CD Skripsi
Analisis Sentimen Twitter Terhadap Peperangan Rusia Dan Ukraina Menggunakan Algoritma Support Vector Machine
Sentiment analysis is one of the sciences in Text Mining which is used to classify text documents in the form of public opinion. This study aims to find out how people's sentiments about the war that occurred between Russia and Ukraine through tweets on Twitter social media using the Support Vector Machine method. Text documents use three labels, namely: positive, negative, and neutral. The data used is 2000 data using two data test scenarios, namely, Split Validation and Cross Validation. Testing data with Split Validation uses 80%:20% data sharing, while testing data with Cross Validation is divided into 10 tests. Testing the data with Split Validation produces an accuracy of 82.5% with a data sharing of 80%:20%. Testing the data with Cross Validation produces the highest accuracy value of 86.0%, with a value of fold = 7.
Keywords : Sentiment Analysis, Cross Validation, Fold, Split Validation, Support Vector Machine, Text Mining
Tidak tersedia versi lain