• Publications
  • Influence
Sentiment analysis in microblogging: a practical implementation
The system addresses this problem by retrieving raw data from Twitter one of the most popular microblogging platforms pre-processing on that raw data, and finally analyzing it using machine learning techniques to classify them by sentiment as either positive or negative. Expand
Web Usage Mining Using Self Organized Maps
The capacity of use of Self Organized Maps, kind of artificial neural network, in the process of Web Usage Mining to detect user’s patterns is detailed. Expand
Performance Evaluation of Knowledge Extraction Methods
This paper shows the precision, the recall and the F-measure for the knowledge extraction methods (under Open Information Extraction paradigm): ReVerb, OLLIE and ClausIE. For obtaining these threeExpand
Knowledge Discovery Process for Description of Spatially Referenced Clusters
A knowledge discovery process for the description of spatially referenced clusters that uses decision tree learning algorithms is proposed and two proofs of concept of the proposed process using different spatial clustering algorithm on real data are provided. Expand
Software as a Service: Undo
This paper proposes a highly automated mechanism to build an undo facility into a new or existing system easily. Our proposal is based on the observation that for a large set of operators it is notExpand
Service Oriented Architecture for Undo Functionality
A proof of concept is presented illustrating the simplicity and reusability of the proposed framework under alignments of Software as a Service and the use of services strategy simplifies greatly the design of the undo process. Expand
Evaluation of open information extraction methods using Reuters-21578 database
Although the correction improved the precision of Clausie, ReVerb turned out to be the most precise method; however ClausIE is the one with the better F1-measure. Expand
Tumor Classification on Mammographies Based on BPNN and Sobel Filter
An existent computer aided diagnosis method using neural network is studied and its detection success rate is improved from 60% to 73%. Expand
Application of Keystroke Dynamics Modelling Techniques to Strengthen the User Identification in the Context of E-commerce
Analysis of keystroke dynamics against an e-commerce site for personal identification showed that it was possible to identify typists with an accuracy of 89% from a sampling of 300 randomly selected users just by reading comment field keystrokes. Expand