Using Multi-Label Classification Methods to Analyze Complaints Against Cargo Services During the COVID-19 Outbreak: Comparing Survey-Based and Word-Based Labeling

ÇALLI, Levent; Kuyucuk, Tolga

doi:10.35377/saucis.05.03.1121830

Using Multi-Label Classification Methods to Analyze Complaints Against Cargo Services During the COVID-19 Outbreak: Comparing Survey-Based and Word-Based Labeling

Tolga KUYUCUK, (Sakarya Üniversitesi, Bilgisayar ve Bilişim Bilimleri Fakültesi, Bilişim Sistemleri Mühendisliği Bölümü, Sakarya, Türkiye)

Levent ÇALLI (Sakarya Üniversitesi, Bilgisayar ve Bilişim Bilimleri Fakültesi, Bilişim Sistemleri Mühendisliği Bölümü, Sakarya, Türkiye)

Sakarya University Journal of Computer and Information Sciences (Online)

8 3

Yıl: 2022 Cilt: 5 Sayı: 3 Sayfa Aralığı: 371 - 384 Metin Dili: İngilizce DOI: 10.35377/saucis.05.03.1121830 İndeks Tarihi: 31-12-2022

Using Multi-Label Classification Methods to Analyze Complaints Against Cargo Services During the COVID-19 Outbreak: Comparing Survey-Based and Word-Based Labeling

Öz:

This study investigates how cargo companies, with a significant market share in Turkey's service sector, managed their last-mile activities during the Covid-19 outbreak and suggests the solution to the adverse outcomes. The data used in the study included complaints made for cargo companies from an online complaint management website called sikayetvar.com from the start of the pandemic to the date of the research, which contained words related to the pandemic and was collected using Python language and the Scrapy module web scraping methods. Multilabel classification algorithms were used to categorize complaints based on assessments of training data obtained according to the topics. Results showed that parcel delivery-related themes were the most often complained about, and a considerable portion were delay issues.

Anahtar Kelime: Covid-19 web scraping cargo companies customer complaints multi-label classification text mining

