Ellen P.R. Souza

Prof. Dr. Ellen P.R. Souza

Institute of Mathematics and Computing Sciences, Federal Rural University of Pernambuco, Recife 52171-900, Brazil

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 March 2022
Verified
Book Chapter
Closed access
PDF file
HAHidelberg O. Albuquerque
Hidelberg O. Albuquerque
RCRosimeire Costa
Rosimeire Costa
GSGabriel Silvestre
Gabriel Silvestre
Ellen P.R. SouzaEllen P.R. Souza
Ellen P.R. Souza
NSNádia Silva
Nádia Silva
Adriano L.I. OliveiraAdriano L.I. Oliveira
Adriano L.I. Oliveira

1 December 2017 in Applied Soft Computing
Verified
Journal Article
Closed access
DCDayvid W. Castro
Dayvid W. Castro
Ellen P.R. SouzaEllen P.R. Souza
Ellen P.R. Souza
DVDouglas Vitório
Douglas Vitório
DSDiego Santos
Diego Santos
AOAdriano L.I. Oliveira
Adriano L.I. Oliveira

25 April 2018 in Natural Computing
Verified
Journal Article
Open access
PDF file
Ellen P.R. SouzaEllen P.R. Souza
Ellen P.R. Souza
DSDiego Santos
Diego Santos
GOGustavo Oliveira
Gustavo Oliveira
Alisson Marques SilvaAlisson Marques Silva
Alisson Marques Silva
Adriano L.I. OliveiraAdriano L.I. Oliveira
Adriano L.I. Oliveira
Supervised machine learning and opinion lexicon are the most frequent approaches for opinion mining, but they require considerable effort to prepare the training data and to build the opinion lexicon, respectively. In this paper, a novel unsupervised clustering approach is proposed for opinion mining. Three swarm algorithms based on Particle Swarm Optimization are evaluated using three corpora with different levels of complexity with respect to size, number of opinions, domains, languages, and class balancing. K-means and Agglomerative clustering algorithms, as well as, the Artificial Bee Colony and Cuckoo Search swarm-based algorithms were selected for comparison. The proposed swarm-based algorithms achieved better accuracy using the word bigram feature model as the pre-processing technique, the Global Silhouette as optimization function, and on datasets with two classes: positive and negative. Although the swarm-based algorithms obtained lower result for datasets with three classes, they are still competitive considering that neither labeled data, nor opinion lexicons are required for the opinion clustering approach.

18 August 2024 in Language Resources and Evaluation
Verified
Journal Article
Closed access
PDF file
DVDouglas Vitório
Douglas Vitório
Ellen P.R. SouzaEllen P.R. Souza
Ellen P.R. Souza
LMLucas Martins
Lucas Martins
NSNádia Silva
Nádia Silva
ACAndré Carlos Ponce de Leon de Carvalho
André Carlos Ponce de Leon de Carvalho
FAFrancisco Edmundo de Andrade
Francisco Edmundo de Andrade

13 September 2022
Verified
Book Chapter
Closed access
PDF file
RCRosimeire Costa
Rosimeire Costa
HAHidelberg Oliveira Albuquerque
Hidelberg Oliveira Albuquerque
GSGabriel Silvestre
Gabriel Silvestre
NSNádia Silva
Nádia Silva
Ellen P.R. SouzaEllen P.R. Souza
Ellen P.R. Souza
Adriano L.I. OliveiraAdriano L.I. Oliveira
Adriano L.I. Oliveira

28 August 2019
Verified
Conference Paper
Open access
PDF file
EQEduarda Queiroz
Eduarda Queiroz
RMRafaela Moura
Rafaela Moura
Ellen P.R. SouzaEllen P.R. Souza
Ellen P.R. Souza
A Realidade Aumentada (RA) é definida como qualquer sistema que combine o real com o virtual, que seja interativo em tempo real e que esteja registrado em três dimensões. No ensino das ciências da natureza, ela pode proporcionar aos estudantes a visualização de conceitos abstratos. Este trabalho tem como objetivo investigar como a RA tem auxiliado no processo de ensino e aprendizagem das ciências naturais. Foi realizado um mapeamento sistemático que é um estudo secundário e tem como foco identificar as lacunas de pesquisas na literatura. Estudos primários publicados entre os anos de 2009 a 2018 foram analisados a fim de extrair dados que pudessem responder às questões de pesquisa e assim alcançar o objetivo deste trabalho.