Noticias

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 https://innovadores.larazon.es/es/not/un-sistema-espanol-detecta-resenas-falsas-en-internet-gracias-a-la-inteligencia-artificial

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: https://ieeexplore.ieee.org/document/8798675

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 http://www.citisim.org/category/blog/

 

Hola,

Estas semanas se leen varios trabajos fin de titulación, estáis todos invitados a las lecturas.

 

El jueves 4/7/2019 en el aula B225, los TFGs:

  • 9:00 Fernando Loro, "Development of Intrusion Detection Models for CyberSecurity in Computer Networks applying Machine Learning Algorithms"
  • 10:20 Adrián González, "Design and development of a developer sentiment analysis system based on GitHub commit comments"
  • 10:40 Luis Caballero, "Development of a Mobile Nutritional Assistant for Supermarkets with the technology DialogFlow"
  • 11:00 Alejandro López, "Design and development of gamified smart objects for museums based on automatically generated quizzes exploiting Linked Data. Application: Telecommunications Museum at ETSIT."

El viernes 5/7/2019 en el aula B225, los TFGs: 

  • 9:40 Pablo Lostao, "Development of a Mobile augmented reality virtual assistant for a smart office"
  • 10:00 Gonzalo Osende, "Design and Development of a song recommender system based on user experience and emotions"

El martes 9/7/2019 en el aula B223, el TFM:

  • 9:20, Fernando Benayas, "Design of an architecture for cyber-attack detection on an SDN environment"

El miércoles 10/7/2019 en el aula B222, el TFG:

  • 9:40, Luis García, "Design and Development of a Lexicon-based Emotion Classifier for the Sports Domain on Twitter"

El viernes 12/7/2019 en el aula B22, los TFMs:

  • 9:00 José Fernández, "Design of an Emotional Lighting System based on Sentiment Analysis of Twitter"
  • 9:20 Enrique Sánchez, "Design and Development of an Emotion-aware Learning Analytics system based on Machine Learning Techniques and Semantic Task Automation"
  • 9:40 Eduardo Merino, "Design and Development of a Social Choice Model Simulation for occupant welfare in Smart Buildings based on a Blockchain solution"