TY - GEN
T1 - What Users Want for Gig Economy Platforms
T2 - 6th International Conference on Science in Information Technology, ICSITech 2020
AU - Indrawan, Nadina Adelia
AU - Sucahyo, Yudho Giri
AU - Ruldeviyani, Yova
AU - Gandhi, Arfive
N1 - Funding Information:
This research was supported by Universitas Indonesia under the PITTA Grants 2018 of “Risk Evaluation and Improvement Startegies for Platform-based Startup Business” (No: 1899/UN2.R3.1/HKP.05.00/2018). We would like to express our gratitude to the Faculty of Computer Science and the Directorate of Research and Community Engagement, Universitas Indonesia.
Funding Information:
This research was supported by Universitas Indonesia under the PITTA Grants 2018 of "Risk Evaluation and Improvement Startegies for Platform-based Startup Business" (No: 1899/UN2.R3.1/HKP.05.00/2018). We would like to express our gratitude to the Faculty of Computer Science and the Directorate of Research and Community Engagement, Universitas Indonesia.
Publisher Copyright:
© 2020 IEEE.
PY - 2020/10/21
Y1 - 2020/10/21
N2 - Gig economy-based mobile applications are increasingly in demand by the public. An increment in the number of users rises the number of downloads and reviews. However, the number of reviews makes it difficult for developers to understand the information contained in reviews. Besides, one review can have a variety of information. This study proposes a model that can categorize content and sentiment reviews using Support Vector Machine (SVM), Multinomial Naïve Bayes, Complement Naïve Bayes classifier, and Binary Relevance, Classifier Chain, and Label Power Sets as the data transformation method. This study used the reviews contained in the Gojek, Sampingan, and Ruang Guru applications, with 10, 123 reviews. This study found the review text's length influenced accuracy based on the evaluation of Gojek application. Generally, this study results showed that the SVM algorithm (both in the classification of sentiment reviews and review categorization) and Label Power Sets as the transformation method, yielded the best accuracy.
AB - Gig economy-based mobile applications are increasingly in demand by the public. An increment in the number of users rises the number of downloads and reviews. However, the number of reviews makes it difficult for developers to understand the information contained in reviews. Besides, one review can have a variety of information. This study proposes a model that can categorize content and sentiment reviews using Support Vector Machine (SVM), Multinomial Naïve Bayes, Complement Naïve Bayes classifier, and Binary Relevance, Classifier Chain, and Label Power Sets as the data transformation method. This study used the reviews contained in the Gojek, Sampingan, and Ruang Guru applications, with 10, 123 reviews. This study found the review text's length influenced accuracy based on the evaluation of Gojek application. Generally, this study results showed that the SVM algorithm (both in the classification of sentiment reviews and review categorization) and Label Power Sets as the transformation method, yielded the best accuracy.
KW - classification
KW - machine learning
KW - multi-label
KW - sentiment analysis
KW - user reviews
UR - http://www.scopus.com/inward/record.url?scp=85104540644&partnerID=8YFLogxK
U2 - 10.1109/ICSITech49800.2020.9392060
DO - 10.1109/ICSITech49800.2020.9392060
M3 - Conference contribution
AN - SCOPUS:85104540644
T3 - 2020 6th International Conference on Science in Information Technology: Embracing Industry 4.0: Towards Innovation in Disaster Management, ICSITech 2020
SP - 68
EP - 73
BT - 2020 6th International Conference on Science in Information Technology
A2 - Kasim, Anita Ahmad
A2 - Pranolo, Andri
A2 - Hernandez, Leonel
A2 - Wibawa, Aji Prasetya
A2 - Voliansky, Roman
A2 - Ngemba, Hajra Rasmita
A2 - Drezewski, Rafal
A2 - Zachir, Zachir
A2 - Haviluddin, Haviluddin
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 21 October 2020 through 22 October 2020
ER -