Numerical recipes in C (2nd ed.): the art of scientific computing
Numerical recipes in C (2nd ed.): the art of scientific computing
Foundations of statistical natural language processing
Foundations of statistical natural language processing
Data mining (Invited talk. Abstract only): crossing the Chasm
KDD '99 Proceedings of the fifth ACM SIGKDD international conference on Knowledge discovery and data mining
Mining the most interesting rules
KDD '99 Proceedings of the fifth ACM SIGKDD international conference on Knowledge discovery and data mining
Data mining: concepts and techniques
Data mining: concepts and techniques
Information Retrieval: Algorithms and Heuristics
Information Retrieval: Algorithms and Heuristics
Modern Information Retrieval
Artificial Intelligence
Feature Weighting in k-Means Clustering
Machine Learning
Design and implementation of the UIMA common analysis system
IBM Systems Journal
Incremental personalized web page mining utilizing self-organizing HCMAC neural network
Web Intelligence and Agent Systems
Introduction to Data Mining, (First Edition)
Introduction to Data Mining, (First Edition)
Temporal multi-page summarization
Web Intelligence and Agent Systems
Proceedings of the 2007 ACM SIGMOD international conference on Management of data
Generating and Browsing Multiple Taxonomies Over a Document Collection
Journal of Management Information Systems
Consumer behavior analysis from buzz marketing sites over time series concept graphs
KES'11 Proceedings of the 15th international conference on Knowledge-based and intelligent information and engineering systems - Volume Part II
Detecting unexpected correlation between a current topic and products from buzz marketing sites
DNIS'11 Proceedings of the 7th international conference on Databases in Networked Information Systems
Hi-index | 0.00 |
Corporations are extremely sensitive to issues such as brand stewardship and product reputation. Traditional brand image and reputation tracking is limited to news wires and contact centre analysis. However, with the emergence of web, Consumer Generated Media (CGM), such as blogs, news forums, message boards, and web pages/sites, is rapidly becoming the “voice of the people”. Effectively leveraging such readily available and massive amount of CGM content for brand and reputation insights can be extremely valuable to corporations. Yet the existing solutions in this space are commonly limited to keyword search based technologies that often result in excessive amount of information for users to digest manually. Some text mining based technologies exist for mining the web. However, they often target very narrow problems such as web page classification instead of looking at the overall stack of technologies required for web mining. This paper describes a holistically integrated brand and reputation analysis solution that mines CGM contents for insights, called COBRA (COrporate Brand and Reputation Analysis). COBRA contains a flexible ETL (Extract, Transform, and Load) engine that processes diverse sets of structured and unstructured information, a suite of analytical capabilities that mines CGM content to extract semantic entities and insights out of the data, and an alerting mechanism that utilizes a technique called “orthogonal filtering” to accurately generate brand and reputation alerts by filtering through orthogonal dimensions of information. We use a set of real-world case studies to demonstrate the effectiveness of our overall approach. We show that by applying such analytics techniques, we significantly improved the accuracy of alert identification by 10-200 times when compared to the popular keyword-search based techniques in today's alerting systems.