Research On Influence Of Consumer Reviews On Product Word-of-Mouth And Sales

In the era of E-commerce and Web2.0, more and more consumers prefer to share their experience on purchasing by consumer reviews. Some valuable knowledge contained in consumer reviews not only could help consumers to know the products, but also could help businessmen to manage their products. By reading consumer reviews, Consumers could compare word of mouth (WOM) of some candidate products and do reasonable purchasing decision. Businessmen also could analyze influence of consumer reviews on product sales, meanwhile understand favor of consumers, and then make market strategy. However, the number of consumer reviews is very considerable and the style of consumer reviews is various, consumer reviews could not read all reviews before decision. So it is very necessary to mine and analyze influence of consumer reviews on product WOM and sales.At first, the paper proposes an effective WOM ranking method by means of ratings and comparative votes on products. It firstly computes relative WOM based on comparative votes, and then modifies the original ratings. Afterwards it combines relative WOM ratings and modified ratings to form the summarized WOM ratings for all products. Evaluation on the proposed WOM ranking method is conducted by using the real world datasets coming from a famous third party review website in China. Empirical results show that the WOM ranking list obtained by our approach has a higher support than other methods and also has a highest correlation with products sales ranking.Besides, we propose a method to quantify consumer text reviews, and then introduce quantified text reviews, numerical ratings, number of reviews, products price and products search volume into a regression estimation model to analyze influence of all factors on product sales. We estimate our model based on the real world datasets coming from a famous website in China. By contrast experiments, we can find that when taking consumer text reviews into account, the fixed effect model with the individual product diffusion fits better with the data. Meanwhile, both numerical ratings and opinions can affect product sales, but numerical ratings contribute more to the sales of product. Besides, based on analysis of opinions of product features in consumer reviews, we can identify positive features or negative features of products that have the effect on product sales. Empirical findings of the paper not only could help consumers to select product based on word of mouth, but also could help business increase the product sales.