Jurnal SINTA 2
Rekomendasi Pengembangan Fasilitas Wisata Tugu Pahlawan Surabaya Melalui Visualisasi Dashboard Hasil Klasifikasi Analisis Sentimen Ulasan Pengunjung
Jurnal Teknologi Informasi dan Ilmu Komputer (JTIIK) · Vol. 9 No. 2 (2022) · pp. 363–372
- ISSN
- 2528-6579, 2355-7699
- Published
- 2022-02-24
- Publisher
- Fakultas Ilmu Komputer, Universitas Brawijaya
- Language
- id
Abstract
Tugu Pahlawan Surabaya merupakan salah satu pariwisata andalan Kota Surabaya yang selalu berupaya memperhatikan ulasan pengunjung sebagai acuan evaluasi. Namun, pengelola tidak memiliki teknologi yang mampu mengumpulkan, mengolah, dan menganalisis seluruh data ulasan yang dapat menghasilkan informasi secara ringkas. Salah satu solusi dapat dilakukan melalui analisis sentimen pada level aspek terhadap aspek edukasi, fasilitas, kebersihan, pelayanan, dan umum dengan penyajian informasi dalam bentuk dashboard. Analisis sentimen dilakukan menggunakan Support Vector Machine terhadap 2180 data ulasan selama 2 tahun terakhir yang diambil dari Google Review. Ulasan terbanyak terdapat pada aspek fasilitas sebanyak 538 ulasan dengan sebaran sentimen 285 ulasan positif, 95 ulasan negatif, dan 158 ulasan netral. Rekomendasi berdasarkan kekuatan dan kelemahan saat ini adalah penyediaan lahan atau objek foto bernuansa sejarah pahlawan secara lebih nyata serta penyediaan ventilasi terbuka atau standing cooler di beberapa area. Berdasarkan confusion matrix, nilai F1-Score menjadi penentu seberapa baik model mengklasifikan data daripada nilai Accuracy dikarenakan dataset yang dimiliki bersifat imbalance sehingga kesalahan prediksi pada precision atau recall sangat memungkinkan terjadi. Kesalahan prediksi banyak ditemukan pada kelas sentimen netral. Keseluruhan hasil klasifikasi disajikan dalam bentuk dashboard dengan nilai SUS Score 77,5, menandakan bahwa dashboard dapat diterima dengan baik oleh responden sebagai pengguna. Abstract Tugu Pahlawan Surabaya is one of the mainstays of tourism in Surabaya city which always tries to pay attention to visitor reviews as a reference for evaluation. However, the managers do not have technology capable of collecting, processing and analyzing all review datas that can produce information in a concise manner. One solution can be done through sentiment analysis at the aspect level of education, facilities, cleanliness, service, and general aspects by presenting information in the form of a dashboard. Sentiment analysis was carried out using the Support Vector Machine on 2180 review datas for the last 2 years taken from Google Reviews. The most reviews were on the facility aspect in total of 538 reviews with a sentiment distribution of 285 positive reviews, 95 negative reviews and 158 neutral reviews. Recommendations based on current strengths and weaknesses are providing more real area or photo objects with historical nuances of heroes and providing open ventilation or standing coolers in several areas. Based on the confusion matrix, the F1-Score value determines how well the model classifies data rather than the Accuracy value because the dataset is imbalance so that prediction errors in precision or recall are very possible. Prediction errors are more likely to be found in the neutral sentiment class. The overall classification results are presented in the form of a dashboard with a SUS Score of 77.5, indicating that the dashboard is well received by respondents
Collaboration network of the authors
40 authors · 93 co-authorship links · 42 across different organisations · showing the 40 most connected
Hover or tap a name to highlight its co-authors. Double-click to open the author's page.
- University of Brawijaya
- National Research and Innovation Agency
- Indonesian Institute of Sciences
- Institut Teknologi, Sains, dan Kesehatan RS.DR. Soepraoen Kesdam V/BRW
- Institut Teknologi Sepuluh Nopember
- Affiliation unknown
- Different organisations
- Same organisation
- Affiliation unknown
- Thicker line = more joint articles · bigger circle = more articles
Show as table
| Co-author | Organisation | Joint articles |
|---|---|---|
| Vicky Zilvan | Indonesian Institute of Sciences | 3 |
| Asri Rizki Yuliani | Indonesian Institute of Sciences | 3 |
| Ade Ramdan | Indonesian Institute of Sciences | 3 |
| Sutrisno . | Affiliation unknown | 2 |
| Tibyani Tibyani | University of Brawijaya | 2 |
| Hilman Ferdinandus Pardede | National Research and Innovation Agency | 2 |
| Wahyu Teja Kusuma | Institut Teknologi, Sains, dan Kesehatan RS.DR. Soepraoen Kesdam V/BRW | 2 |
| Herman Tolle | University of Brawijaya | 2 |
| Welly Purnomo | University of Brawijaya | 2 |
| Dian Eka Ratnawati | University of Brawijaya | 2 |
| Nur Laita Rizki Amalia | University of Brawijaya | 2 |
| Satrio Hadi Wijoyo | University of Brawijaya | 2 |
| Reza Andria S | Affiliation unknown | 1 |
| Sarwosri Sarwosri | Institut Teknologi Sepuluh Nopember | 1 |
| Imam Cholissodin | University of Brawijaya | 1 |
| Budi Darma Setiawan | University of Brawijaya | 1 |
| Farhanna Mar’i | University of Brawijaya | 1 |
| Rizal Arif Zulfikar | University of Brawijaya | 1 |
| I Putu Pradnyana Iswara | University of Brawijaya | 1 |
| Irvi Oktanisa | University of Brawijaya | 1 |
| Fitra Abdurrachman Bachtiar | University of Brawijaya | 1 |
| Iqbal Taufiq Ahmad Nur | University of Brawijaya | 1 |
| Aditya Hari Bawono | University of Brawijaya | 1 |
| Nabila Divanadia Luckyana | University of Brawijaya | 1 |
| Yusi Tyroni Mursityo | University of Brawijaya | 1 |
| Yustinus Radityo Pradana | University of Brawijaya | 1 |
| Komang Candra Brata | University of Brawijaya | 1 |
| Santi Yunika Sufiana | University of Brawijaya | 1 |
| Mochammad Izzuddin | University of Brawijaya | 1 |
| Syaiful Anam | University of Brawijaya | 1 |
| Onky Prasetyo | University of Brawijaya | 1 |
| R. Budiarianto Suryo Kusumo | National Research and Innovation Agency | 1 |
| Abdul Harris Wicaksono | University of Brawijaya | 1 |
| Didik Krisnandi | National Research and Innovation Agency | 1 |
| Ana Heryana | National Research and Innovation Agency | 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.