关键词: 评论排序, 消费者偏好, 优化问题, 贪婪算法, 近似求解

Abstract: Due to the information overload of online reviews and consumer demand for customized services, it is particularly necessary to achieve personalized review ranking. Based on consumers’ multidimensional preferences, that is, product feature preference, review sentiment preference and browse quantity preference, this paper proposes a method to calculate consumer preference satisfaction of a review ranking, so as to transform the ranking issue into an optimization problem with the goal of maximizing the satisfaction. Because the problem is too complex to be solved accurately, an approximate solution based on an improved greedy algorithm is proposed. Finally, intensive experiments are conducted on real data from meituan.com, and the optimal parameter of the algorithm is determined. The results reveal that the proposed approach has the best effectiveness compared with other relevant methods and high sensitivity. The research can provide important practical guidance for consumers to improve decision-making efficiency and e-commerce platforms to improve review systems.

Key words: review ranking, consumer preference, optimization problem, greedy algorithm, approximate solution