Mayasari, Rakhmah Wahyu (2018) Text Mining Pada Akun Resmi Pemerintah Kota Surabaya Dengan Metode Regresi Logistik, Support Vector Machine (Svm), Dan Naïve Bayes Classifier (Nbc). Undergraduate thesis, INSTITUT TEKNOLOGI SEPULUH NOPEMBER.
Preview |
Text
06211645000034-Undergraduate_Theses.pdf - Accepted Version Download (2MB) | Preview |
Abstract
Pemerintah merupakan suatu lembaga administrasi yang berwenang atas kegiatan masyarakat dalam sebuah negara, kota dan sebagainya. Dalam menjalankan suatu kepemerintahan, Surabaya senantiasa terbuka dalam menerima sebuah masukan. Salah saru media penyampaiannya yaitu media sosial. Twitter merupakan salah satu media sosial yang telah ramai digunakan. Akun twitter resmi yang digunakan oleh pemerintah kota Surabaya adalah Sapawarga Surabaya (@SapawargaSby). Adapun akun radio Suara Surabaya (@e100ss) juga menjadi tempat berkeluh kesah masyarakat Surabaya. Data dari twitter diambil menggunakan sistem Application Programming Interface, dimana data kemudian dilakukan analisis sentimen. Berdasarkan hasil dari analisis diketahui bahwa metode terbaik yang digunakan adalah Support Vector Machine (SVM) kernel Radial Basis Function (RBF) karena memiliki ketepatan klasifikasi tertinggi dari pada metode SVM kernel Linear, Naïve Bayes Classifire (NBC), dan Regresi Logistik. Dilakukan pula analisis menggunakan Social Network Analysis (SNA) yang menghasilkan kesimpulan bahwa urutan tiga akun twitter yang sangat berpengaruh adalah @e100ss, @SapawargaSby, dan @BanggaSurabaya.
=========================================================
Government is an administrative institution authorized for community activities in a country, city and so forth. In running a government, Surabaya is always open in receiving a suggestion. One of the media for delivering such suggestions is social media. Twitter is social media that has been used, wherever the official account used by Surabaya government is Sapawarga Surabaya (@SapawargaSby). The Radio Suara Surabaya official account (@e100ss) is also a place to express the opinion of Surabaya government performance. Data from twitter was taken using Application Programming Interface system, thereafter the data was analyzed sentiment. Based on the analysis results, it is known that the best method used is the Support Vector Machine (SVM) using Radial Basis Function kernel (RBF,) because it has the highest classification accuracy rather than kernel Linear, and also another method like Naïve Bayes Classifier (NBC), and Logistic Regression. In this study also perform an analysis using Social Network Analysis (SNA) which resulted in the conclusion that the sequence of three highly influential twitter account is @e100ss, @SapawargaSby, and @BanggaSurabaya.
| Item Type: | Thesis (Undergraduate) |
|---|---|
| Uncontrolled Keywords: | Analisis Sentimen, Naïve Bayes Classifier, Regresi Logistik, Social Network Analysis, Support Vector Machine |
| Subjects: | H Social Sciences > HD Industries. Land use. Labor > HD108 Classification (Theory. Method. Relation to other subjects ) Q Science > QA Mathematics > QA278.2 Regression Analysis. Logistic regression Q Science > QA Mathematics > QA279.5 Bayesian statistical decision theory. Q Science > QA Mathematics > QA76.9.D343 Data mining. Querying (Computer science) |
| Divisions: | Faculty of Mathematics, Computation, and Data Science > Statistics > 49201-(S1) Undergraduate Thesis |
| Depositing User: | Mayasari Rakhmah Wahyu |
| Date Deposited: | 09 Jul 2021 10:21 |
| Last Modified: | 09 Jul 2021 10:21 |
| URI: | http://repository.its.ac.id/id/eprint/57324 |
Actions (login required)
 |
View Item |