Belge Türü: Makale Makale Türü: Araştırma Makalesi Erişim Türü: Erişime Açık

[1] V. Surveillances, “The epidemiological characteristics of an outbreak of 2019 novel coronavirus diseases (COVID-19) in China,” Zhonghua Liu Xing Bing Xue Za Zhi, vol. 41, no. 2, pp. 145– 151, 2020, doi: 10.3760/cma.j.issn.0254-6450.2020.02.003.
[2] Z. Y. Zu et al., “Coronavirus Disease 2019 (COVID-19): A Perspective from China,” Radiology, vol. 296, no. 2. pp. E15–E25, 2020, doi: 10.1148/radiol.2020200490.
[3] F. Budak and Ş. Korkmaz, “Covid-19 Pandemi Sürecine Yönelik Genel Bir Değerlendirme: Türkiye Örneği,” Sos. Araştırmalar ve Yönetim Derg., no. 1, pp. 62–79, May 2020, doi: 10.35375/sayod.738657.
[4] GoogleNews, “Koronavirüs (COVID-19),” 2022. https://news.google.com/covid19/map?hl=tr&mid=%2Fm%2F02j71&gl=TR&ceid=TR%3Atr.
[5] M. Bulut, “Analysis of The Covid-19 Impact on Electricity Consumption and Production,” Sak. Univ. J. Comput. Inf. Sci., vol. 3, no. 3, 2020, doi: 10.35377/saucis.03.03.817595.
[6] B. Kaya and A. Günay, “Twitter Sentiment Analysis Based on Daily Covid-19 Table in Turkey,” Sak. Univ. J. Comput. Inf. Sci., vol. 4, no. 3, 2021, doi: 10.35377/saucis...932620.
[7] L. Çallı and B. A. Çallı, “Covid-19 Aşı Tereddütüne Sahip Hekimlerin Gizli Dirichlet Ayrımı (GDA) Algoritmasıyla Twitter Paylaşımlarının Konu Modellemesi,” in 8th International Management Information Systems Conference, 2021, no. October, pp. 91–103.
[8] V. Alfonso, C. Boar, J. Frost, L. Gambacorta, and J. Liu, “E-Commerce in the Pandemic and Beyond,” BIS Bull., vol. 220, no. 44, 2021, [Online]. Available: https://ideas.repec.org/p/bis/bisblt/36.html.
[9] E-TicaretBilgiPlatformu, “2020 Yılı İstatistikleri (Ocak - Aralık),” 2021. https://www.eticaret.gov.tr/istatistikler.
[10] ETBİS, “Elektronik Ticaret Bilgi Sistemi (Etbis) 2021 Yılı Verileri,” 2022. https://www.eticaret.gov.tr/dnnqthgzvawtdxraybsaacxtymawm/content/FileManager/Dosyalar/ 2021 Yılı E-Ticaret Bülteni.pdfpdf.
[11] H. Güven, “Covid-19 Sürecinde E-Ticaret Sitelerine Yöneltilen Müşteri Şikâyetlerinin İncelenmesi,” J. Turkish Stud., vol. Volume 15, no. Volume 15 Issue 4, pp. 511–530, 2020, doi: 10.7827/turkishstudies.44354.
[12] A. Parlakkılıç, M. Üzmez, and S. Mertoğlu, “How Does Covid-19 Pandemic Effect Online Shopping in E-Commerce?,” J. Bus. Digit. Age, vol. 3, no. 2, pp. 117–122, 2020, doi: 10.46238/jobda.823955.
[13] Etid, “EY Parthenon & ETİD COVID 19 Yönetici ve KOBİ Anketleri,” 2020. [Online]. Available: https://assets.ey.com/content/dam/ey-sites/ey-com/tr_tr/pdf/2020/07/ey-turkiye- parthenon--etid--covid-19-anketleri.pdf.
[14] L. Jean Harrison-Walker, “E-complaining: A content analysis of an Internet complaint forum,” 2001.
[15] D. Istanbulluoglu, S. Leek, and I. T. Szmigin, “Beyond exit and voice: developing an integrated taxonomy of consumer complaining behaviour,” Eur. J. Mark., vol. 51, no. 5–6, pp. 1109–1128, 2017, doi: 10.1108/EJM-04-2016-0204.
[16] L. Çallı and F. Çallı, “Understanding Airline Passengers during Covid-19 Outbreak to Improve Service Quality: Topic Modeling Approach to Complaints with Latent Dirichlet Allocation Algorithm,” Transp. Res. Rec. J. Transp. Res. Board, p. 036119812211120, 2022, doi: 10.1177/03611981221112096.
[17] sikayetvar.com, “About Us,” 2021. https://www.sikayetvar.com/hakkimizda.
[18] D. Gündüz Hoşgör and H. Hoşgör, “Sağlık Hizmeti Tüketicileri Perspektifinden Özel Hastane Şikâyetlerinin İncelenmesi (Sikayetvar.Com Örneği),” Hacettepe Sağlık İdaresi Derg., vol. 22, no. 4, pp. 823–842, 2019, [Online]. Available: https://orcid.org/0000-0002-1377-4617.
[19] H. N. Güler, “Koronavirüsü (COVID-19) Günlerinde Bankalara İletilen Müşteri İtiraz ve Şikayetlerinin İncelenmesi,” Avrasya Sos. ve Ekon. Araştırmaları Derg., vol. 7, no. 4, pp. 85– 99, 2020.
[20] M. Burucuoğlu and E. E. Yazar, “Üçüncü Parti Platformda Kargo Firmalarına Yapılan Müşteri Şikayetlerinin İçerik Analizi,” Ekon. ve Sos. Araştırmalar Derg., vol. 16, no. 1, pp. 99–114, 2020.
[21] M. Y. Gürce and P. Tosun, “Kargo Hizmetlerine İlişkin Müşteri Şikayetleri: Bir İçerik Analizi,” J. Bus. Res. - Turk, vol. 3, no. 9, pp. 177–196, 2017, doi: 10.20491/isarder.2017.294.
[22] İ. Kocabaş, “Covid- 19 Döneminde E - Şikâyet Yönetimi Perspektifinden Müşterilerin Çevrimiçi Alışverişte Karşılaştıkları Sorunlar,” Selçuk İletişim Derg., vol. 15, no. 1, pp. 323–359, 2022.
[23] A. Deniz and L. Gödekmerdan, “Müşterilerin Kargo Firmalarının Sunduğu Hizmetlere Yönelik Tutum ve Düşünceleri Üzerine Bir Araştırma,” Atatürk Üniversitesi Sos. Bilim. Enstitüsü Derg., vol. 15, no. 2, pp. 379–396, 2011.
[24] S. Kapıkıran, F. Öztürk, and E. Akkan, “Kargo Hizmetlerine Yönelik Hizmet Hatası Seviyesi , Hizmet Telafisi ve Tatminin Müşteri Sadakati Üzerindeki Etkisi Belirlemeye Yönelik Pilot,” pp. 0–2, 2021.
[25] A. H. Özaydın, S. Çelikkaya, and G. Duran, “Kargo Hizmetlerinin Tüketici Davranışlarına Etkisi Üzerine Bir Çalışma: Süleyman Demirel Üniversitesi Örneği,” Enderun Derg., vol. 3, no. 2, pp. 86–97, 2019.
[26] Y. Cho, I. IM, R. Hiltz, and J. Fjermestad, “An analysis of online customer complaints: Implications for Web complaint management,” Proc. Annu. Hawaii Int. Conf. Syst. Sci., vol. 2002-Janua, no. c, pp. 2308–2317, 2002, doi: 10.1109/HICSS.2002.994162.
[27] M. N. Alabay, “Müşteri Şikâyetleri Yönetimi,” Uluslararası Yönetim İktisat ve İşletme Derg., vol. 8, no. 16, 2012.
[28] S. Ray, “A Quick Review of Machine Learning Algorithms,” in Proceedings of the International Conference on Machine Learning, Big Data, Cloud and Parallel Computing: Trends, Prespectives and Prospects, COMITCon 2019, 2019, pp. 35–39, doi: 10.1109/COMITCon.2019.8862451.
[29] I. El Naqa, R. Li, and M. J. Murphy, Machine Learning in Radiation Oncology. Cham: Springer International Publishing, 2015. cuk et al. 384 [30] J. Castañón, “10 Machine Learning Methods that Every Data Scientist Should Know,” 2019. https://towardsdatascience.com/10-machine-learning-methods-that-every-data-scientist-should- know-3cc96e0eeee9.
[31] T. Kwartler, “What is Text Mining?,” in Text Mining in Practice with R, 2017, pp. 1–15.
[32] L. Çallı, F. Çallı, and B. Alma Çallı, “Yönetim Bilişim Sistemleri Disiplininde Hazırlanan Lisansüstü Tezlerin Gizli Dirichlet Ayrımı Algoritmasıyla Konu Modellemesi,” MANAS Sos. Araştırmalar Derg., pp. 2355–2372, 2021, doi: 10.33206/mjss.894809.
[33] M. Roukalova, “Text Mining vs. Natural Language Processing,” Scion Analytics, 2021. https://scionanalytics.com/text-mining-vs-natural-language-processing.
[34] A.-H. Tan, “Text Mining: The state of the art and the challenges,” Proc. PAKDD 1999 Work. Knowl. Disocovery from Adv. Databases, vol. 8, pp. 65–70, 1999, doi: 10.1.1.38.7672.
[35] S. Kazan and H. Karakoca, “Product Category Classification with Machine Learning,” Sak. Univ. J. Comput. Inf. Sci., vol. 2, no. 1, pp. 18–27, 2019, doi: 10.35377/saucis.02.01.523139.
[36] A. C. P. L. F. de Carvalho and A. A. Freitas, “A Tutorial on Multi-label Classification Techniques,” 2009, pp. 177–195.
[37] P. Szymanski and T. Kajdanowicz, “Scikit-multilearn: A python library for multi-label classification,” J. Mach. Learn. Res., vol. 20, no. 6, pp. 1–22, 2019.
[38] A. K. Singh and M. Shashi, “Vectorization of text documents for identifying unifiable news articles,” Int. J. Adv. Comput. Sci. Appl., vol. 10, no. 7, pp. 305–310, 2019, doi: 10.14569/ijacsa.2019.0100742.
[39] A. Aizawa, “An information-theoretic perspective of tf-idf measures,” Inf. Process. Manag., vol. 39, no. 1, pp. 45–65, Jan. 2003, doi: 10.1016/S0306-4573(02)00021-3.
[40] W. Zhang, T. Yoshida, and X. Tang, “A comparative study of TF*IDF, LSI and multi-words for text classification,” Expert Syst. Appl., vol. 38, no. 3, pp. 2758–2765, 2011, doi: 10.1016/j.eswa.2010.08.066.
[41] S. Kaur, P. Kumar, and P. Kumaraguru, “Automating fake news detection system using multi- level voting model,” Soft Comput., vol. 24, no. 12, pp. 9049–9069, 2020, doi: 10.1007/s00500- 019-04436-y.
[42] J. Deepakumara, H. M. Heys, and R. Venkatesan, “FPGA implementation of MD5 hash algorithm,” Can. Conf. Electr. Comput. Eng., vol. 2, pp. 919–924, 2001, doi: 10.1109/ccece.2001.933564.
[43] J. Brownlee, “One-vs-Rest and One-vs-One for Multi-Class Classification,” Machine Learning Mastery, 2020. https://machinelearningmastery.com/one-vs-rest-and-one-vs-one-for-multi- class-classification/.
[44] TurkishMinistryofHealth, “COVID-19 Bilgilendirme Platformu,” 2022. https://covid19.saglik.gov.tr/

