Fernando Enríquez
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Fernando Enríquez has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Jose Antonio Troyano
Universidad de Sevilla
5 shared publications - Fermin L. Cruz
Department of Computer Languages and Systems, University of Seville, Seville, Spain
4 shared publications - F. Javier Ortega
Universidad de Sevilla
3 shared publications - Carlos G. Vallejo
Universidad de Sevilla, Escuela Técnica Superior de Ingeniería Informática, Avenida Reina Mercedes, s/n 41012 Sevilla, Spain
1 shared publication - Fernando J. Rendón-Segador
Departamento de Lenguajes y Sistemas Informáticos, Universidad de Sevilla, 41012 Sevilla, Spain
1 shared publication - Isidro Lloret
Department of Computer Engineering, Engineering School of Algeciras, University of Cádiz, Algeciras, Spain
1 shared publication
Latest Publications
- Open Access
- 29 September 2025
- Published by Springer Nature in Scientific Data
- Vol. 12 (1) , 1-9
Annotated Spanish general election debate transcriptions 1993-2023
The automatic analysis of political discourse requires systematic resources, particularly for non-Anglophone electoral debates, which differ from parliamentary sessions. This paper describes the DebatES dataset, containing manually reviewed transcriptions of nearly all Spanish nationally televised general election debates since 1993. Transcripts are segmented into turns and thematic blocks and include participant metadata. The data is enriched with linguistic-stylistic metrics derived from NLP analysis and extensive annotations combining Large Language Models and manual validation. Annotations cover turn topics, emotions, relevant entity mentions, electoral proposals, and factual claims. To facilitate access and reuse, the dataset is distributed in standard formats (XML and CSV), accompanied by interactive reports for visual exploration. This dataset provides a valuable resource for researchers in linguistics, political science, and language technologies, opening new avenues for studying the evolution of discourse, persuasive strategies, and ideological polarisation within the Spanish political context.
- 29 September 2025
- Published by Springer Nature in Scientific Data
- Vol. 12 (1) , 1-9
Open AccessAnnotated Spanish general election debate transcriptions 1993-2023
The automatic analysis of political discourse requires systematic resources, particularly for non-Anglophone electoral debates, which differ from parliamentary sessions. This paper describes the DebatES dataset, containing manually reviewed transcriptions of nearly all Spanish nationally televised general election debates since 1993. Transcripts are segmented into turns and thematic blocks and include participant metadata. The data is enriched with linguistic-stylistic metrics derived from NLP analysis and extensive annotations combining Large Language Models and manual validation. Annotations cover turn topics, emotions, relevant entity mentions, electoral proposals, and factual claims. To facilitate access and reuse, the dataset is distributed in standard formats (XML and CSV), accompanied by interactive reports for visual exploration. This dataset provides a valuable resource for researchers in linguistics, political science, and language technologies, opening new avenues for studying the evolution of discourse, persuasive strategies, and ideological polarisation within the Spanish political context.
- Open Access
- 3 July 2021
- Published by MDPI AG in Electronics
- Vol. 10 (13) , 1601
ViolenceNet: Dense Multi-Head Self-Attention with Bidirectional Convolutional LSTM for Detecting Violence
Introducing efficient automatic violence detection in video surveillance or audiovisual content monitoring systems would greatly facilitate the work of closed-circuit television (CCTV) operators, rating agencies or those in charge of monitoring social network content. In this paper we present a new deep learning architecture, using an adapted version of DenseNet for three dimensions, a multi-head self-attention layer and a bidirectional convolutional long short-term memory (LSTM) module, that allows encoding relevant spatio-temporal features, to determine whether a video is violent or not. Furthermore, an ablation study of the input frames, comparing dense optical flow and adjacent frames subtraction and the influence of the attention layer is carried out, showing that the combination of optical flow and the attention mechanism improves results up to 4.4%. The conducted experiments using four of the most widely used datasets for this problem, matching or exceeding in some cases the results of the state of the art, reducing the number of network parameters needed (4.5 millions), and increasing its efficiency in test accuracy (from 95.6% on the most complex dataset to 100% on the simplest one) and inference time (less than 0.3 s for the longest clips). Finally, to check if the generated model is able to generalize violence, a cross-dataset analysis is performed, which shows the complexity of this approach: using three datasets to train and testing on the remaining one the accuracy drops in the worst case to 70.08% and in the best case to 81.51%, which points to future work oriented towards anomaly detection in new datasets.
