A5091757548- Sentiment Analysis and Opinion Mining
- Advanced Text Analysis Techniques
- Topic Modeling
- Natural Language Processing Techniques
- Text and Document Classification Technologies
- Privacy-Preserving Technologies in Data
- Complex Network Analysis Techniques
- Adversarial Robustness in Machine Learning
- Journalism and Media Studies
- Spam and Phishing Detection
- Misinformation and Its Impacts
- Hate Speech and Cyberbullying Detection
- Cultural and political discourse analysis
- Digital Communication and Language
- Spanish Linguistics and Language Studies
- E-Learning and Knowledge Management
- Domain Adaptation and Few-Shot Learning
- Media and Digital Communication
- Communication and COVID-19 Impact
- Terrorism, Counterterrorism, and Political Violence
- Cryptography and Data Security
- Humor Studies and Applications
- Educational Outcomes and Influences
- Web Data Mining and Analysis
- Computational and Text Analysis Methods
Universidad de Jaén
2011-2024
Instituto Andaluz de Ciencias de la Tierra
2018-2023
Universidad de Granada
2018-2023
Cardiff University
2019
Ubiquitous Energy (United States)
2017
Technical University of Darmstadt
2017
Abstract In recent years, the interest among research community in sentiment analysis (SA) has grown exponentially. It is only necessary to see number of scientific publications and forums or related conferences understand that this a field with great prospects for future. On other hand, Twitter boom boosted investigation area due fundamentally its potential applications areas such as business government intelligence, recommender systems, graphical interfaces virtual assistance. However,...
Jose Camacho-collados, Kiamehr Rezaee, Talayeh Riahi, Asahi Ushio, Daniel Loureiro, Dimosthenis Antypas, Joanne Boisson, Luis Espinosa Anke, Fangyu Liu, Eugenio Martínez Cámara. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. 2022.
Polarity classification is a well-known Sentiment Analysis task. However, most research has been oriented towards developing supervised or unsupervised systems without paying much attention to certain linguistic phenomena such as negation. In this paper we focus on specific issue in order demonstrate that dealing with negation can improve the final system. Although find some studies of detection, them deal English documents. On contrary, our study focused scope Spanish Analysis. Thus, have...
Extremism has grown as a global problem for society in recent years, especially after the apparition of movements such jihadism. This and other extremist groups have taken advantage different approaches, use Social Media, to spread their ideology, promote acts recruit followers. The discourse, therefore, is reflected on language used by these groups. Natural processing (NLP) provides way detecting this type content, several authors make it describe discriminate discourse held groups, with...
Every day more companies are interested in users’ opinions about their products or services. Also, every there users that search for reviews on the web before purchasing a product. These and not satisfied with knowing overall sentiment of product, they want finer knowledge opinions. Owing to this fact, researchers working analysis at aspect-level. This paper describes an unsupervised approach aspect-based analysis, which aims identify aspects given target entities expressed each aspect. We...
The "wisdom of the crowd" theory states that a nonexpert crowd makes smarter decisions than reduced set experts. Social network platforms are source evaluations in natural language any topic, which may be considered as crowd. Decision-making (DM) models constrained by their inability processing large amounts language, those ones from social networks. We claim networks can enhance quality multiperson multicriteria DM models. Accordingly, we propose model guided sentiment analysis (SA), solves...
There exist a high demand to provide explainability artificial intelligence systems, where decision making models are included. This paper focuses on crowd using natural language evaluations from social media with the aim explainability. We present Explainable Crowd Decision Making based Subgroup Discovery and Attention Mechanisms (ECDM-SDAM) methodology as an posteriori explainable process that captures wisdom of crowds is naturally provided in opinions. It extracts opinions texts deep...
The automatic detection of disinformation presents a significant challenge in the field natural language processing. This task addresses multifaceted societal and communication issue, which needs approaches that extend beyond identification general linguistic patterns through data-driven algorithms. In this research work, we hypothesise text classification methods are not able to capture nuances they often ground their decision superfluous features. Hence, apply post-hoc explainability...
It was not until 2010 when businesses, politicians and people in general began to realize the potential of Twitter Spain. This fact has awoken research interest extraction knowledge from Twitter. paper aims fill gap lack resources for sentiment analysis Spanish by performing a study different features machine learning algorithms classifying polarity posts. The result is new corpus tweets called COST, we have carried out wide-ranging experiment which been used. Furthermore, tested influence...