Text
Analisis Sentimen PT Tiki Jalur Nugraha Ekakurir (PT Tiki JNE) pada Media Sosial Twitter Menggunakan Model Feed Forward Neural Network
ABSTRACT
In the 2000s until now, e-commerce systems have continued to develop throughout the world and even in
Indonesia. PT Tiki Jalur Nugraha Ekakurir (PT Tiki JNE) is a freight forwarding company that provides
convenience for the public in carrying out online shopping activities, and shipping other goods. The large
volume of shipments makes PT Tiki JNE have several problems in service that have led to several kinds of
responses from users. Sentiment analysis on Twitter social media can be an option to see how PT Tiki JNE’s
users respond to services that have been provided. These responses are classified into positive sentiments
and negative sentiments. In this research data processing is performed using text mining as the initial source
of numerical data from document data which will later be classified using the Artificial Neural Network
model with the Resilient Backpropagation algorithm. Data labeling is done manually and sentiment scoring.
The test results show that the best model obtained is FFNN 867-7-1 by using the evaluation model 10-Fold
Cross Validation to get an overall accuracy performance of 80.27%, kappa accuracy of 39.13%, precision of
69.04%, recall of 70.56%, and f-measure of 69.8% which can be interpreted that the model used is quite
good. Analysis of the results using wordcloud shows the tendency of opinion sentiment categories
depending on the words used in the tweet.
Keywords: PT Tiki Jalur Nugraha Ekakurir, Twitter, Text Mining, Artificial Neural Network,
Resilient Backpropagation
807E20IV | 807 E 20-iv | Perpustakaan FSM Undip (Referensi) | Tersedia |
Tidak tersedia versi lain