José A. Reyes-Ortiz

Clinical Decision Support Systems: A Survey of NLP-Based Approaches from Unstructured Data

Clinical Decision Support on patients health outcomes can be performed from free text with Natural Language Processing techniques. However, it becomes a computational challenge due to the complexity of natural language. In recent years, several NLP-based approaches have been proposed to consider clinical decisions support. This paper presents a survey of Natural Language Processing approaches to support clinical decisions on patient health outcomes. The presented approaches are emphasized on the use of free text as input for diverse languages. An analysis of clinical decision support systems based on natural language processing in terms of their performance results is presented.

Validation of Semantic Relation of Synonymy in Domain Ontologies Using Lexico-Syntactic Patterns and Acronyms.

Synonymy is a relation of equivalence between the meanings of one or more words which allows the use of any word in an equivalent way depending on the context. Given the difficulty of defining the concordance between the meanings, the Natural Language Processing has focused on researching computational techniques that allow defining pairs of synonyms automatically. In this paper, a method based on lexico-syntactic patterns is proposed for the validation of semantic relations of synonymy between ontological concepts. An acronym will be considered a type of synonym within our paper. The results obtained by our proposed method were compared with the criterion of three experts, resulting above 80% of accuracy in the concordances of opinion between what is marked by the experts and the results of our proposed method.

Entity-based Opinion Mining from Spanish Tweets.

Networking service has grown in the last years and therefore, users generate large amounts of data about entities, where they can express opinions about them. This paper presents an approach for opinion mining based on entities, which belong to banks, musicians and automobiles. Our approach uses machine learning techniques in order to classify Spanish tweets into three categories positives, negatives and neutral. A Support Vector Machine (SVM) and the bag of word model is used to obtain the corresponding class given a tweet. Our experimentation shows promising results and they validate that entity-based opinion mining is

An Ontology for Representing Information over Social Service in an Educational Institution.

In this paper, we present a method for constructing a manual ontology for the search of information over social service in a higher level education institution. We use some steps from methodology proposed by Grüninger and Fox. The ontology model will be useful to answer the questions of the students interested in the procedures of the social service. A scenario, competition questions, classes, and relationships are part of the design process. The answer to these questions leads us to the evaluation of the ontology. The ontology is made into Protégé and queries are written in the SPARQL query language.

Techno Neuro Pedagogy System: An Instructional Design Methodology for Customized Online Courses (Virtual Customized Environment Learning)

The Techno Neuro Pedagogy System (TNPS) is a systemic process with interrelated activities that allows you to create environments that facilitate the mediation processes on knowledge construction in virtual environments. Similarly to life cycle in software development, it consists of eight phases: analysis, design, development, testing, implementation, documentation, maintenance, and evaluation. TNPS incorporates a life cycle model of incremental and iterative software development that is an essential part of software engineering. TNPS integrates Education, Neuroscience and Technological dimensions, which facilitate the development of cognitive profile of student thinking in order to customize his/her learning activities. In our experiments, an increment in the weights of thinking style used by the students on a Structured Programming course was observed.

Collaborative Working: Understanding Mobile Applications Requirements

The Rational Unified Process (RUP) as well as the related work embrace the importance of collaborative working teams during software development, but, user-interface designers and system analysts work in parallel or in sequential mode. However, this kind of relationship may not be effective, resulting on functional software but not meeting usability issues. Our proposal is that in order to understand mobile applications requirements work should be made collaboratively between analysts and user-interface designers through sharing artifacts like use-case scenarios, sketching and mock-up. In this paper, we propose a collaborative work framework to meet mobile applications requirements. Also, we show preliminary results of a case study to assess this approach. Results suggest that the collaborative team got a common understanding about system limits and functional and usability requirements.

Phrase-Based Semantic Textual Similarity for Linking Researchers

Researchers need to establish networks with colleagues that work similar topics, frequently, they are looking similar works by exploring free text in scientific publications in order to update them with the recent state of the art. They read the abstracts and decide whether or not it is a related and relevant work. Therefore, this paper presents an approach for linking researchers based on measuring the similarity between the abstracts of their scientific publications in English. Our approach discovers ontological relationships between free text scientific publications using statistical and semantic similarity measures. An evaluation of a gold standard data set is presented, it has shown an average of 0.6399 for Pearson product-moment correlation coefficient.