KUSUMA, AMELIA VERGI (2022) KLASIFIKASI KELUHAN MAHASISWA DI MEDIA SOSIAL WHATSAPP MENGGUNAKAN METODE NAIVE BAYES DAN SUPPORT VECTOR MACHINE. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
01 Cover.pdf Download (1MB) | Preview |
|
|
Text (ABSTRAK)
02 Abstrak.pdf Download (24kB) | 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 (77kB) |
|
|
Text (BAB II)
04 Bab 2.pdf Restricted to Registered users only Download (189kB) |
|
|
Text (BAB III)
05 Bab 3.pdf Restricted to Registered users only Download (52kB) |
|
|
Text (BAB IV)
06 Bab 4.pdf Restricted to Registered users only Download (56kB) |
|
|
Text (BAB V)
07 Bab 5.pdf Restricted to Registered users only Download (28kB) |
|
|
Text (BAB VI)
08 Bab 6.pdf Restricted to Registered users only Download (431kB) |
|
|
Text (DAFTAR PUSTAKA)
09 Daftar Pustaka.pdf Restricted to Registered users only Download (96kB) |
|
|
Text (LAMPIRAN)
10 Lampiran.pdf Restricted to Registered users only Download (267kB) |
Abstract
The quality of an educational institution is one of the main reasons for every student who will go through the educational process. Quality in higher education can be seen from the formulation of its vision and mission, which is then realized in the educational process that will be carried out, besides that the quality of higher education is also determined by the number of complaints given by all education implementers at the university. In improving its quality, the university implements a change strategy from various aspects. However, in making these changes it is still not optimal so that it is not uncommon for the majority of students to submit their complaints through the WhatsApp application. These complaints occur due to unwanted events or things that occur that are not in accordance with the expectations of the education implementer. Based on this, it is necessary to classify text documents by utilizing text mining techniques in categorizing and grouping texts. In this study, the researchers classified using the Naive Bayes method and the Support Vector Machine for the classification of student complaints and then tested both methods using the confusion matrix calculation so as to produce accuracy, precision and f1-measure values where the Support Vector Machine algorithm has better performance in classifying complaints compared to the Naïve Bayes algorithm. The Support Vector Machine algorithm produces an accuracy value of 0.938, a precision value of 0.942, a recall value of 0.990 and an f1-measure value of 0.965. Meanwhile, the Naïve Bayes algorithm produces an accuracy value of 0.882, a precision value of 0.880, a recall value of 1,000 and an f1-measure value of 0.936. From the results of the accuracy of the study, it can be proven that not many complaints are submitted through WhatsApp social media which is generally owned by students. Mutu atau kualitas sebuah lembaga pendidikan menjadi salah satu alasan utama bagi setiap peserta didik yang akan melalui proses pendidikannya. Mutu dalam perguruan tinggi bisa dilihat dari rumusan visi dan misinya, yang kemudian diwujudkan dalam proses pendidikan yang akan dilakukan, selain itu mutu perguruan tinggi itu juga ditentukan oleh banyaknya complain yang diberikan oleh seluruh pelaksana pendidikan di perguruan tinggi tersebut. Dalam meningkatkan mutunya pihak perguruan tinggi melakukan strategi perubahan dari berbagai aspek. Akan tetapi dalam melakukan perubahan tersebut masih belum maksimal sehingga tidak jarang mayoritas mahasiswa menyampaikan keluhannya melalui aplikasi whatsapp. Keluhan tersebut terjadi akibat adanya kejadian yang tidak diinginkan atau hal yang terjadi tidak sesuai harapan pelaksana pendidikan. Berdasarkan hal tersebut diperlukannya klasifikasi dokumen teks dengan memanfaatkan text mining teknik dalam melakukan pengkategorisasian dan pengelompokan teks. Pada penelitian ini peneliti melakukan klasisifikasi menggunakan metode Naive Bayes dan Support Vector Machine terhadap klasifikasi keluhan mahasiswa kemudian melakukan pengujian terhadap kedua metode tersebut menggunakan perhitungan confusion matrix sehingga menghasilkan nilai accuracy, precision dan f1-measure yang mana algoritma Support Vector Machine memiliki performansi lebih baik dalam mengklasifikasikan keluhan dibanding algoritma Naïve Bayes. Algoritma Support Vector Machine dihasilkan nilai accuracy sebesar 0.938, nilai precission sebesar 0.942, nilai recall sebesar 0.990 dan nilai f1-measure sebesar 0.965. Sedangkan, untuk algoritma Naïve Bayes menghasilkan nilai accuracy sebesar 0.882, nilai precission sebesar 0.880, nilai recall sebesar 1.000 dan nilai f1-measure sebesar 0.936. Dari hasil akurasi penelitian bisa dibuktikan bahwa keluhan tidak banyak disampaikan melalui media sosial whatsapp yang umumnya dimiliki oleh mahasiswa.
Actions (login required)
 |
View Item |
