Human Dynamics In Repurchase Behavior Based On Comments Mining

With the iterative development of e-commerce,online consumption has become one of the main ways of people’s consumption.Online consumer environment provides consumers with convenience and diversity,but also increases the cost and difficulty of maintaining the long-term customer relationship.This paper studies the repurchase behavior according to the human dynamics theory and methods,and analyzes the internal characteristic of people’s repurchase behavior,which is beneficial to the enterprise managers.Hundreds of thousands of individual deals and comments are analyzed to ask:what kinds of patterns appear in their repurchase process?The results suggest that,in the empirical description,the intervals between two consecutive purchases obey a power-law distribution.Notwithstanding a wide range of individual preferences,shoppers’repurchase behaviors show some similar patterns,called long-scale quiet and short-scale emergence,and the alternating appearance of them form an endless chain in repurchase.Analyzing the burstness and memory of the users’ repurchase behaviors,and the paper found the repurchase behaviors show the a positive memory and burstness.Moreover,the higher users’ active degrees result in bigger power exponents.The power law characteristics of users’ repurchase behaviors are mainly due to the interest reduction mechanism.The users’ purchase interest will decay with time,but the interest will rise because of an occasional good consumption experience.In agreement with the empirical results,these short-scale and long-scale patterns suggest an adaptive model with alterable exponents complying with a power-law distribution.Compared with the results of empirical analysis,the model can reproduce the repurchase behavior more accurately.And it also implies that each user behaves his own intrinsic pattern such as unique repurchase intensity and silence-emergence cycle,which contributes to customer life-time value from the new view of dynamics and repurchase cycles.