositories and to exploit the knowledge in myriad applications. In this study, we focus on natural language processing (NLP) and, more concretely, the emerging field of affective computing to explore the automation of understanding human emotions from texts. This paper continues previous efforts to utilize and adapt affective techniques into different areas to gain new insights. This paper proposes two novel feature extraction methods that use the previous sentic computing resources AffectiveSpace and SenticNet. These methods are efficient approaches for extracting affect-aware representations from text. In addition, this paper presents a machine learning framework using an ensemble of different features to improve the overall classification performance. Following the description of this approach, we also study the effects of known feature extraction methods such as TF-IDF and SIMilarity-based sentiment projectiON (SIMON). We perform a thorough evaluation of the proposed features across five different datasets that cover radicalization and hate speech detection tasks. To compare the different approaches fairly, we conducted a statistical test that ranks the studied methods. The obtained results indicate that combining affect-aware features with the studied textual representations effectively improves performance. We also propose a criterion considering both classification performance and computational complexity to select among the different methods.

The article "An Agent Based Simulation System for Analyzing Stress Regulation Policies at the Workplace" by Sergio Muñoz and Carlos A. Iglesias has been published in Journal of Computational Science, indexed by JCR Q1.

Abstract. Workplace stress has a significant impact on productivity, since keeping workers’ stress on an adequate level results a key factor for companies to increase their performance. While a high stress level may conduct to anxiety or absenteeism, a low level may also have undesirable consequences, such as lack of motivation. To identify and understand all the elements which interfere on workers’ stress results a key factor in order to improve workers’ performance. However, the complexity of human behavior increases the difficulty of recognizing the influence of these stressors and finding a way to regulate workers’ stress. This paper proposes the use of agent-based simulation techniques for addressing the challenge of analyzing workers’ behavior and stress regulation policies. The main contributions of the paper are: (i) the definition of a stress model that takes into account work and ambient conditions to calculate the stress and the productivity of workers; (ii) the implementation of this model in an agent-based simulation system, enabling the analysis of workplace stress and productivity for different stress regulation policies; (iii) the analysis of four different stress regulation policies; and (iv) the validation of the model with a sensitivity analysis and with its application to a living lab.

The article is available at: