Análise de Sentimentos na Classificação de Online Reviews Aplicando Texto Mining

Translated title of the contribution: Sentiment analysis in online reviews classification using text mining techniques

M. Águeda, Paulo Rita, P. Guerreiro

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

The growth of social media in recent years has led to an increase in online reviews that reflects consumer opinions. Firms benefit greatly from making this information available in order to respond more effectively to consumer dissatisfaction and to exploit market opportunities by observing standards that may represent unsatisfied needs. The present study aims to address this problem through a survey based on the Yelp platform. To this end, 14,000 comments related to different tourism products were used and text mining techniques and topic models were applied to find the main latent topics discussed in the online comments and their associated sentiments. The study presents 20 latent topics from online discussions and reveals that the topic that discusses 'Air Travel' themes is the one with a lower sentiment connotation on average and should therefore be the subject of a deeper evaluation.

Translated title of the contributionSentiment analysis in online reviews classification using text mining techniques
Original languagePortuguese
Title of host publication2019 14th Iberian Conference on Information Systems and Technologies (CISTI)
EditorsRamiro Goncalves, Isabel Pedrosa, Manuel Perez Cota, Alvaro Rocha
PublisherIEEE Computer Society
ISBN (Electronic)9789899843493
DOIs
Publication statusPublished - 15 Jul 2019
Event14th Iberian Conference on Information Systems and Technologies, CISTI 2019 - Coimbra, Portugal
Duration: 19 Jun 201922 Jun 2019

Publication series

NameIberian Conference on Information Systems and Technologies, CISTI
Volume2019-June
ISSN (Print)2166-0727
ISSN (Electronic)2166-0735

Conference

Conference14th Iberian Conference on Information Systems and Technologies, CISTI 2019
Country/TerritoryPortugal
CityCoimbra
Period19/06/1922/06/19

Keywords

  • Natural Language Processing
  • Online Reviews
  • Sentiments Analysis
  • Text Mining
  • Topic Models

Fingerprint

Dive into the research topics of 'Sentiment analysis in online reviews classification using text mining techniques'. Together they form a unique fingerprint.

Cite this