ScholarWorks@경상국립대학교

초록

In the age of digital economy, customers actively share their experiences and issues about products via online product reviews. Mining potential product improvement ideas from customer needs could provide valuable insights into new functionality expected by the markets. Numerous studies have attempted to identify customer needs using these reviews, but they paid less attention to the customer’s specific context in which the product was used. This study provides a novel approach for identifying customer needs based on both context information and product functions of target products. The context information and product functions are derived from online product reviews through linguistic pattern mining, whereby the customer needs are determined by the combination of extracted context information and product functions using a semantic embedding method and a clustering approach. A case study on the Amazon-Echo series was conducted to verify the applicability of the proposed approach. Consequently, we identified 1430 different customer needs, which could be used as an input for improving product design. This study is one of the first attempts to integrate context information for identifying customer needs. The proposed approach can be useful in the idea creation process for future product planning and is expected to add new empirical perspective for the e-commerce industry. Author

키워드