APA	Kuyucuk T, ÇALLI L (2022). Using Multi-Label Classification Methods to Analyze Complaints Against Cargo Services During the COVID-19 Outbreak: Comparing Survey-Based and Word-Based Labeling. , 371 - 384. 10.35377/saucis.05.03.1121830
Chicago	Kuyucuk Tolga,ÇALLI Levent Using Multi-Label Classification Methods to Analyze Complaints Against Cargo Services During the COVID-19 Outbreak: Comparing Survey-Based and Word-Based Labeling. (2022): 371 - 384. 10.35377/saucis.05.03.1121830
MLA	Kuyucuk Tolga,ÇALLI Levent Using Multi-Label Classification Methods to Analyze Complaints Against Cargo Services During the COVID-19 Outbreak: Comparing Survey-Based and Word-Based Labeling. , 2022, ss.371 - 384. 10.35377/saucis.05.03.1121830
AMA	Kuyucuk T,ÇALLI L Using Multi-Label Classification Methods to Analyze Complaints Against Cargo Services During the COVID-19 Outbreak: Comparing Survey-Based and Word-Based Labeling. . 2022; 371 - 384. 10.35377/saucis.05.03.1121830
Vancouver	Kuyucuk T,ÇALLI L Using Multi-Label Classification Methods to Analyze Complaints Against Cargo Services During the COVID-19 Outbreak: Comparing Survey-Based and Word-Based Labeling. . 2022; 371 - 384. 10.35377/saucis.05.03.1121830
IEEE	Kuyucuk T,ÇALLI L "Using Multi-Label Classification Methods to Analyze Complaints Against Cargo Services During the COVID-19 Outbreak: Comparing Survey-Based and Word-Based Labeling." , ss.371 - 384, 2022. 10.35377/saucis.05.03.1121830
ISNAD	Kuyucuk, Tolga - ÇALLI, Levent. "Using Multi-Label Classification Methods to Analyze Complaints Against Cargo Services During the COVID-19 Outbreak: Comparing Survey-Based and Word-Based Labeling". (2022), 371-384. https://doi.org/10.35377/saucis.05.03.1121830

