Klasifikasi Emosi untuk Teks Berbahasa Indonesia pada Pengguna Twitter Mengenai Presiden Joko Widodo

Rahman, Fazlur (2019) Klasifikasi Emosi untuk Teks Berbahasa Indonesia pada Pengguna Twitter Mengenai Presiden Joko Widodo. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.

[img]
Preview
Text
06211440000072-Undergraduate_Theses.pdf - Accepted Version

Download (1MB) | Preview

Abstract

Presiden Jokowi jelas selalu menjadi sorotan di mata ma-syarakat. Beliau bertugas memenuhi harapan rakyatnya, dan akan baik kinerjanya apabila mendapat dukungan penuh pula dari rak-yatnya. Hal tersebut membuat Presiden Jokowi kerap kali diper-bincangkan oleh masyarakat. Pada perkembangan teknologi se-perti saat ini, masyarakat dapat menyuarakan pendapat dan emo-sinya melalui teks pada media social seperti Twitter. Twitter ada-lah sebuah jaringan sosial berupa mikroblog sehingga memung-kinkan penggunanya untuk mengirim dan membaca pesan dalam bentuk teks. Namun, emosi yang diungkapkan oleh masyarakat sa-ngat beragam jenisnya. Mengetahui tanggapan masyarakat berda-sarkan emosinya akan membuat proses evaluasi semakin efek-tif. Oleh karena itu, diperlukannya sebuah penelitian untuk meng-etahui opini dan emosi dari masyarakat. Tanggapan publik meng-enai Presiden Jokowi didapat dari Application Programming In-terface (API). Sebelum dilakukan klasifikasi teks, akan dilakukan praproses teks. Praproses teks yang digunakan adalah case fold-ing, stopwords, dan tokenizing. Sedangkan pada analisis klasifi-kasi data teks tersebut digunakan metode Support Vector Machine (SVM) dan K-Nearest Neighbor (KNN). Klasifi¬kasi menggunakan SVM menghasilkan akurasi prediksi sebesar 95.2%. Sedangkan KNN menghasilkan akurasi 87.2%. ============================================================ President Jokowi obviously always be the spotlight in the eyes of the public. He is in charge of fulfilling the expectations of Indonesian people, and will perform well if he gets full support from the people. This makes President Jokowi often being the topic of people’s talk about. Today, people can say their opinions and emotions through text on social media such as Twitter. Twitter is a microblog social network that allows users to send and read text messages. However, the emotions expressed by Twitter user are very diverse. Knowing people's responses based on their emotions will make President Jokowi knows what is must being evaluated more effectively. Therefore, are being needed a research to find opinions and emotions from the Twitter user. Public response about President Jokowi is obtained from the Application Program-ming Interface (API). Before classification process, preprocess text will be performed. The text praprocess tha is used are case folding, stopwords, and tokenizing. While in the text classification analysis is used Support Vector Machine (SVM) and K-Nearest Neighbor (KNN) method. Predictive accuracy of Classification using SVM yields 95.2%. While for method KNN yield accuracy is 87.2%

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Jokowi, , K-Nearest Neighbor, Klasifikasi Emosi, Support Vector Machine, Twitter
Subjects: H Social Sciences > HD Industries. Land use. Labor > HD108 Classification (Theory. Method. Relation to other subjects )
Q Science > Q Science (General) > Q180.55.M38 Mathematical models
Q Science > QA Mathematics > QA336 Artificial Intelligence
Q Science > QA Mathematics > QA353.K47 Kernel functions (analysis)
Q Science > QA Mathematics > QA402 System analysis.
Q Science > QA Mathematics > QA75 Electronic computers. Computer science. EDP
Q Science > QA Mathematics > QA76.6 Computer programming.
Q Science > QA Mathematics > QA76.9.D343 Data mining
Q Science > QA Mathematics > QA76.9.I52 Information visualization
T Technology > T Technology (General) > T57.5 Data Processing
Divisions: Faculty of Mathematics and Science > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User: Fazlur Rahman
Date Deposited: 19 Jun 2021 15:26
Last Modified: 19 Jun 2021 15:26
URI: https://repository.its.ac.id/id/eprint/57716

Actions (login required)

View Item View Item