Article Per Year (5 Year)
p-Index From 2019 - 2024
0.23
P-Index
This Author published in this journals
All Journal Jurnal Nasional Teknik Elektro dan Teknologi Informasi
M. Mahrus Zein
Politeknik Caltex Riau
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Energy Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Coarse-Grained Sentiment Analysis Berbasis Natural Language Processing – Ulasan Hotel Warnia Nengsih; M. Mahrus Zein; Nazifa Hayati
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 10 No 1: Februari 2021
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1387.91 KB) | DOI: 10.22146/jnteti.v10i1.548

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.
Co-Authors Nazifa Hayati Warnia Nengsih