Ranking product aspects through sentiment analysis of online reviews

The electronic word-of-mouth (e-WOM) is one of the most important among all the factors affecting consumers' behaviours. Opinions towards a product through online reviews will influence purchase decisions of other online consumers by changing their perceptions on the product quality. Furthermore, each product aspect may impact consumers' intentions differently. Thus, sentiment analysis and econometric models are incorporated to examine the relationship between purchase intentions and aspect-opinion pairs, which enable the weight estimation for each product aspect. We first identify product aspects and reduce dimensions to extract aspect-opinion pairs. Next the information gain is calculated for each aspect through entropy theory. Based on sentiment polarity and sentiment strength, we formulate an econometric model by integrating the information gain to measure the aspect's weight. In the experiment, we track 386 digital cameras on Amazon for 39 months, and results show that the aspect weight for digital cameras is detected more precisely than TF-ID and HAC algorithms. The results will bridge product aspects and consumption intention to facilitate e-WOM-based marketing.