Abstract
Customer requirements (CRs) have a significant impact on product design. The existing methods of defining CRs, such as customer surveys and expert evaluations, are time-consuming, inaccurate and subjective. This paper proposes an automatic CRs definition method based on online customer product reviews using the big data analysis. Word vectors are defined using a continuous bag of words (CBOW) model. Online customer reviews are searched by a crawling method and filtered by the parts of speech and frequency of words. Filtered words are then clustered into groups by an affinity propagation (AP) clustering method based on trained word vectors. Exemplars in each clustering group are finally used to define CRs. The proposed method is verified by case studies of defining CRs for product design. Results show that the proposed method has better performance to determine CRs compared to existing CRs definition methods.
Highlights
The quality of product design highly depends on effective collections of customer requirements (CRs) to decide function requirements (FRs).[1]
This research proposed a new CR definition method based on the data crawling and affinity propagation (AP) clustering method
After filtering online customer reviews using parts of speech and frequency of words, filtered words were clustered into groups by the AP clustering method
Summary
The quality of product design highly depends on effective collections of customer requirements (CRs) to decide function requirements (FRs).[1]. There is not an existing method to effectively collect online customer review data and transfer the data into specific CRs for a product. Crawling methods such as focused crawling and deep web crawling methods are widely used for collecting online data. Mining methods, online customer reviews and sales profit can be collected to find CRs for product improvement. A CRs definition method is proposed in this paper using web crawling and data mining methods based on online customer reviews. To improve the accuracy of CRs definitions in product design, the focused crawling method is used to collect related articles of products. Research conclusion and further work are described in the last section
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
