Bank of America Corporation
CUSTOMER SENTIMENT DRIVEN WORKFLOW TUNED USING TOPIC ANALYSIS TO IMPLEMENT HIERARCHICAL ROUTING

Abstract:

A system that leverages social media account history and/or third party data source information to improve the accuracy of a sentiment analysis performed on a customer support request ("CSR") is provided. A receiver receives logins. Each login initiates a customer support request that includes a date/time of the CSR, a location of computer that was used to generate the CSR, a username associated with the CSR and a message. The system retrieves the third party data associated with a user. The processor harvests artifacts including sentiment information relevant to the CSR. The processor calculates a sentiment value based on the artifacts, the message, and historical information. The processor routes the CSR based on at least two of the date, time, username, location, and the sentiment value. The routing destination is selected from levels defined in a vertical stratification of the entity and corresponds that level to information contained within the message.