DOI: https://doi.org/10.14710/j.gauss.12.4.616-624

ANALISIS SENTIMEN PENGGUNA ONLINE TRAVEL AGENT (OTA) PADA PERUSAHAAN PEGIPEGI.COM MENGGUNAKAN RANDOM FOREST

*Ayu Lestari  -  Departemen Statistika, Jl. Prof. Sudarto, SH, Tembalang, Semarang, Indonesia 50275, Indonesia
Rukun Santoso  -  Departemen Statistika, Fakultas Sains dan Matematika, Universitas Diponegoro, Indonesia
Suparti Suparti  -  Departemen Statistika, Fakultas Sains dan Matematika, Universitas Diponegoro, Indonesia
Open Access Copyright 2024 Jurnal Gaussian under http://creativecommons.org/licenses/by-nc-sa/4.0.

Citation Format:
Abstract
The presence of the internet makes online applications increasingly attractive to the public in supporting their daily activities. Online applications have developed rapidly, including online travel agent (OTA) companies such as Pegipegi. Pegipegi is a platform designed to meet the community's tertiary needs, such as providing accommodations for vacations. Pegipegi has an application that can be downloaded through the Google Playstore. Google Playstore provides a review feature as a medium for communication between application owners and consumers to express opinions that felt when using the application. The reviews submitted can be used as data to carry out sentiment analysis. Data collection was carried out on 11 December 2021 – 11 December 2022. A total of 2926 reviews obtained. Sentiment analysis was able to proceed by a classification method. This research used Random Forest to classify opinions on positive and negative sentiments. Random Forest is a classification model based on the majority vote of all decision trees. Classification using Random Forest produces an accuracy of 92.27% and AUC-ROC of 82.35%. Based on this accuracy and AUC-ROC value, the Random Forest algorithm has a good model performance in classifying the opinions of Pegipegi application users because it has a good accuracy and AUC-ROC value.

Note: This article has supplementary file(s).

Fulltext View|Download |  Research Instrument
ANALISIS SENTIMEN PENGGUNA ONLINE TRAVEL AGENT (OTA) PADA PERUSAHAAN PEGIPEGI.COM MENGGUNAKAN RANDOM FOREST
Subject
Type Research Instrument
  Download (192KB)    Indexing metadata
Keywords: Application; Pegipegi; Sentiment Analysis, Random Forest

Article Metrics:

Article Info
Section: Articles
Language : ID
Recent articles
ANALISIS KEPUASAN TERHADAP LAYANAN APLIKASI DOLTINUKU DENGAN MENGGUNAKAN METODE STRUCTURAL EQUATION MODELING-PARTIAL LEAST SQUARE (SEM-PLS) PENERAPAN REGRESI COX PROPORTIONAL HAZARD PADA KEJADIAN BERSAMA (TIES) DENGAN METODE BRESLOW, EFRON, DAN EXACT ANALISIS SENTIMEN KEBIJAKAN PENYELENGGARA SISTEM ELEKTRONIK LINGKUP PRIVAT MENGGUNAKAN PENALIZED LOGISTIC REGRESSION DAN SUPPORT VECTOR MACHINE More recent articles
  1. Breiman, L., dan Cutler A. 2003. Manual on Setting Up, Using, and Understanding Random Forest V4.0. Tersedia: https://www.stat.berkeley.edu/~breiman/Using_random_ forests_v4.0.pdf (diakses pada tanggal 30 November 2023)
  2. Breiman, L. 2001. Random Forest. Machine Learning. Jurnal: University of California, Berkeley
  3. Feldman, R., dan Sanger, J. 2007. The Text Mining Handbook: Advanced approaches in Analyzing Unstructured Data. New York: Cambridge University Press
  4. Liu, B. 2015. Sentimen Analysis: Mining Opinions, Sentiments, and Emoticons. Cambridge: Cambridge University Press
  5. Maskoen, T. T., dan Purnama, D. (2018). Area Under the Curve dan Akurasi Cystatin C untuk Diagnosis Acute Kidney Injury pada Pasien Politrauma. Majalah Kedokteran Bandung, 50(4), 259–264. https://doi.org/10.15395/mkb.v50n4.1342
  6. Ningtyas, A. M. 2016. Pengaruh Penanganan Negasi Dalam Bahasa Indonesia Untuk Pelabelan Otomatis Pada Analisis Sentimen Twitter. Disertasi. Universitas Gadjah Mada Yogyakarta
  7. Nurjanah, W. E., Perdana, R. S., dan Fauzi, M. A. 2017. Analisis Sentimen Terhadap Tayangan Televisi Berdasarkan Opini Masyarakat Pada Media Sosial Twitter menggunakan K-Nearest Neighbour dan Pembobotan Jumlah Retweet. Jurnal Pengembangan Teknologi Informasi dan Ilmi Komputer, Vol.1, No.12, Hal: 1750-1757
  8. Olabenjo, B. 2016. Applying Naive Bayes Classification to Google Play Apps categorization. Jurnal: University of Saskatchewan
  9. Pegipegi. 2022. About Pegipegi. Tersedia: https://www.pegipegi.com/team/ (diakses pada tanggal 26 November 2022)
  10. Pradana, M. G. 2020. Penggunaan Fitur Wordcloud dan Document Term Matrix dalam Text Mining. Jurnal Ilmiah Informatika, Vol. 8, No.1, Hal: 38-43
  11. Sa’adah U., Rochayani, M. Y., Lestari, D. W., dan Lusia, D. A. 2021. Kupas Tuntas Algoritma Data Mining dan Implementasinya Menggunakan R. Malang: UBPress
  12. Santoso, E. B., dan Nugroho, A. 2019. Analisis Sentimen Calon Presiden Indonesia 2019 Berdasarkan Komentar Publik Di Facebook. Jurnal Eksplora Informatika, Vol. 9, No.1, Hal: 60-69
  13. Sari, V. R., Firdausi, F., dan Azhar, Y. 2020. Perbandingan Prediksi Kualitas Kopi Arabika dengan Menggunakan Algoritma SGD, Random Forest dan Naive Bayes. EDUMATIC: Jurnal Pendidikan Informatika, Vol. 4 No.2, Hal: 1-9
  14. Wardhani, N. W. S., Rochayani, M. Y, Iriany, A., Sulistyono, A. D., dan Lestantyo, P. 2019. Cross-validation Metrics for Evaluating Classification Performance on Imbalanced Data. Hal: 14-18

Last update:

No citation recorded.

Last update:

No citation recorded.