Jurnal Nasional Teknik Elektro dan Teknologi Informasi
Vol 10 No 1: Februari 2021

Coarse-Grained Sentiment Analysis Berbasis Natural Language Processing – Ulasan Hotel

Warnia Nengsih (Politeknik Caltex Riau)
M. Mahrus Zein (Politeknik Caltex Riau)
Nazifa Hayati (Politeknik Caltex Riau)



Article Info

Publish Date
25 Feb 2021

Abstract

Sentiment analysis is a method for obtaining data from various platforms available on the internet. Advances in technology enable the machine to recognize a term that is considered a positive opinion and vice versa. These data and opinions play an important role as product, services, or other topic feedback. Without the need to obtain an opinion directly from the public, the provider has obtained an important evaluation to develop themselves. Hospitality business is a field related to services, providing services to customers. Indicators of business continuity also depend on customer feedback and serve as a reference for strategic policy. Sentiment analysis techniques based on Natural Language Processing are expected to overcome these problems. In this study, the prediction uses a temporary Random Forest (RF) classifier to summarize the quality of the classifier then it can be done using the Receiver Operating Characteristic (ROC) curve. The ROC curve is a good graphic to summarize the quality of the classifier. The higher the curve is above the diagonal line, the better the prediction, with the ROC Curve value of 0.90. The result shows that positive reviews are more than the negative reviews, i.e., 68% and 32%, respectively.

Copyrights © 2021






Journal Info

Abbrev

JNTETI

Publisher

Subject

Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Energy Engineering

Description

Topics cover the fields of (but not limited to): 1. Information Technology: Software Engineering, Knowledge and Data Mining, Multimedia Technologies, Mobile Computing, Parallel/Distributed Computing, Artificial Intelligence, Computer Graphics, Virtual Reality 2. Power Systems: Power Generation, ...