Open AccessThe accuracy comparison of vector support machine and decision tree methods in sentiment analysis
Author(s) -
Nurfaizah,
Taqwa Hariguna,
Y I Romadon
Publication year - 2019
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1367/1/012025
Subject(s) - support vector machine , sentiment analysis , computer science , decision tree , service (business) , process (computing) , download , e commerce , tree (set theory) , data mining , machine learning , world wide web , marketing , business , mathematics , mathematical analysis , operating system
Analysis of customer satisfaction with company service is one of the tools for the company to be able to find out the lack of services and be able to know the expectations of users of the company. This is very possible in real-time, especially companies that are engaged in buying and selling online because one of the features they provide is a comment column from the user. In addition to using websites or known as e-commerce sites that can be accessed by consumers through media websites, currently online buying and selling providers can also be accessed through Google Play. Consumers download e-commerce applications and install them on their smartphones. This study aims to process user comments using Support Vector Machine (SVM) and Decision Tree algorithms to see the accuracy of the algorithm used and see positive and negative reviews. In addition to producing sentiment analysis, SVM classification algorithms and Decision Tree methods will be compared to their accuracy values in calculating datasets.