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

Abstract

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.