- 3 July 2021
- Published by MDPI AG in Electronics
- Vol. 10 (13) , 1601
Open AccessViolenceNet: Dense Multi-Head Self-Attention with Bidirectional Convolutional LSTM for Detecting Violence
Introducing efficient automatic violence detection in video surveillance or audiovisual content monitoring systems would greatly facilitate the work of closed-circuit television (CCTV) operators, rating agencies or those in charge of monitoring social network content. In this paper we present a new deep learning architecture, using an adapted version of DenseNet for three dimensions, a multi-head self-attention layer and a bidirectional convolutional long short-term memory (LSTM) module, that allows encoding relevant spatio-temporal features, to determine whether a video is violent or not. Furthermore, an ablation study of the input frames, comparing dense optical flow and adjacent frames subtraction and the influence of the attention layer is carried out, showing that the combination of optical flow and the attention mechanism improves results up to 4.4%. The conducted experiments using four of the most widely used datasets for this problem, matching or exceeding in some cases the results of the state of the art, reducing the number of network parameters needed (4.5 millions), and increasing its efficiency in test accuracy (from 95.6% on the most complex dataset to 100% on the simplest one) and inference time (less than 0.3 s for the longest clips). Finally, to check if the generated model is able to generalize violence, a cross-dataset analysis is performed, which shows the complexity of this approach: using three datasets to train and testing on the remaining one the accuracy drops in the worst case to 70.08% and in the best case to 81.51%, which points to future work oriented towards anomaly detection in new datasets.
- 20 March 2021
- Published by Springer Nature in Soft Computing
- Vol. 25 (12) , 7769-7784
Two deep learning approaches to forecasting disaggregated freight flows: convolutional and encoder–decoder recurrent
- 20 March 2021
- Published by Springer Nature in Soft Computing
- Vol. 25 (12) , 7769-7784
Two deep learning approaches to forecasting disaggregated freight flows: convolutional and encoder–decoder recurrent
- Open Access
- 19 October 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 192218-192228
Known by Who We Follow: A Biclustering Application to Community Detection
The detection of communities in social networks is a task with multiple applications both in research and in sectors such as marketing and politics among others. In this paper, we address the task of detecting on-line communities of Twitter users for a given domain. Our main contribution consists in modelling the community detection problem as a biclustering task. We have performed the experimentation with data from the political domain, a very dynamic area with a large number of interested users and a high availability of tweets. We have evaluated our proposal using both extrinsic and intrinsic methods, reaching very good results in both cases. We use the silhouette coefficient as intrinsic metric for clustering evaluation, and a classification task of political leanings of Twitter users as extrinsic evaluation. One of the most interesting conclusions of our experiments is the quality, from the point of view of predictive capacity in the classification task, of the communities identified with the proposed method. The information provided by communities detected through “follow” relationships has a predictive capacity comparable to that of the contents of tweets written by users. The results also show how detected communities can give insights about future events related to these communities that arise around social networks.
- 19 October 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 192218-192228
Open AccessKnown by Who We Follow: A Biclustering Application to Community Detection
The detection of communities in social networks is a task with multiple applications both in research and in sectors such as marketing and politics among others. In this paper, we address the task of detecting on-line communities of Twitter users for a given domain. Our main contribution consists in modelling the community detection problem as a biclustering task. We have performed the experimentation with data from the political domain, a very dynamic area with a large number of interested users and a high availability of tweets. We have evaluated our proposal using both extrinsic and intrinsic methods, reaching very good results in both cases. We use the silhouette coefficient as intrinsic metric for clustering evaluation, and a classification task of political leanings of Twitter users as extrinsic evaluation. One of the most interesting conclusions of our experiments is the quality, from the point of view of predictive capacity in the classification task, of the communities identified with the proposed method. The information provided by communities detected through “follow” relationships has a predictive capacity comparable to that of the contents of tweets written by users. The results also show how detected communities can give insights about future events related to these communities that arise around social networks.
- 1 September 2016
- Published by Elsevier in Information Fusion
- Vol. 31, 54-64
Tweet categorization by combining content and structural knowledge
- 1 September 2016
- Published by Elsevier in Information Fusion
- Vol. 31, 54-64
Tweet categorization by combining content and structural knowledge
- 1 July 2013
- Published by Elsevier in Information Fusion
- Vol. 14 (3) , 255-267
A comparative study of classifier combination applied to NLP tasks
- 1 July 2013
- Published by Elsevier in Information Fusion
- Vol. 14 (3) , 255-267
A comparative study of classifier combination applied to NLP tasks