Yoan Gutiérrez

GPLSI: Supervised Sentiment Analysis in Twitter using Skipgrams

In this paper we describe the system submitted for the SemEval 2014 Task 9 (Sentiment Analysis in Twitter) Subtask B. Our contribution consists of a supervised approach using machine learning techniques, which uses the terms in the dataset as features. In this work we do not employ any external knowledge and resources. The novelty of our approach lies in the use of words, ngrams and skipgrams (notadjacent ngrams) as features, and how they are weighted.

A graph-based approach to WSD using relevant semantic trees and n-cliques model

In this paper we propose a new graph-based approach to solve semantic ambiguity using a semantic net based on WordNet. Our proposal uses an adaptation of the Clique Partitioning Technique to extract sets of strongly related senses. For that, an initial graph is obtained from senses of WordNet combined with the information of several semantic categories from different resources: WordNet Domains, SUMO and WordNet Affect. In order to obtain the most relevant concepts in a sentence we use the Relevant Semantic Trees method. The evaluation of the results has been conducted using the test data set of Senseval-2 obtaining promising results.

A semantic framework for textual data enrichment

A semantic framework for recommender systems is presented.An in-depth analysis of different Natural Language Processing resources is showed.A description of different Natural Language Processing approaches is addressed.Related research works are described.A case of study to evaluate our proposal with real data is presented. In this work we present a semantic framework suitable of being used as support tool for recommender systems. Our purpose is to use the semantic information provided by a set of integrated resources to enrich texts by conducting different NLP tasks: WSD, domain classification, semantic similarities and sentiment analysis. After obtaining the textual semantic enrichment we would be able to recommend similar content or even to rate texts according to different dimensions. First of all, we describe the main characteristics of the semantic integrated resources with an exhaustive evaluation. Next, we demonstrate the usefulness of our resource in different NLP tasks and campaigns. Moreover, we present a combination of different NLP approaches that provide enough knowledge for being used as support tool for recommender systems. Finally, we illustrate a case of study with information related to movies and TV series to demonstrate that our framework works properly.

UMCC_DLSI_SemSim: Multilingual System for Measuring Semantic Textual Similarity

In this paper we describe the specifications and results of UMCC_DLSI system, which was involved in Semeval-2014 addressing two subtasks of Semantic Textual Similarity (STS, Task 10, for English and Spanish), and one subtask of Cross-Level Semantic Similarity (Task 3). As a supervised system, it was provided by different types of lexical and semantic features to train a classifier which was used to decide the correct answers for distinct subtasks. These features were obtained applying the Hungarian algorithm over a semantic network to create semantic alignments among words. Regarding the Spanish subtask of Task 10 two runs were submitted, where our Run2 was the best ranked with a general correlation of 0.807. However, for English subtask our best run (Run1 of our 3 runs) reached 16 th place of 38 of the official ranking, obtaining a general correlation of 0.682. In terms of Task 3, only addressing Paragraph to Sentence subtask, our best run (Run1 of 2 runs) obtained a correlation value of 0.760 reaching 3 rd place of 34.

Spreading semantic information by Word Sense Disambiguation

Abstract This paper presents an unsupervised approach to solve semantic ambiguity based on the integration of the Personalized PageRank algorithm with word-sense frequency information. Natural Language tasks such as Machine Translation or Recommender Systems are likely to be enriched by our approach, which includes semantic information that obtains the appropriate word-sense via support from two sources: a multidimensional network that includes a set of different resources (i.e. WordNet, WordNet Domains, WordNet Affect, SUMO and Semantic Classes); and the information provided by word-sense frequencies and word-sense collocation from the SemCor Corpus. Our series of results were analyzed and compared against the results of several renowned studies using SensEval-2, SensEval-3 and SemEval-2013 datasets. After conducting several experiments, our procedure produced the best results in the unsupervised procedure category taking SensEval campaigns rankings as reference.

UMCC_DLSI: Sentiment Analysis in Twitter using Polirity Lexicons and Tweet Similarity

This paper describes a system submitted to SemEval-2014 Task 4B: Sentiment Analysis in Twitter, by the team UMCC DLSI Sem integrated by researchers of the University of Matanzas, Cuba and the University of Alicante, Spain. The system adopts a cascade classification process that uses two classifiers, K-NN using the lexical Levenshtein metric and a Dagging model trained over attributes extracted from annotated corpora and sentiment lexicons. Phrases that fit the distance thresholds were automatically classified by the KNN model, the others, were evaluated with the Dagging model. This system achieved over 52.4% of correctly classified instances in the Twitter message-level subtask.

On Evaluating the Contribution of Text Normalisation Techniques to Sentiment Analysis on Informal Web 2.0 Texts

The writing style used in social media usually contains informal elements that can lower the performance of Natural Language Processing applications. For this reason, text normalisation techniques have drawn a lot of attention recently when dealing with informal content. However, not all the texts present the same level of informality and may not require additional pre-processing steps. Therefore, in this paper we explore the results of applying lexical normalisation applied to a sentiment analysis classification task on Web 2.0 texts, shows more than a 2.6% improvement over average F1 for the most informal data.

Opinion Mining in Social Networks versus Electoral Polls.

The recent failures of traditional poll models, like the predictions in United Kingdom with the Brexit, or in United States presidential elections with the victory of Donald Trump, have been noteworthy. With the decline of traditional poll models and the growth of the social networks, automatic tools are gaining popularity to make predictions in this context. In this paper we present our approximation and compare it with a real case: the 2017 French presidential election.

Natural Language Processing Technologies for Document Profiling.

Nowadays, search for documents on the Internet is becoming increasingly difficult. The reason is the amount of content published by users (articles, comments, blogs, reviews). How to facilitate that the users can find their required documents? What would be necessary to provide useful document meta-data for supporting search engines? In this article, we present a study of some Natural Language Processing (NLP) technologies that can be useful for facilitating the proper identification of documents according to the user needs. For this purpose, it is designed a document profile that will be able to represent semantic meta-data extracted from documents by using NLP technologies. The research is basically focused on the study of different NLP technologies in order to support the creation our novel document profile proposal from semantic perspectives.

Developing an Ontology to Capture Documentsź Semantics

Ontologies have been shown to be one of the best mechanisms to represent knowledge within a domain for later reasoning and inferring new knowledge that may not be initially explicitly stated. Most of the research works focus on the representation of a particular domain, thus designing and building domain ontologies (e.g. tourism, medical, etc.). However, the development of task-oriented ontologies may be more appropriate, since they can be applied to different domains, avoiding the limitation of the ad-hoc ontologies. Therefore, the goal of this paper is to present a task-oriented ontology, with the purpose of capturing the semantics of a document, in order to be used for Natural Language Processing applications, and more specifically, for the automatic generation of personalized information. The preliminary evaluation and validation of our ontology through a wide range of competence questions clearly shows its potentiality to extract the information according to specific information needs.