Sentiment Analysis on Twitter Against IndiHome Providers Using Chi-Square and Ensemble Bagging Methods
- Anisa Nur Aini Telkom University, Bandung, Indonesia
-
Jondri Jondri
*
Telkom University, Bandung,
Indonesia
- Widi Astuti Telkom University, Bandung, Indonesia (*) Corresponding Author
Abstract
During the Covid-19 pandemic, internet usage has increased rapidly. Now the internet is used as a means in the online teaching and learning process and work from home. One of the internet service providers is IndiHome. IndiHome is an internet service provider company that has a huge number of users. A large number of IndiHome users causes frequent problems, and this is one of the factors that IndiHome users provide various kinds of opinions or responses. Sentiment analysis is used to see the opinion or opinion given by someone on a particular object or problem. This study conducted a sentiment analysis using the Chi-square and the Ensemble Bagging method with three base classifier methods, namely K-Nearest Neighbor (K-NN), Support Vector Machine (SVM), and Naive Bayes (NB). Prediction results on labels obtained from each base classifier are combined using a hard majority vote. Tweet data collection was carried out in March 2022, and 6,962 tweets were collected. This study conducted two test scenarios. Scenario 1 is a scenario without oversampling with test results showing that Ensemble Bagging has the highest accuracy value of 83.32%, and in scenario 1 with hyperparameter tuning, Ensemble Bagging has the highest accuracy value of 83.93%. Scenario 2 is a scenario with oversampling, showing that Ensemble Bagging has the highest accuracy value of 84.51%, and scenario 2 with hyperparameter tuning also shows Ensemble Bagging has the highest accuracy value of 84.56%.
Downloads
References
DOI 10.47065/bits.v4i2.1901[1] “Peluang penetrasi Internet dan Tantangan Regulasi Daerah : Asosiasi Penyelenggara Jasa Internet Indonesia,” 2021.
“Penetrasi & Profil Perilaku Pengguna Internet Indonesia: Asosiasi Penyelenggara Jasa Internet Indonesia,” 2018.
Bill Clinten, “Pengguna Aktif Harian Twitter Indonesia Diklaim Terbanyak,” Kompas.com, Aug. 2019. https://tekno.kompas.com/read/2019/10/30/16062477/pengguna-aktif-harian-twitter-indonesia-diklaim-terbanyak (accessed Jul. 22, 2022).
C. S. Rao, G. S. Prasad, and V. V. Rao, “Prediction and Analysis of Sentiments on Twitter Data using Hybrid Naive Bayes Approach,” International Journal of Innovative Technology and Exploring Engineering (IJITEE), vol. 8, no. 8, pp. 2278–3075, 2019.
S. Farah Aliyah, H. Yasin, B. Warsito, T. Widiharis, D. Statistika, and F. Sains dan Matematika, “Analisis Sentimen PT TIKI Jalur Nugraha Ekakurir (PT TIKI JNE) Pada Media Sosial Twitter Menggunakan Model Feed Forward Neural Network,” Stastistika, vol. 8, no. 2, pp. 103–113, 2020.
N. Dimas Pratama, Y. A. Sari, and P. P. Adikara, “Analisis Sentimen Pada ReviewKonsumen Menggunakan Metode Naive BayesDengan Seleksi Fitur Chi SquareUntuk Rekomendasi Lokasi Makanan Tradisional,” Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, vol. 2, no. 9, pp. 2982–2988, 2018, [Online]. Available: http://j-ptiik.ub.ac.id
D. B. Satmoko, P. Sukarno, and E. M. Jadied, “Peningkatan Akurasi Pendeteksian Serangan DDoS Menggunakan Multiclassifier Ensemble Learning dan Chi-Square,” e-Proceeding of Engineering, vol. 5, no. 3, pp. 7877–7985, 2018.
J. Ling, I. Putu, E. N. Kencana, and T. B. Oka, “Analisis Sentimen Menggunakan Metode Naïve Bayes Classifierdengan Seleksi Fitur Chi Square,” E-Jurnal Matematika, vol. 3, no. 3, pp. 92–99, 2014.
A. Nisa, E. Darwiyanto, and I. Asror, “Analisis Sentimen Menggunakan Naive Bayes Classifier dengan Chi-Square Feature Selection Terhadap Penyedia Layanan Telekomunikasi,” e-Proceeding of Engineering , vol. 6, pp. 8650–8658, 2019.
A. Susanto, M. Atho’il Maula, I. Utomo, W. Mulyono, and K. Sarker, “Sentiment Analysis on Indonesia Twitter Data Using Naïve Bayes and K-Means Method,” Journal of Applied Intelligent System, vol. 6, no. 1, pp. 40–45, 2021, [Online]. Available: http://kateglo.com.
B. Pahwa, S. Taruna, and N. Kasliwal, “Sentiment Analysis- Strategy for Text Pre-Processing,” International Journal of Computer Applications, vol. 180, no. 34, pp. 15–18, Apr. 2018, doi: 10.5120/ijca2018916865.
C. Toraman, E. H. Yilmaz, F. Şahinuç, and O. Ozcelik, “Impact of Tokenization on Language Models: An Analysis for Turkish,” Apr. 2022, [Online]. Available: http://arxiv.org/abs/2204.08832
A. W. Pradana and M. Hayaty, “The Effect of Stemming and Removal of Stopwords on the Accuracy of Sentiment Analysis on Indonesian-language Texts,” Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control, vol. 4, pp. 375–380, Oct. 2019, doi: 10.22219/kinetik.v4i4.912.
S. Sharma and M. Bansal, “Stemming and lemmatization of tweets for sentiment analysis using R,” International Journal of Recent Technology and Engineering, vol. 8, no. 2, pp. 2038–2040, Jul. 2019, doi: 10.35940/ijrte.B2157.078219.
I. C. Negara and A. Prabowo, “Penggunaan Uji Chi-Square untuk Mengetahui Pengaruh Tingkat Pendidikan dan Umur terhadap Pengetahuan Penasun Mengenai HIV-AIDS di Provinsi DKI Jakarta,” FMIPA Unsoed Purwokerto, pp. 1–8, 2018.
Zhi-Hua Zhou, “Ensemble Methods Foundations and Algorithms,” in Chapman & Hall/CRC Machine Learning & Pattern Recognition Series, 2012, pp. 47–66. Accessed: May 28, 2022. [Online]. Available: https://tjzhifei.github.io/links/EMFA.pdf
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Sentiment Analysis on Twitter Against IndiHome Providers Using Chi-Square and Ensemble Bagging Methods
Pages: 516-521
Copyright (c) 2022 Anisa Nur Aini, Jondri, Widi Astuti
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
