FACHRUROZI, RIZQY (2022) ANALISIS SENTIMEN PADA SOSIAL MEDIA TWITTER UNTUK MENGETAHUI PERSEPSI MASYARAKAT MENGENAI FESTIVAL MUSIK WE THE FEST. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
01 Cover.pdf Download (603kB) | Preview |
|
|
Text (ASBTRAK)
02 Abstrak.pdf Download (74kB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (BAB I)
03 Bab 1.pdf Restricted to Registered users only Download (113kB) |
|
|
Text (BAB II)
04 Bab 2.pdf Restricted to Registered users only Download (19kB) |
|
|
Text (BAB III)
05 Bab 3.pdf Restricted to Registered users only Download (212kB) |
|
|
Text (BAB IV)
06 Bab 4.pdf Restricted to Registered users only Download (43kB) |
|
|
Text (DAFTAR PUSTAKA)
07 Daftar Pustaka.pdf Restricted to Registered users only Download (81kB) |
|
|
Text (LAMPIRAN)
08 Lampiran.pdf Restricted to Registered users only Download (264kB) |
Abstract
Social media Twitter can be a source of information to find out what the public thinks about certain subjects, for example the We The Fest music festival. This article presents the results of research on the sentiment analysis of the Twitter user community towards the We The Fest music festival. For the purposes of this prediction, the Decision Tree, Logistic Regression (SVM), and Support Vector Machine (SVM) techniques are used. The research dataset is obtained from Twitter tweets that are pulled by crawling the Twitter API using the keyword "We The Fest". For the implementation of the classification technique, the Rapid miner 9.7 tools are used. 002 both at the pre-processing and classification stages. The validation and evaluation used are split validation operators with a split ratio of 0.7 in the Logistic Regression (SVM) algorithm to produce regression and cross validation values for the number of folds with k = 10 for the Decision Tree algorithm and Support Vector Machine (SVM). From the experimental results it is known that the Support Vector Machine (SVM) technique provides the best results with accuracy, precision, and recall values of 85.40%, 85.57%, and 99.66%, respectively. Keyword: We The Fest, Twitter, Sentiment analysis, Rapidminer. Media sosial Twitter bisa menjadi salah satu sumber informasi untuk mengetahui pendapat masyarakat mengenai subjek tertentu seperti festival musik “We The Fest”. Artikel ini menyajikan hasil penelitian prediksi sentimen analisis masyarakat pengguna Twitter terhadap festival musik “We The Fest”. Untuk keperluan prediksi tersebut, digunakan teknik Decision Tree, Logistic Regression (SVM), dan Support Vector Machine (SVM). Dataset penelitian ini diperoleh dari cuitan Twitter yang ditarik melalui cara crawling API Twitter dengan menggunakan kata kunci “We The Fest”. Untuk implementasi teknik klasifikasi digunakan tools Rapidminer 9.7.002 baik pada tahap pre-processing dan klasifikasi. Validasi dan evaluasi yang digunakan adalah operator validation split dengan split ratio 0,7 Pada algoritma Logistic Regression (SVM) untuk menghasilkan nilai regresi dan cross validation pada number of folds dengan k=10 untuk algoritma Decision Tree dan Support Vector Machine (SVM). Dari hasil eksperimen diketahui bahwa teknik Support Vector Machine (SVM) memberikan hasil terbaik dengan nilai akurasi, presisi, dan recall masing-masing sebesar 85,40%, 85,57%, dan 99,66%. Kata kunci : We The Fest, Twitter, Sentimen analisis, Rapidminer.
Actions (login required)
 |
View Item |
