Sentiment Analysis of Delivery Services Using the Sastrawi Library and Biobii Naive Bayes Text Classifier
DOI:
Keywords:
Abstract
Sentiment analysis from social media is an important aspect to find out people's views. This research produces a web-based system that can analyze public sentiment towards a delivery service based on social media Twitter (currently X). The technology used is the Twitter(X) API, Sastrawi library and Biobii Naïve Bayes text classifier. The Twitter(X) API is used to retrieve data from the Twitter(X) social media platform, while the Sastrawi library is used to process and analyze texts in Indonesian. In this system users can enter certain keywords or hashtags for analysis. The collected tweet data is then processed using a customized Naïve Bayes text classifier Library to identify positive and negative sentiments towards the services offered by a delivery service company. The results of sentiment analysis are displayed in the form of informative graphical visualizations, providing a better understanding of customer views regarding the service. The accuracy of the sentiment analysis results produced was based on testing with one of the delivery service companies, obtaining results with a value of 93.75% accurate.
Downloads
References
[1] M. S. Mustofa, T. Wijayanti, N. A. Putri, and D. Hermawan, “Strategies for increasing the competitiveness of micro-businesses in using e-commerce amidst the Covid-19 pandemic,” Stud. Appl. Econ., vol. 40, no. 2, 2022, doi: 10.25115/eea.v40i2.5541.
[2] M. A. Camilleri, “E-commerce websites, consumer order fulfillment and after-sales service satisfaction,” J. Strategy Manag., vol. 15, no. 3, 2022, doi: 10.1108/JSMA-02-2021-0045.
[3] S. G. Ajiniyazovna, “Implementation of e-commerce security methods and tools,” Int. J. Emerg. Trends Eng. Res., vol. 8, no. 5, 2020, doi: 10.30534/ijeter/2020/12852020.
[4] M. Nashar, A. Hariadi D. P., and R. D. Parashakti, “E-commerce, economic growth and gross domestic product to the demand for delivery goods,” Int. J. Organ. Innov., vol. 12, no. 3, 2020.
[5] G. Battumur, K. Gantumur, and W. Kim, “Factors affecting satisfaction with the postal delivery service,” Int. J. Adv. Appl. Sci., vol. 10, no. 1, 2023, doi: 10.21833/ijaas.2023.01.015.
[6] E. Febriyani and H. Februariyanti, “Analisis sentimen terhadap program Kampus Merdeka menggunakan Naive Bayes classifier di Twitter,” J. Tekno Kompak, vol. 17, no. 1, 2023.
[7] M. Murni, I. Riadi, and A. Fadlil, “Analisis sentimen hatespeech pada pengguna layanan Twitter,” JURIKOM, vol. 10, no. 2, 2023, doi: 10.30865/jurikom.v10i2.5984.
[8] Y. A. Rohman and R. Kusumaningrum, “Twitter storytelling generator using LDA and HMM POS-tag,” in Proc. ICICOS, 2019, doi: 10.1109/ICICoS48119.2019.8982411.
[9] N. Garg, “Annotated corpus creation for sentiment analysis in Hinglish social network data,” Indian J. Sci. Technol., vol. 13, no. 40, 2020, doi: 10.17485/ijst/v13i40.1451.
[10] N. Ilk and S. Fan, “Combining textual cues with social clues for sentiment analysis,” Decis. Sci., vol. 53, no. 2, 2022, doi: 10.1111/deci.12490.
[11] S. W. Ritonga, M. Fikry, and E. P. Cynthia, “Klasifikasi sentimen masyarakat di Twitter terhadap Ganjar Pranowo,” BITS, vol. 5, no. 1, 2023, doi: 10.47065/bits.v5i1.3535.
[12] C. L. Rujiani, E. R. Syahputra, and S. D. Andriana, “Implementation of API using REST architecture,” Int. J. Data Sci. Vis., vol. 1, no. 1, 2022.
[13] D. A. S. G. Putra Kusuma, “Designing REST architecture for school MIS,” Int. J. Emerg. Trends Eng. Res., vol. 8, no. 7, 2020, doi: 10.30534/ijeter/2020/124872020.
[14] A. Syaifuddin and M. Muslimin, “Analisis sentimen implementasi kebijakan PSE Kominfo,” Seminar Nas. Fak. Tek., vol. 1, no. 1, 2022, doi: 10.36815/semastek.v1i1.2.
[15] W. Bourequat and H. Mourad, “Sentiment analysis for iPhone release using SVM,” Int. J. Adv. Data Inf. Syst., vol. 2, no. 1, 2021, doi: 10.25008/ijadis.v2i1.1216.
[16] U. Nawaz, A. Ali, and K. S. U. A. Raza, “Survey on sentiment analysis using ML techniques,” Int. J. Adv. Trends Comput. Sci. Eng., vol. 10, no. 2, 2021, doi: 10.30534/ijatcse/2021/1091022021.
[17] H. Suroso, I. Budi, A. B. Santoso, and P. K. Putra, “Sentiment analysis on homecoming restriction policy,” in Proc. IC2IE, 2020, doi: 10.1109/IC2IE50715.2020.9274609.
[18] G. Sailasya and G. L. A. Kumari, “Stroke prediction using ML algorithms,” Int. J. Adv. Comput. Sci. Appl., vol. 12, no. 6, 2021, doi: 10.14569/IJACSA.2021.0120662.
[19] M. A. Rosid et al., “Improving text preprocessing for complaint classification,” IOP Conf. Ser. Mater. Sci. Eng., vol. 874, no. 1, 2020, doi: 10.1088/1757-899X/874/1/012017.
[20] M. Syarifuddin, “Analysis of public opinion sentiment on Covid-19 using NB and KNN,” Inti Nusa Mandiri, vol. 15, no. 1, 2020.
[21] J. Pfeffer et al., “Assessing coverage and temporal reliability of Twitter’s Academic API,” Proc. ICWSM, vol. 17, 2023, doi: 10.1609/icwsm.v17i1.22182.
[22] M. Heak and S. H. Choi, “Dynamic crawling system for news extraction,” Int. J. Adv. Sci. Technol., vol. 28, no. 3, 2019.
[23] A. A. I. A. Maharani, S. S. Prasetiyowati, and Y. Sibaroni, “Classification of public sentiment on fuel price increases using CNN,” Sinkron, vol. 8, no. 3, 2023, doi: 10.33395/sinkron.v8i3.12609.
[24] R. Kosasih and A. Alberto, “Sentiment analysis of game products on Shopee,” ILKOM J. Ilm., vol. 13, no. 2, 2021, doi: 10.33096/ilkom.v13i2.721.101-109.
[25] A. S. Rizki, A. Tjahyanto, and R. Trialih, “Comparison of stemming algorithms for Indonesian text,” TELKOMNIKA, vol. 17, no. 1, 2019, doi: 10.12928/TELKOMNIKA.v17i1.10183.
[26] C. F. Hasri and D. Alita, “Penerapan NBC dan SVM pada analisis sentimen dampak Covid-19,” JATIKA, vol. 3, no. 2, 2022.
[27] D. F. Risa, F. Pradana, and F. A. Bachtiar, “Implementasi Naive Bayes untuk mendeteksi stres siswa berdasarkan tweet,” J. Tek. Inf. Ilmu Komput., vol. 8, no. 6, 2021, doi: 10.25126/jtiik.2021864372.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Eko Budi Setiawan, Muhammad Lutfie Zakaria (Author)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
