A Deep Learning Approach for Sentiment Analysis Applied to Hotel’s Reviews

Souza, Joana Gabriela Ribeiro de; Oliveira, Alcione de Paiva; Andrade, Guidson Coelho de; Moreira, Alexandra

doi:10.1007/978-3-319-91947-8_5

Cited by 10 publications

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They have concluded that linear SVM performs better among the three. Ms Aarti A. Patil, Prof. Seema Kolkur [4], have applied the advanced naive Bayesian algorithm on product reviews and achieved a precision of 82.85%.Joana, Alcione de Paiva, Guidson Coelho, Alexandra [13], presented a convolutional neural network approach on hotel reviews and stated that CNN has performed better than the previously considered models on the same corpus.…”

Section: E Present Review System (Combination Of Star Rating and Texmentioning

confidence: 99%

Exploring Classification Techniques for Sentiment Analysis

G.*,

T.,

et al. 2020

IJRTE

View full text Add to dashboard Cite

In the recent years, there has been tremendous improvements in the Information Technology industry. Every day 2.5 quintillion bytes of data is generated, this provides sentiment analysis to become a key tool to make something out of it. This has allowed companies to grab this key acumen and automate the needed processes. This information can serve as good source for extracting useful insights regarding the products/services. It would be helpful for the product owners if these thousands of reviews could be summarized using the latest technologies. Also it would be more useful if the sentiment scores are provided for each aspects of products/services. This paper presents Sentiment Analysis for various predefined aspects for Hotel Reviews. We have used Naive Bayes Classifier for classifying hotel reviews as positive or negative and we have evaluated the performance and suggested few future enhancements.

show abstract

Section: E Present Review System (Combination Of Star Rating and Texmentioning

confidence: 99%