Data-Driven Approach to Dual Service Failure Monitoring From Negative Online Reviews: Managerial Perspective

Abstract

Monitoring of dual service failures (e.g., trends in service failures and consecutive service failures) in business is emphasized for service quality management. Previous studies analyzing negative online reviews to conduct dual service failure monitoring from a managerial perspective are scarce. Numerous negative online reviews are useful sources for dual service failure monitoring because they can be easily collected at a low cost. This article proposes a data-driven approach to monitor service failure trends and consecutive service failures from negative online reviews. In the proposed approach, first a classifier is developed to categorize newly collected negative reviews into service failures by Latent Dirichlet allocation. Subsequently, a threshold value is provided to identify a new type of service failure, which was not achieved previously using a control chart. Finally, the probability of consecutive service failures is obtained by association rule mining. A case study of Uber is conducted to validate the proposed approach. The results exhibit that the proposed approach can perform dual service failure monitoring. This study can increase marketing intelligence for dynamic management of service failure and allow rapid responses to service failures.

Classifying Online Customer Complaints: A Multiagent Perspective

“…This study adopted a qualitative approach using content analysis. This is considered appropriate since collecting information about incidents as they happen would be expensive, time-consuming (Joung, et al, 2021), hard, and ethically controversial (Smith & Bolton, 1998).…”

“…Because consumers participate voluntarily and actively while giving reviews, they are more motivated to participate than with surveys (Belkahla & Triki, 2011). The consumers' active role in this website produces valuable and complete data (Joung, et al, 2021) based on real incidents, which allows observation of actual human behavior and thus, provides construct validity.…”

“…Using data from www.people.com.cn, Huang (2017, as cited in Fu, et al, 2021 found that the top six tourist complaints concerned travel agencies, scenic spots, fraud, hotels, Ctrip (top Chinese online travel agent), and tour guides. Considering dual service failures with Uber, Joung, et al (2021) identified five categories: unwanted cancellation of ride requests, long waits, poor customer service contact, unclear pricing policies, and unskilled drivers. While providing a valuable perspective, none of these studies shed light on multi-agent failures experienced in, for instance, TSC settings.…”

Determining the factors affecting customer satisfaction using an extraction-based feature selection approach

“…OCRs provide a rich source of data to extract the dimensions of customer satisfaction for tourism sectors ( Chen et al, 2019 ; Hlee et al, 2020 ; Joung, Kim & Kim, 2021 ; Lien, Wen & Wu, 2011 ; Zinko et al, 2021 ). The results of the studies using OCRs ought to be more dependable and exact than those statistical results acquired from conventional satisfaction surveys dependent on little data samples ( Sánchez-Franco, Navarro-García & Rondán-Cataluña, 2019 ).…”

Research on express service defect evaluation based on semantic network diagram and SERVQUAL model

“…However, at present, the relevant research on express service quality mostly focuses on the establishment of express service quality evaluation model and the main factors affecting express service quality (3)(4)(5), and there is little direct research on express service defects. Identifying and monitoring service defects is very important for enterprises to meet customer needs and improve service quality (6,7). User generated content (UGC) has good autonomy, universality and interactivity, and can truly reflect user evaluation (8).…”