Analisis Kompetitif Transportasi Umum Konvensional dan Online pada Saat COVID-19 di Media Sosial Twitter

Widyarindra, Elen Nova (2021) Analisis Kompetitif Transportasi Umum Konvensional dan Online pada Saat COVID-19 di Media Sosial Twitter. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.

Text 10611710000016-Undergraduate_Theses.pdf - Accepted Version Restricted to Repository staff only until 1 October 2023. Download (1MB) | Request a copy

Abstract

Pandemi COVID-19 berdampak buruk pada pekerja mandiri yang bergantung pada sistem kerja berdasarkan permintaan atau Sharing Economy. Adanya peraturan Pembatasan Sosial Berskala Besar (PSBB) dan Work from Home (WFH) yang membuat pengguna taksi menurun sehingga mengakibatkan pendapatan perusahaan juga mengalami penurunan. Salah satu angkutan umum yang sering digunakan oleh masyarakat adalah taksi. Berkembangnya layanan taksi berbasis online membuat persaingan dengan taksi konvensional seringkali menuai berbagai tanggapan publik di media sosial. Penelitian ini dilakukan untuk mengetahui tanggapan masyarakat atau opini tentang taksi konvensional dan taksi online di media sosial Twitter. Metode yang digunakan adalah Naïve Bayes Classifier (NBC) dan Support Vector Machine (SVM). Tweet yang membahas taksi online paling banyak adalah bersentimen negatif sebesar 64%, sedangkan yang membahas taksi konvensional paling banyak bersentimen positif sebesar 58%. Metode SVM merupakan metode terbaik untuk mengklasifikasikan tweet taksi online dengan AUC bernilai 65% dan G-mean sebesar 59%, sedangkan metode NBC merupakan metode terbaik untuk mengklasifikasikan tweet taksi konvensional dengan nilai accuracy, sensitivity dan specificity sebesar 67%, 60% dan 77%.
================================================================================================
The COVID-19 pandemic has had a devastating impact on self-
employed workers who depend on the on-demand work system or the
Sharing Economy. The existence of Large-Scale Social Restrictions
(PSBB) and Work from Home (WFH) regulations which have reduced
taxi users, resulting in a decrease in company income. One of the public
transportation that is often used by the public is a taxi. The development
of online-based taxi services makes competition with conventional taxis
often made various public responses on social media. This research was
conducted to find out public responses or opinions about conventional
taxis and online taxis on Twitter social media. The methods used are
Naive Bayes Classifier (NBC) and Support Vector Machine (SVM).
Tweets that discuss online taxis have the most negative sentiments by
64%, while those that discuss conventional taxis have the most positive
sentiments by 58%. The SVM method is the best method for classifying
online taxi tweets with an AUC of 65% and a G-mean of 59%, while the
NBC method is the best method for classifying conventional taxi tweets
with accuracy, sensitivity and specificity values of 67%, 60% and 77%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	NBC, SVM, Taksi, Tanggapan, Twitter, NBC, Perception, SVM, Taxi, Twitter.
Subjects:	H Social Sciences > HE Transportation and Communications > HE336.C5 Choice of transportation Q Science > QA Mathematics > QA76.9.D343 Data mining. Querying (Computer science) R Medicine > RA Public aspects of medicine > RA644.C67 COVID-19 (Disease)
Divisions:	Faculty of Vocational > 49501-Business Statistics
Depositing User:	Elen Nova Widyarindra
Date Deposited:	16 Aug 2021 04:57
Last Modified:	16 Aug 2021 04:57
URI:	http://repository.its.ac.id/id/eprint/86938

Actions (login required)

View Item