Jurnal SINTA 2
Analisis Sentimen terhadap Kebijakan Kuliah Daring Selama Pandemi Menggunakan Pendekatan Lexicon Based Features dan Support Vector Machine
Jurnal Teknologi Informasi dan Ilmu Komputer (JTIIK) · Vol. 9 No. 2 (2022) · pp. 357–362
- ISSN
- 2528-6579, 2355-7699
- Published
- 2022-02-24
- Publisher
- Fakultas Ilmu Komputer, Universitas Brawijaya
- Language
- id
Abstract
Adanya virus baru yaitu COVID-19 atau SARS-CoV-2 yang berasal dari Wuhan, China pada awal tahun 2020 telah menggemparkan seluruh warga dunia salah satunya Indonesia dan memiliki tingkat penularan yang tinggi. Sehingga untuk meminimalisir penyebaran COVID-19, pemerintah Indonesia menetapkan salah satu kebijakan dalam dunia pendidikan yaitu pembelajaran/perkuliah online. Kebijakan tersebut mengakibatkan seluruh penyebaran informasi berubah menjadi online dan memberikan dampak yang luas bagi keberlanjutan pendidikan di Indonesia. Hal tersebut menimbulkan kontroversi pada kalangan masyarakat dan banyak yang akhirnya beropini pada media sosial, salah satunya Twitter. Analisis sentimen berguna untuk mengetahui ketepatan komputasi sistem dalam mengenali pembicaraan pada Twitter mengenai kebijakan pembelajaran online cenderung bersentimen negatif atau positif dengan menggunakan metode Support Vector Machine dan Lexicon Based Features. Penggunaan Lexicon Based Features berpengaruh terhadap objek penelitian yang menghasilkan nilai accuracy 0,6, nilai precision 0,56, nilai recall 0,75, dan fmeasure 0,64 dengan parameter optimal dalam mencapai konvergensi yaitu???? (Lambda) = 0,7, nilai parameter???? (gamma) = 0,0001, nilai parameter???? (Kompleksitas) = 0,0001, iterasi = 50, dan???? (Epsilon) = 0,00000001. Hal tersebut menunjukkan bahwa metode yang digunakan pada penelitian ini dapat mengenali pembicaraan data komentar pada Twitter karena dibuktikan dengan nilai accuracy yang cukup tinggi.AbstractThe existence of a new virus, namely COVID-19 or SARS-CoV-2, that come from Wuhan, China, in early 2020, has shocked all citizens of the world, including Indonesia, and has a high transmission rate. So to minimize the spread of COVID-19, the Indonesian government has set one policy in online learning/lectures. This policy resulted in all information dissemination being online and had a broad impact on education in Indonesia. This policy caused controversy among the public, and many ended up giving opinions on social media, one of which was Twitter. Sentiment analysis is useful for determining the timeliness of system computing in discussions on Twitter regarding online learning policies that tend to have negative or positive sentiments using the Support Vector Machine and Lexicon Based Features methods. The use of Lexicon Based Features affects the object of research which produces an accuracy value of 0.6, a precision value of 0.56, a recall value of 0.75, and a size of 0.64 with the optimal parameter in achieving convergence, namely (Lambda) = 0.7, the parameter value (gamma) = 0.0001, the parameter value (Complexity) = 0.0001, iterations = 50, and (Epsilon) = 0.00000001. This evaluation value shows that the method used in this study can recognize the conversation of comment data on Twitter because a fairly high accuracy value evidences it.
Collaboration network of the authors
28 authors · 52 co-authorship links · 5 across different organisations
Hover or tap a name to highlight its co-authors. Double-click to open the author's page.
- University of Brawijaya
- Institut Teknologi Sepuluh Nopember
- Different organisations
- Same organisation
- Affiliation unknown
- Thicker line = more joint articles · bigger circle = more articles
Show as table
| Co-author | Organisation | Joint articles |
|---|---|---|
| Candra Dewi | University of Brawijaya | 2 |
| Rifki Akbar Siregar | University of Brawijaya | 2 |
| Agus Zainal Arifin | Institut Teknologi Sepuluh Nopember | 1 |
| Evy Kamilah Ratnasari | Institut Teknologi Sepuluh Nopember | 1 |
| Siti Mutrofin | Institut Teknologi Sepuluh Nopember | 1 |
| Fadhil Yusuf Rahadika | University of Brawijaya | 1 |
| Novanto Yudistira | University of Brawijaya | 1 |
| Chastine Fatichah | Institut Teknologi Sepuluh Nopember | 1 |
| Ratih Kartika Dewi | University of Brawijaya | 1 |
| Putra Pandu Adikara | University of Brawijaya | 1 |
| Sigit Adinugroho | University of Brawijaya | 1 |
| Andri Santoso | University of Brawijaya | 1 |
| Nadia Artha Dewi | University of Brawijaya | 1 |
| Yoke Kusuma Arbawa | University of Brawijaya | 1 |
| Bayu Rahayudi | University of Brawijaya | 1 |
| Rizky Maulana Iqbal | University of Brawijaya | 1 |
| Edy Santoso | University of Brawijaya | 1 |
| Raditya Rinandyaswara | University of Brawijaya | 1 |
| Muhammad Tanzil Furqon | University of Brawijaya | 1 |
| Alfisyar Jefry Pranata | University of Brawijaya | 1 |
| Edy Santoso | University of Brawijaya | 1 |
| Fitra Abdurrachman Bachtiar | University of Brawijaya | 1 |
| Aisyah Awalina | University of Brawijaya | 1 |
| Rangga Adi Satria | University of Brawijaya | 1 |
| Sutrisno Sutrisno | University of Brawijaya | 1 |
Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.