Sentiment Analysis of Twitter Users’ Opinion Towards Face-to-Face Learning
Analisis Sentimen Tanggapan Masyarakat Pengguna Twitter terhadap Pembelajaran Tatap Muka
DOI:
https://doi.org/10.29244/ijsa.v7i1p15-31Keywords:
binary logistic regression, face-to-face learning, sentiment analysis, twitterAbstract
In early 2022, the government allowed face-to-face learning again after approximately one year of online learning. When face-to-face learning will be held again in several areas, the number of Covid-19 has increased and the government has imposed the enforcement of restrictions on community activities. The pros and cons of face-to-face learning also occur on social media, one of them is on Twitter. This study used twitter data for January 30th – February 7th 2022. Opinions on twitter regarding face-to-face learning were studied by sentiment analysis using the binary logistic regression method with sentiment classes being positive and negative. Labeling uses based on the final score of the difference between the number of positive and negative words. The purpose of this study is to determine the public’s perception of the policy of implementing face-to-face learning in the era of the Covid-19 on social media especially Twitter. From this study, public’s perception tends to be in a negative direction which indicates that they have not agreed enough with the existence of face-to-face learning in the period of February 2022 with the accuracy was 85%, sensitivity was 77%, specificity was 88%, and AUC was 91%.
Downloads
References
Aliyah SF, Yasin H, Suparti, Warsito B, Widiharis T. 2020. Analisis sentimen PT Tiki Jalur Nugraha Ekakurir (PT Tiki JNE) pada media sosial twitter menggunakan model feed forward neural network. Statistika. 8(2): 103-113.
Chavoshi N, Mueen A. 2018. Model bots, not humans on social media. International Conference on Advances in Social Networks Analysis and Mining (ASONAM). 178-185.
Chu Z, Gianvecchio S, Wang H. 2010. Who is tweeting on twitter: human, bot, or cyborg? Twenty-Sixth Annual Computer Security Applictaions Conference, ACSAC. 21-30.
Hosmer DW, Lemeshow S, Studrivant RX. 2013. Applied Logistic Regression. 3rd ed. New Jersey (US): John Wiley and Sons, Inc.
[Kemendibud] Kementrian Pendidikan, Kebudayaan, Riset, dan Teknologi. Surat Edaran Mendikbud Nomor 4 Tahun 2020 Tentang Pelaksanaan Kebijakan Pendidikan dalam Masa Darurat Penyebaran Corona Virus Disease (Covid-19). 2020.
Khotimah N. 2019. Analisis sentimen terhadap review e-commerce dengan metode stochastic gradient descent [skripsi]. Semarang: Universitas Muhammadiyah Semarang.
Krawzyck B. 2016. Learning from imbalanced data: open challenges and future directions. Prog Artif Intell. 5: 221-232. doi: 10.1007/s13748-016-0094-0.
Pratama PG, Rakhmawati NA. 2019. Social bot detection on 2019 Indonesia’s president candidate’s supporter’s tweets. The Fifth Information Systems International Conference 2019. 161: 813-820.
Refaeilzadeh P, Tang L, Liu H. 2009. Cross-Validation. In: Liu L., Özsu M. (eds) Encyclopedia of Database Systems. New York (NY): Springer. doi: https://doi.org/10.1007/978-1-4899-7993-3_565-2.
Santoso EB, Nugroho A. 2019. Analisis sentimen calon presiden Indonesia 2019 berdasarkan komentar publik di facebook. Jurnal Eksplora Informatika. 9(1): 60-69.
Sari EDN, Irhamah. 2019. Analisis sentimen nasabah pada layanan perbankan menggunakan metode regresi logistik biner, Naïve Bayes classifier (NBC), dan support vector machine (SVM). Jurnal Sains dan Seni ITS. 8(2): 177-184.
Siddiqi N. 2006. Credit Risk Scorecards: Developing and Implementing Intelligent Credit Scoring. New Jersey (US): John Wiley and Sons, Inc.
