Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : Building of Informatics, Technology and Science

Implementasi Library Textblob dan Metode Support Vector Machine Pada Analisis Sentimen Pelanggan Terhadap Jasa Transportasi Online Laia, Yardiana; Berutu, Sunneng Sandino; Sumihar, Yo’el Pieter; Budiati, Haeni
Building of Informatics, Technology and Science (BITS) Vol 6 No 1 (2024): June 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i1.5090

Abstract

Online transportation services have become an inseparable part of human life today. This research aims to develop an effective sentiment analysis method to measure public opinion about the quality of online transportation services, which has a significant impact on company reputation and public acceptance of these services. In this research, we propose the use of TextBlob library to perform sentiment analysis of public opinion on online transportation services. This library allows to measure the positive, negative and neutral polarity and subjectivity of opinion text collected from Gojek, Maxim and Grab application reviews through Google Play Store. Sentiment analysis steps are carried out starting from data preparation, data pre-processing, data labeling using the Text Blob library. Furthermore, building a sentiment classification model based on the Support Vector Machine (SVM) algorithm through training and testing stages. Model testing results are evaluated with confusion matrix. The results of the analysis with textblob showed that online transportation received the highest positive sentiment of 40.1%, followed by neutral sentiment of 26.7% and negative sentiment of 25.2%. Meanwhile, the model performance measurement results show that the precision obtained the highest value in positive sentiment of 0.93. The recall parameter reaches the highest value in negative sentiment of 0.95 and f1-score in neutral and positive sentiment of 0.92. Thus, this research not only contributes to the development of sentiment analysis classification, but also has a significant practical impact in improving online transportation services and providing useful information to the public, thus encouraging innovation and continuous improvement in online transportation services.