Mining Customer Requirement from Online Reviews Based on Multi-aspected Sentiment Analysis and KANO Model

Customer requirement plays a more and more important role in the enterprise innovation. With the development of the internet, online reviews have become an important information source of mining customer requirement. In this paper, a novel method is proposed to mine customer requirement form online reviews based on multi-aspected sentiment analysis and KANO model. In the method, product features are first extracted and clustered in the form of feature-sentiment word pairs from online reviews. Then, a special domain sentiment lexicon is constructed by modified SO-PMI method to quantify the customer satisfaction. The KANO model is innovatively applied to identify the category of customer requirement from online reviews. Finally, an experiment is given to illustrate the accuracy of the sentiment analysis and the effectiveness of the proposed method.