APA	Kuyucuk T, ÇALLI L (2022). Using Multi-Label Classification Methods to Analyze Complaints Against Cargo Services During the COVID-19 Outbreak: Comparing Survey-Based and Word-Based Labeling. Sakarya University Journal of Computer and Information Sciences (Online), 5(3), 371 - 384. 10.35377/saucis.05.03.1121830
Chicago	Kuyucuk Tolga,ÇALLI Levent Using Multi-Label Classification Methods to Analyze Complaints Against Cargo Services During the COVID-19 Outbreak: Comparing Survey-Based and Word-Based Labeling. Sakarya University Journal of Computer and Information Sciences (Online) 5, no.3 (2022): 371 - 384. 10.35377/saucis.05.03.1121830
MLA	Kuyucuk Tolga,ÇALLI Levent Using Multi-Label Classification Methods to Analyze Complaints Against Cargo Services During the COVID-19 Outbreak: Comparing Survey-Based and Word-Based Labeling. Sakarya University Journal of Computer and Information Sciences (Online), vol.5, no.3, 2022, ss.371 - 384. 10.35377/saucis.05.03.1121830
AMA	Kuyucuk T,ÇALLI L Using Multi-Label Classification Methods to Analyze Complaints Against Cargo Services During the COVID-19 Outbreak: Comparing Survey-Based and Word-Based Labeling. Sakarya University Journal of Computer and Information Sciences (Online). 2022; 5(3): 371 - 384. 10.35377/saucis.05.03.1121830
Vancouver	Kuyucuk T,ÇALLI L Using Multi-Label Classification Methods to Analyze Complaints Against Cargo Services During the COVID-19 Outbreak: Comparing Survey-Based and Word-Based Labeling. Sakarya University Journal of Computer and Information Sciences (Online). 2022; 5(3): 371 - 384. 10.35377/saucis.05.03.1121830
IEEE	Kuyucuk T,ÇALLI L "Using Multi-Label Classification Methods to Analyze Complaints Against Cargo Services During the COVID-19 Outbreak: Comparing Survey-Based and Word-Based Labeling." Sakarya University Journal of Computer and Information Sciences (Online), 5, ss.371 - 384, 2022. 10.35377/saucis.05.03.1121830
ISNAD	Kuyucuk, Tolga - ÇALLI, Levent. "Using Multi-Label Classification Methods to Analyze Complaints Against Cargo Services During the COVID-19 Outbreak: Comparing Survey-Based and Word-Based Labeling". Sakarya University Journal of Computer and Information Sciences (Online) 5/3 (2022), 371-384. https://doi.org/10.35377/saucis.05.03.1121830