Analisis Sentimen Menggunakan Word2VEC Dan Support Vector Machine (Studi Kasus: Sentimen Pelanggan Sicepat)
Total View This Week0
Total View This Week0
Institusion
Institut Teknologi Telkom Purwokerto
Author
Desi, Natalia Br. Sidauruk
Subject
T Technology (General)
Datestamp
2022-08-02 08:20:54
Abstract :
E-commerce in Indonesia is growing due to the explosion in the number of users, that's why freight forwarding services are needed, one of which is Sicepat. Sicepat is very concerned with customer satisfaction, Sicepat customers can provide positive, negative, and neutral comments about their services through Twitter. The opinion of the community, a study was made on sentiment analysis. The sentiment analysis system is divided into 5 (five) stages, namely data crawling, labeling, preprocessing, feature extraction, and sentiment classification. The method used is Word2vec as feature extraction by converting data into vector values. The labeling results are 200 negative classes, 695 positive classes, and 50 neutral classes with manual labeling while the classification method in this study uses the Support Vector Machine (SVM). Furthermore, the confusion matrix test gives an accuracy value of 78%. Keywords: Sentiment Analysis, Sicepat, Word2vec, Support Vector Machine, Twitter
E-commerce in Indonesia is growing due to the explosion in the number of users, that's why freight forwarding services are needed, one of which is Sicepat. Sicepat is very concerned with customer satisfaction, Sicepat customers can provide positive, negative, and neutral comments about their services through Twitter. The opinion of the community, a study was made on sentiment analysis. The sentiment analysis system is divided into 5 (five) stages, namely data crawling, labeling, preprocessing, feature extraction, and sentiment classification. The method used is Word2vec as feature extraction by converting data into vector values. The labeling results are 200 negative classes, 695 positive classes, and 50 neutral classes with manual labeling while the classification method in this study uses the Support Vector Machine (SVM). Furthermore, the confusion matrix test gives an accuracy value of 78%. Keywords: Sentiment Analysis, Sicepat, Word2vec, Support Vector Machine, Twitter
Download
book
BibTex
Latex, Jabref
cloud_download
Original Resource
url resource Institution
