Durable product review mining for customer segmentation

Abstract

Purpose -More and more e-commerce web sites are using online customer reviews (OCRs) for customer segmentation. However, for durable products, customer purchases, and reviews only once for a long time, as while the product review score may highly affected by service factors or be "gently" evaluated. Existing regression or machine learning-based methods suffer from low accuracy when applied to the OCRs of durable products on e-commerce web sites. The purpose of this paper is to propose a new approach for customer segment analysis base on OCRs of durable products. Design/methodology/approach -The research proposes a two-stage approach that employs latent class analysis (LCA): the feature-mention matrix construction stage and the LCA-based customer segmentation stage. The approach considers reviewers' mention on product features, and the probability-based LCA method is adopted upon the characteristics of online reviews, to effectively cluster reviewers into specified segmentations. Findings -The research finding is that, using feature-mention instead of feature-opinion records makes segment analysis more effective. The research also finds that, LCA method can better explain the characteristics of the OCR data of durable products for customer segmentation. Practical implications -The research proposes a new approach to durable product review mining for customer segmentation analysis. The segment analysis result can provide supports for new product design and development, repositioning of existing products, marketing strategy development and product differentiation. Originality/value -A new approach for customer segmentation analysis base on OCRs of durable products is proposed.

Sentiment annotations for reviews: an information quality perspective

“…Sentiment analysis, also called opinions mining, is used for analyzing people’s opinions towards products or services (Liu, 2010). There are many applications, for example, Jiang et al (2015) conducted customer segment analysis base on online customer reviews of durable products. Typical tasks of sentiment analysis are: finding suitable collection of reviews, pre-processing texts by using natural language processing techniques and identifying sentiment in texts (Schmunk et al , 2014).…”

A multi-dimensional analysis of CBEC English genre variation in South Asia: Based on Daraz

“…Sentiment analysis and bidirectional recurrent neural network (RNN) were applied in the analysis of customer reviews [5,9]. Latent class analysis can better explain the characteristics of the online customer reviews data of durable products for customer segmentation, which may provide support for new product design and development, repositioning of existing products, and product differentiation [10].…”

Supporting the purchase decisions of consumers

“…An investigation by Duan, et al found that 20 per cent of consumers ranked products based on online ratings alone when searching for product information on an e-commerce website (Duan et al , 2009). In addition, numerous existing studies have shown that online ratings or online reviews play an important role in the decision-making process of consumers, which are not only sources of information used by consumers to understand the function and quality of a product or service but also sources of information used to find desirable products (Fang et al , 2016; Jiang et al , 2015; Zhou et al , 2015; Sameti et al , 2016; Salehan and Kim, 2016). When a consumer is willing to buy an expensive product, such as mobile phone and automobile, he (she) usually considers several alternative products and their attributes according to his (her) expectations, as well as to the corresponding online ratings.…”