Sentiment analysis and opinion mining applied to scientific paper reviews

Norambuena, Brian Keith; Lettura, Exequiel Fuentes; Villegas, Claudio Meneses

doi:10.3233/ida-173807

Cited by 50 publications

(19 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Construct a semantic-based research hotspot query. According to the lucene scoring formula (18) and the normalization formula (19), the score values of the keywords and the distributions of the words according to the year are obtained and the hotspot field evolution of the NSFC is identified.…”

Section: A Flowchart For Our Methodsmentioning

confidence: 99%

“…Bai [17] realized the recommendation of scientific papers and research fields via the investigation of scientific papers. Norambuena et al [18] proposed a sentiment analysis and opinion mining method that is based on scientific research papers. Waheed et al [19] proposed a hybrid method for the recommendation of scientific research papers and promoted the full use of the papers.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Research Hotspot Prediction and Regular Evolutionary Pattern Identification Based on NSFC Grants Using NMF and Semantic Retrieval

et al. 2019

View full text Add to dashboard Cite

Analyzing the research hotspots and regular evolutionary patterns of R&D projects can help researchers find potential information. This paper considers the titles of the National Natural Science Foundation of China (NSFC) grants that have been awarded in the past 20 years as the research objects. First, we analyze the number and funding amounts of project grants for each department over the past 20 years. Second, we propose a topic discovery method that is based on nonnegative matrix factorization and further propose a keyword scoring method that is based on semantic retrieval, from which we can discover the regular evolutionary patterns of research hotspots. Finally, we conduct experiments on datasets on grants in the Department of Information Science. To identify research characteristics, trends and prospects, we explore the regular evolutionary patterns of research hotspots via experiments using three methods from multiple perspectives: word cloud, topic corresponded to keywords display and topic evolution display. The results of the experimental studies demonstrate that researchers can keep abreast of the main content and hotspots in the research field via hot spot discovery and the identification of regular evolutionary pattern of NSFC grants. This study can also help the government improve the allocation of scientific and technological resources and help decision makers make scientific decisions.

show abstract

Section: A Flowchart For Our Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Research Hotspot Prediction and Regular Evolutionary Pattern Identification Based on NSFC Grants Using NMF and Semantic Retrieval

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Keith, Fuentes y Meneses [34] presentan un método que aplica POS Tagging a textos en español para obtener la estructura de una oración y luego, con el uso de diccionarios, determinar la orientación semántica del texto. Miranda y Guzmán [35] proponen extraer información desde la web para luego identificar los elementos que corresponden a un modelo de acción para tareas de Planeación automática.…”

Section: Referencia Idioma Del Texto Procesadounclassified

Método para la representación semi-automática de modelos conceptuales desde documentos de negocio escritos en lenguaje natural en español

Marín-Alvarez

Losada

Quintero

2020

Ingeniare. Rev. chil. ing.

View full text Add to dashboard Cite

Actualmente la industria de desarrollo de software presenta grandes retos para el procesamiento de información de negocio, particularmente aquella contenida en documentos textuales. En el proceso de educción de requisitos de software una fuente potencial de información relevante son los documentos de negocio, pues a partir de éstos se puede facilitar la comprensión de conocimiento de un dominio, así como conocer la evolución de un producto. A pesar de su utilidad, los ingenieros de requisitos no siempre la usan para su labor por los tiempos y costos que implica. En el presente trabajo se aborda esta problemática y se reconoce por medio de una revisión sistemática, la potencialidad de usar técnicas de Procesamiento de Lenguaje Natural (NLP por sus siglas en inglés) para extraer información textual relevante de documentos de negocio, y la utilidad de representarla en modelos conceptuales. A partir de esto, se propone un método semi-automático de extracción de información desde documentos de negocio escritos en lenguaje natural en español y su representación en un modelo conceptual. El método se soporta en un marco metodológico de referencia para proyectos de Analítica de Texto, se fundamenta en técnicas de NLP, y se representa la salida en un diagrama de clases. El método fue evaluado mediante un caso de estudio con analistas de software en Medellín-Colombia, tomando como entrada documentos de resolución de telecomunicaciones. La evaluación permite concluir que el modelo es una satisfactoria aproximación a solucionar el problema planteado mejorando el tiempo de procesamiento y manteniendo un nivel de interpretación similar al proceso manual. Palabras clave: Procesamiento de lenguaje natural, POS Tagging, modelo conceptual, educción de requisitos.

show abstract

“…We aim to develop a demonstration model based on the healthcare sector. The task of sentiment analysis of hospital reviews mainly includes the following steps in sequence: pre-processing [ 7 ], attribute extraction which is followed by the selection of the relevant attribute [ 8 ], emotional analysis [ 9 ], and at last quantifying the extracted attributes. A typical approach is to compute an average quantitative rating based on individual user ratings.…”

Section: Introductionmentioning

confidence: 99%

“…Significant work has been done with respect to analyses of reviews to provide a single qualitative rating of a product or service [ 5 – 9 ]. But there have been limited studies which quantify a product or service along multiple key attributes/aspects.…”

Section: Introductionmentioning

confidence: 99%