Multimodal Representation Learning from raw data to detect customers emotional state in the financial industry
Currently, call centres effort in this matter is largely reactive. Someone calls in, they are upset, and agents respond accordingly. However, this approach is not always most effective, especially with difficult customers. Therefore, knowing the customers current emotional state is very important for appropriate problem solving. Affective computing can be used to detect and evaluate the client emotion rapidly, for example if the customer is angry or frustrated the algorithm will find out that emotional state and alert the agent to be more patient, understandable, and most importantly know how to deal with the client.