Identifying targeted needs from online marketer- and user-generated data

Abstract

On e-retailing sites, marketer-generated content (MGC), user-generated content (UGC), and potential user-generated content (PUGC) are constantly conveying their needs. Identifying and clustering these needs, especially targeted needs, helps implement differentiated market strategies, improves the helpfulness of user's review content, and enhances potential user's purchase experiences. If so, then, how to identify diverse needs and find out where they are targeted (lower/higher). Based on Maslow's hierarchy of needs theory, the authors propose a need hierarchy framework to explore these questions. We utilize the datasets from two experiential products on Amazon.com and combine text mining methods with regression analyses to identify and cluster the targeted needs of online-generated content. The results show that the needs conveyed by MGC, UGC and PUGC are hierarchical and targeted, and the targeted needs are mapped to higher levels. Furthermore, we also find that the needs conveyed by PUGC are influenced by and aligned with needs of UGC. The findings reveal the deeper value of online-generated content for identifying needs, and provide a highlight for studying needs of Maslow's hierarchy of needs theory in the new field of e-commerce. Meanwhile, the results obtain the new ideas for enhancing the online interaction experiences of all the stakeholders.