El mes pasado ha comenzado la segunda edición de las Becas GSI. Reunido el comité, seleccionó los siguientes candidatos:

  • Beca Profesor Gregorio Fernández de Iniciación a la investigación en aprendizaje automático y Big Data, a D. Alejandro López Martínez.
  • Beca Profesora Mercedes Garijo de iniciación a la investigación en tecnología de agentes, a D. Daniel Carlander-Reuterfelt Gallo.
  • Beca Profesor Fernando Sáez-Vacas de iniciación a la investigación en complejidad y sistemas sociales, a D. Daniel Vera Nieto.

The journal paper MoralStrength: Exploiting a moral lexicon and embedding similarity for moral foundations prediction, by Oscar Araque, Lorenzo Gatti, and  Kyriaki Kalimeri has been published at Knowledge-Based Systems (5.101 impact factor, Q1 JCR-2018).

The paper is available at the following URL:

A green open access version is available at arXiv.



Moral rhetoric plays a fundamental role in how we perceive and interpret the information we receive, greatly influencing our decision-making process. Especially when it comes to controversial social and political issues, our opinions and attitudes are hardly ever based on evidence alone. The Moral Foundations Dictionary (MFD) was developed to operationalize moral values in the text. In this study, we present MoralStrength, a lexicon of approximately 1,000 lemmas, obtained as an extension of the Moral Foundations Dictionary, based on WordNet synsets. Moreover, for each lemma it provides with a crowdsourced numeric assessment of Moral Valence, indicating the strength with which a lemma is expressing the specific value. We evaluated the predictive potentials of this moral lexicon, defining three utilization approaches of increased complexity, ranging from lemmas’ statistical properties to a deep learning approach of word embeddings based on semantic similarity. Logistic regression models trained on the features extracted from MoralStrength, significantly outperformed the current state-of-the-art, reaching an F1-score of 87.6% over the previous 62.4% (p-value < 0.01), and an average F1-Score of 86.25% over six different datasets. Such findings pave the way for further research, allowing for an in-depth understanding of moral narratives in text for a wide range of social issues.

Un sistema español detecta reseñas falsas en internet gracias a la inteligencia artificial


Investigadores de la Politécnica de Madrid logran un precisión del 80% para descubrir a los usuarios fake de la mano de la combinación de inteligencia artificial, lenguaje natural y aprendizaje automático

07 OCT. 2019
4 minutos

Hoy en día un gran número de usuarios consulta internet para decidir qué productos consumir, dónde irse de vacaciones, y hasta dónde se pueden encontrar los productos con la mejor relación calidad-precio. Pero, ¿cómo podemos saber si estas reseñas han sido redacatadas por usuarios verdaderos? Un equipo de investigadores del Grupo de Sistemas Inteligentes de la Universidad Politécnica de Madrid (UPM) ha desarrollado un sistema, con técnicas de inteligencia artificial, procesamiento de lenguaje natural y aprendizaje automático, que es capaz de detectar de manera automática 'revisores' falsos (fake reviewers) que muestran opiniones en internet.

Más información en

The journal paper DepecheMood++: a Bilingual Emotion Lexicon Built Through Simple Yet Powerful Techniques, by Oscar Araque, Lorenzo Gatti, Jacopo Staiano and Marco Guerini has been published at the IEEE Transactions on Affective Computing (6.288 Impact Factor, Q1 JCR-2018).

The paper is available at the following URL:

A green open access version is available at arXiv.

DOI: 10.1109/TAFFC.2019.2934444

Abstract: Several lexica for sentiment analysis have been developed; while most of these come with word polarity annotations (e.g., positive/negative), attempts at building lexica for finer-grained emotion analysis (e.g., happiness, sadness) have recently attracted significant attention. They are often exploited as a building block for developing emotion recognition learning models, and/or used as baselines to which the performance of the models can be compared. In this work, we contribute two new resources, that we call DepecheMood++ (DM++): a) an extension of an existing and widely used emotion lexicon for English; and b) a novel version of the lexicon, targeting Italian. Furthermore, we show how simple techniques can be used, both in supervised and unsupervised experimental settings, to boost performance on datasets and tasks of varying degree of domain-specificity. Also, we report an extensive comparative analysis against other available emotion lexica and state-of-the-art supervised approaches, showing that DepecheMood++ emerges as the best-performing non-domain-specific lexicon in unsupervised settings. We also observe that simple learning models on top of DM++ can provide more challenging baselines. We finally introduce embedding-based methodologies to perform a) vocabulary expansion to address data scarcity and b) vocabulary porting to new languages in case training data is not available.

En el contexto del proyecto europeo Citisim, desde el Grupo de Sistema Inteligentes hemos desarrollado una herramienta de simulación para situaciones de evacuación. En este sistema se realiza un modelado basado en agentes para la estudiar el comportamiento de ellos en distintas situaciones de evacuación. La noticia sobre el desarrollo aparece en la página web del proyecto