What can direct marketing do for branding and bonding?

Abstract

Web opinion feeds have become one of the most popular informationsources users consult before buying products or contracting services.Negative opinions about a product can have a high impact in its salesfigures. As a consequence, companies are more and more concerned abouthow to integrate opinion data in their business intelligence models sothat they can predict sales figures or define new strategic goals. Afteranalysing the requirements of this new application, this paper proposesa multidimensional data model to integrate sentiment data extracted fromopinion posts in a traditional corporate data warehouse. Then, a newsentiment data extraction method that applies semantic annotation as ameans to facilitate the integration of both types of data is presented.In this method, Wikipedia is used as the main knowledge resource,together with some well-known lexicons of opinion words and othercorporate data and metadata stores describing the company products like,for example, technical specifications and user manuals. The resultinginformation system allows users to perform new analysis tasks by usingthe traditional OLAP-based data warehouse operators. We have developed acase study over a set of real opinions about digital devices which areoffered by a wholesale dealer. Over this case study, the quality of theextracted sentiment data is evaluated, and some query examples thatillustrate the potential uses of the integrated model are provided.