Análisis de sentimientos basado en aspectos: un modelo para identificar la polaridad de críticas de usuario

Quiroga, Miguel Angel Rosales; Ayala, Darnes Vilariño; Pinto, David; Tovar, Mireya; Beltrán, Beatriz

doi:10.13053/rcs-115-1-14

Cited by 2 publications

(2 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Diaz-Garcia, Ruiz, & Martin-Bautsta (2018) association rules are applied to the database, in this case Twitter, with these rules, opinions can be categorized, and people's feelings identified. In the research work developed by Quiroga, Ayala, Pinto, Tovar, & Beltrán (2016), the authors propose a model composed of three phases: Pre-processing, Identification of Aspects and Polarity Identification, obtaining 50% effectiveness in the SemEval 2016 Competition forum. They use the sentiment dictionary SentiWordNet, which is generally so that some words in specific contexts have one polarity and, in another context, a different one, is used for comments in Spanish.…”

Section: Related Workmentioning

confidence: 99%

Improving Prediction of Polarity in Tourism Domain using Convolutional Neural Network

Leiva Vasconcellos,

Tovar Vidal

2023

Int. Journal of COP and Infor.

View full text Add to dashboard Cite

The analysis of the polarity of various types of comments has been enhanced by the development of Web 2.0, where millions of user-generated opinions on different sites now offer a wealth of information. Opinion mining focuses on automatically determining the polarity of posts for research and the development of real-world applications. This article aims to determine which of the proposed algorithms (Decision Trees, Support Vector Machine, Naïve Bayes, and Convolutional Neural Network) are most suitable for predicting the polarity of opinions in the tourism domain. For this purpose, a set of opinions (30,210) from the REST-MEX 2022 Sentiment Analysis competition, pertaining to hotels, attractions, and restaurants, is used. The experimental results obtained show that the Convolutional Neural Network (CNN) is the best classifier, achieving an accuracy of 98.83%, followed by the Support Vector Machine (SVM) and Naïve Bayes with accuracies of 71% and 70% respectively. The worst performance was observed with Decision Trees, which achieved 62% accuracy.

show abstract

Section: Related Workmentioning

confidence: 99%

Improving Prediction of Polarity in Tourism Domain using Convolutional Neural Network

Leiva Vasconcellos,

Tovar Vidal

2023

Int. Journal of COP and Infor.

View full text Add to dashboard Cite

show abstract

“…The basic task in sentiment analysis, opinion mining, or emotional artificial intelligence is to classify the polarity of 832 the text present in documents, sentences, or opinions [12]- [15]. Sentiment analysis is a text classification task within the NLP area, its objective is to weigh the sentiment contained in opinions or comments through tones or polarities [16]- [19]. The task of identifying the predominant sentiment in a text is a complex task for the human being, however through NLP and text mining it is possible to extract relevant characteristics and qualities [20]- [22].…”

Section: Introductionmentioning

confidence: 99%

Student satisfaction in the context of hybrid learning through sentiment analysis

Chamorro-Atalaya,

Sobrino-Chunga,

Guerrero-Carranza

et al. 2024

IJERE

View full text Add to dashboard Cite

<span lang="EN-US">With the incursion of data science into the academic field and the massification of social networks, it is possible to extract information on student satisfaction that contributes to feedback on teacher teaching strategies and methods. This article aims to determine student satisfaction with teaching performance, through sentiment analysis. Methodologically, the research is of a non-experimental longitudinal design, with a quantitative approach. Data collection was carried out through the social network Twitter, and data analysis was carried out through the sentiment analysis technique. As a result, it was identified that in the first week of class, the highest level of satisfaction was obtained, reaching 96.3% of the total number of students. Meanwhile, in the evaluation weeks, the highest level of dissatisfaction was reaching 29.17%. It is concluded that when going from totally virtual learning to hybrid learning, students express a certain level of dissatisfaction typical of a process of progressive adaptation. Therefore, teachers should take advantage of these findings to redesign assessment rubrics in the context of hybrid teaching. Aspects such as collecting opinions through social networks and extracting a degree of satisfaction through them apply in a crossed way to other professional fields.</span>

show abstract

Análisis de sentimientos basado en aspectos: un modelo para identificar la polaridad de críticas de usuario

Abstract: negative and neutral. Some features as the following ones are employed: part-of-speech tags, semantic similarity among words and co-ocurrence.

Cited by 2 publications

References 5 publications

Improving Prediction of Polarity in Tourism Domain using Convolutional Neural Network

Improving Prediction of Polarity in Tourism Domain using Convolutional Neural Network

Student satisfaction in the context of hybrid learning through sentiment analysis

Contact Info

Product

Resources

About