Lifestyles in Amazon: Evidence from online reviews enhanced recommender system

Abstract

Online lifestyles have been shown to reflect and affect consumers’ preferences across a wide range of online scenarios. In the context of e-commerce, it still remains unclear whether online lifestyles are practically influential in predicting consumers’ purchasing preferences across different product categories, especially considering its potential influence over the widely used personality traits. In this study, we provide the first, to the best of our knowledge, quantitative demonstration of online lifestyles in predicting consumers’ online purchasing preferences in e-commerce by using a data-driven approach. We first construct an online lifestyles lexicon including seven distinct dimensions using text mining approaches based on consumers’ language use behaviors. We then incorporate the lexicon in a typical e-commerce recommender system to predict consumers’ purchasing preferences. Experimental results on Amazon Review Dataset show that online lifestyles and all its subdimensions significantly improve preference predicting performance and outperform the widely used Big Five personality traits as a whole. In addition, product types significantly moderate the influence of online lifestyle on consumer preference. The strong empirical evidence indicates that the big e-commerce consumer data facilitates more specialized market psychographic segmentation, which advances data-driven marketing decision-making.