Sentiment Analysis on MyPertamina Application Reviews Using NBC and SVM with Negation Handling
Journal Title: Engineering and Technology Journal - Year 2024, Vol 9, Issue 08
Abstract
Pertamina has issued a cashless application for fuel purchases since July 2019, named as MyPertamina. The application aims to make it easier for customers to make payments in transactions at fuel stations. MyPertamina application can currently be downloaded on Google Play Store. Since its release until now, MyPertamina has been downloaded as many as 10 million with a rating of 3.1 and 339 thousand reviews. Unfortunately, the low rating and user reviews dominated by negative comments show that the app's performance is still not satisfactory. The reviews data can be converted into valuable information by using sentiment analysis. Many researchers have applied sentiment analysis to MyPertamina user comment data. However, there have been no studies that apply the handling of negation in MyPertamina reviews, even though negative comments are very often found, i.e ‘tidak’,’jangan’,’belum’ and ‘bukan’. The negative words will change the sentiment of next sentence. Untreated negation words will lead to errors in classification which in turn will decrease accuracy. This study applies the handling of negation words using First Sentiment Word (FSW) and Fixed Window Length (FWL) methods. The classification algorithms used are Naïve Bayes Classifier (NBC) and Support Vector Machine (SVM). In this work, we analyzed 1000 comments consisting of 390 positive comments and 610 negative comments. The results showed that the best performance of negation handling is FSW. This method has improved accuracy by 2.5% and improved F1 by 1.5% using NBC algorithm and has improved accuracy by 2.9% and F1 by 3.4% using SVM algorithm.
Authors and Affiliations
Amir Hamzah , Renna Yanwastika Ariyana ,
Keywords
Related Articles
- EP ID EP743215
- DOI 10.47191/etj/v9i08.44
- Views 103
- Downloads 0
Cassava Starch-Based Composite Reinforced with Coconut Mesocarpfibers: Analysis of Physicochemical Stability
In one of our previous articles, we developed a cassava starch material reinforced with coconut mesocarpfibers. Its properties have been evaluated. It appears that the behavior of the composite depends on the atmospheric...
Covid-19 Review: A Trend Analysis of the Impact of Religious Festivities and Non-Adherence to Social Distancing in Nigeria
The global negative impact of Covid-19 pandemic necessitates curtailing measures and policies in case of future outbreak. A trend analysis of the spread of Covid-19 showing the effect of social gatherings especially duri...
A Systematic Review of Predictive Analytics Applications in Early Disease Detection and Diagnosis
The integration of predictive analytics and artificial intelligence (AI) in healthcare has revolutionized early disease detection and diagnosis, significantly improving patient outcomes and reducing healthcare costs. Thi...
IMPROVED INTELLIGENT BASE TECHNIQUE FOR PATH AND SOLUTION IN ROBOTIC USING PREWILL EDGE DETECTION PARADIGM
The major contribution in this research paper is concerned with the development of a humanoid robot using edge detection technique which selects features of the principal parts of the object and eliminates parts that are...
Proposing Process and Experiment of Drying Roses by Freeze-Drying Method
Roses, both fresh and dried, often appear during festive occasions. However, fresh roses do not last long, and dried flowers are marinated with environmentally unfriendly chemicals. This paper proposes the procedure and...