It aims to develop the HoQ methodology by integrating Online Product Reviews (OPR) and expert evaluations and automatically determining normalized Customer Requirement (CR) weights to improve the product development process.
The research uses NLP and text mining to analyze OPRs and expert reports. CRs, CR importance, and local/competitor CR scores are extracted by Latent Dirichlet Allocation, and point-of-sale importance values are determined from Product Evaluation Platforms (PEP).
The study shows that automating the HoQ process using OPRs and expert assessments is effective. Fourteen CRs are identified, and a data-driven comparative analysis of brands is conducted. Integrating PEP sources yields more accurate PSI values, thereby enhancing product development based on CRs.
The reliability of OPRs and expert assessments may affect the results. The methodology requires computational resources and expertise. Its applicability across different industries and its cross-checking with conventional HoQ remain to be tested.
This method offers businesses, especially SMEs, a cost-effective and efficient approach to aligning product features with CRs. It reduces reliance on traditional surveys and provides rapid, real-time insights.
This study promotes transparency by incorporating OPRs and PEPs, allowing companies to meet CRs better and leading to higher satisfaction.
For the first time, it offers an automated approach to HoQ that integrates layered OPRs to determine normalized CR weights and uses PEPs for PSI determination. This innovation improves product development efficiency by saving time and cost while minimizing dependency on experts.
