Extract attribute types and values based on sentiment analysis and preference disaggregation

By harnessing evaluation information like attribute types and attribute values hidden in online reviews, managers can acquire consumer preference and satisfaction over products. Most existing studies only considered how to extract attribute types or attribute values of products from textual reviews, but ignored the role of attribute-level ratings in reflecting consumer preference and satisfaction. Based on the techniques of sentiment analysis and preference disaggregation, this paper unifies the quantitative and qualitative information extracted from textual reviews and attribute-level ratings to obtain attribute types and values of products. A real case on TripAdvisor.com is given to verify the proposed method.