TY - JOUR
T1 - Supporting collaborative service improvement
T2 - A novel approach for customer requirement classification on digital industrial service platforms
AU - You, Jiapeng
AU - Gou, Huaxing
AU - Jiang, Hongwei
AU - Wang, Chengjun
AU - Sha, Weinan
AU - Xu, Jiahao
AU - Ming, Xinguo
AU - Sun, Poly Z.H.
N1 - Publisher Copyright:
© 2026 Elsevier Ltd
PY - 2026/4
Y1 - 2026/4
N2 - Digital industrial service platforms integrate multiple service providers to deliver one-stop solutions for demand-side customers. However, the dynamic nature of customer requirements (CRs) and fluctuations in service quality pose significant challenges in maintaining a competitive advantage in rapidly evolving markets. Existing research, often limited to single-service analysis, fails to address the need for coordinated improvements from a platform-wide perspective. To bridge this gap, this study proposes an online review-driven approach to support collaborative service improvement. We first introduce a methodology to model CRs across three key dimensions: sentiment strength, sentiment dynamics, and global influence. Building on the multi-dimensional representation, we then develop two new classification models, a generalized multi-dimensional benefit classification (GMBC) and an influence-attention Kano (IA-Kano), to strategically prioritize improvement actions under platform-level resource constraints. The feasibility and effectiveness of the proposed method are validated through a case study on a digital service platform in the automotive industry. Our method provides platform operators with a systematic approach to monitor CRs dynamically and a periodic decision-support tool for effective resource allocation, thereby converting fragmented customer feedback into actionable strategies for coordinated service enhancement.
AB - Digital industrial service platforms integrate multiple service providers to deliver one-stop solutions for demand-side customers. However, the dynamic nature of customer requirements (CRs) and fluctuations in service quality pose significant challenges in maintaining a competitive advantage in rapidly evolving markets. Existing research, often limited to single-service analysis, fails to address the need for coordinated improvements from a platform-wide perspective. To bridge this gap, this study proposes an online review-driven approach to support collaborative service improvement. We first introduce a methodology to model CRs across three key dimensions: sentiment strength, sentiment dynamics, and global influence. Building on the multi-dimensional representation, we then develop two new classification models, a generalized multi-dimensional benefit classification (GMBC) and an influence-attention Kano (IA-Kano), to strategically prioritize improvement actions under platform-level resource constraints. The feasibility and effectiveness of the proposed method are validated through a case study on a digital service platform in the automotive industry. Our method provides platform operators with a systematic approach to monitor CRs dynamically and a periodic decision-support tool for effective resource allocation, thereby converting fragmented customer feedback into actionable strategies for coordinated service enhancement.
KW - Collaborative service improvement
KW - Customer requirement classification
KW - Digital industrial service platforms
KW - Platform operation
UR - https://www.scopus.com/pages/publications/105030128365
U2 - 10.1016/j.cie.2026.111892
DO - 10.1016/j.cie.2026.111892
M3 - 文章
AN - SCOPUS:105030128365
SN - 0360-8352
VL - 214
JO - Computers and Industrial Engineering
JF - Computers and Industrial Engineering
M1 - 111892
ER -