J
John Atkinson
Researcher at Adolfo Ibáñez University
Publications - 55
Citations - 795
John Atkinson is an academic researcher from Adolfo Ibáñez University. The author has contributed to research in topics: Natural language & Context (language use). The author has an hindex of 12, co-authored 54 publications receiving 610 citations. Previous affiliations of John Atkinson include University of Concepción & Yahoo!.
Papers
More filters
Journal ArticleDOI
Improving BCI-based emotion recognition by combining EEG feature selection and kernel classifiers
John Atkinson,Daniel Campos +1 more
TL;DR: A novel feature-based emotion recognition model is proposed for EEG-based Brain-Computer Interfaces which combines statistical-based feature selection methods and SVM emotion classifiers and incorporates additional features which are relevant for signal pre-processing and recognition classification tasks.
Journal ArticleDOI
Adaptive feedback selection for intelligent tutoring systems
Fernando Gutiérrez,John Atkinson +1 more
TL;DR: The approach suggested that combining SVM and CRF models are promising to get effective feedback correction from student tutoring, showing that the multi-strategy selection approach outperformed the traditional meta-linguistic rules based feedback strategies.
Journal ArticleDOI
Effluent composition prediction of a two-stage anaerobic digestion process: machine learning and stoichiometry techniques
TL;DR: The SVM-based model outperformed the analytical method for the TAN prediction, and showed higher prediction accuracy in comparison with Artificial Neural Networks, revealing the future promise of SVM for prediction in non-linear and dynamic AD processes.
Journal ArticleDOI
Rhetorics-based multi-document summarization
John Atkinson,Ricardo Munoz +1 more
TL;DR: A new multi-document summarization framework which combines rhetorical roles and corpus-based semantic analysis is proposed which is able to capture the semantic and rhetorical relationships between sentences so as to combine them to produce coherent summaries.
Journal ArticleDOI
Discovering implicit intention-level knowledge from natural-language texts
TL;DR: A new approach to automatic discovery of implicit rhetorical information from texts based on evolutionary computation methods is proposed, which uses previously obtained training information which involves semantic and structural criteria.