System and method for sentiment analysis of chat ghost typing
The present invention allows for the capture and sentiment analysis of text the customer inputs into a chat, but never actually sends to the customer service representative (ghost text). The system captures this ghost text with a ghost capture system (GCS) software module. The GCS module analyzes the ghost text to generate metadata. The ghost text and metadata are used by a sentiment analysis engine to apply appropriate sentiment to the ghost text. The sentiment and ghost text are routed to a customer service representative (CSR). This provides the customer service agent with additional detail and information about a customer's emotions during a text chat conversation, allowing the CSR to determine a court of interaction not only based on the customer's response, but also based on the ghost text and the sentiment from the ghost text.
1. A method for capturing and analyzing ghost text, comprising:
capturing a ghost text, wherein the ghost text is text entered by a customer and not sent to a customer service representative (CSR);
generating ghost text metadata for the captured ghost text based on an analysis of the captured ghost text;
assigning at least one sentiment to the ghost text based on an analysis of the ghost text metadata and a set of sentiment criteria;
routing the at least one sentiment to a determined CSR based on a determination of the CSR by a routing engine; and
displaying the sentiment on a CEC desktop for the determined CSR.
2. The method of claim 1 , wherein the ghost text is captured by a customer engagement center (CEC) system and further wherein the ghost text entered is entered by the customer from outside of the CEC system.
3. The method of claim 1 , wherein the analysis to assign the at least one sentiment to the ghost text includes analysis of the captured ghost text.
4. The method of claim 1 , further comprising displaying the captured ghost text for the determined CSR.
5. The method of claim 1 , further comprising receiving an update to at least one sentiment criteria.
6. The method of claim 1 , further comprising displaying the ghost text metadata for the determined CSR.
7. The method of claim 1 , wherein the ghost text is captured at predetermined intervals.
8. A system for capturing and analyzing ghost text for sentiment, comprising:
a processor, and
a non-transitory computer readable medium programmed with computer readable code that upon execution by the processor causes the processor to:
capture a ghost text, wherein the ghost text is text entered by a customer and not sent to a customer service representative (CSR);
generate ghost text metadata for the captured ghost text based on an analysis of the captured ghost text;
assign at least one sentiment to the ghost text based on an analysis of the ghost text metadata and a set of sentiment criteria;
route the at least one sentiment to a determined CSR based on a determination of the CSR by a routing engine; and
display the sentiment on a CEC desktop for the determined CSR.
9. The system of claim 8 , wherein the ghost text is captured by a customer engagement center (CEC) system and further wherein the ghost text entered is entered by the customer from outside of the CEC system.
10. The system of claim 8 , wherein the analysis to assign the at least one sentiment to the ghost text includes analysis of the captured ghost text.
11. The system of claim 8 , wherein the ghost text metadata is at least one of a speed at which the customer typed the ghost text, a time the customer spent not actively typing the ghost text, a number of edits, deletes or mistakes made prior to capturing the ghost text, A tone of the ghost text, or an intent or meaning of the ghost text.
12. The system of claim 8 , wherein the processor is further caused to receive an update to at least one sentiment criteria.
13. The system of claim 8 , wherein the processor is further caused to display the ghost text metadata for the determined CSR.
14. The system of claim 8 , wherein the ghost text is captured at predetermined intervals.
15. A non-transitory computer readable medium programmed with computer readable code that upon execution by a processor causes the processor to:
capture a ghost text, wherein the ghost text is text entered by a customer and not sent to a customer service representative (CSR);
generate ghost text metadata for the captured ghost text based on an analysis of the captured ghost text;
assign at least one sentiment to the ghost text based on an analysis of the ghost text metadata and a set of sentiment criteria;
route the at least one sentiment to a determined CSR based on a determination of the CSR by a routing engine; and
display the sentiment on a CEC desktop for the determined CSR.
16. The non-transitory computer readable medium of claim 15 , wherein the ghost text is captured by a customer engagement center (CEC) system and further wherein the ghost text entered is entered by the customer from outside of the CEC system.
17. The non-transitory computer readable medium of claim 15 , wherein the analysis to assign the at least one sentiment to the ghost text includes analysis of the captured ghost text.
18. The non-transitory computer readable medium of claim 15 , wherein the ghost text metadata is at least one of a speed at which the customer typed the ghost text, a time the customer spent not actively typing the ghost text, a number of edits, deletes or mistakes made prior to capturing the ghost text, A tone of the ghost text, or an intent or meaning of the ghost text.
19. The non-transitory computer readable medium of claim 15 , wherein the processor is further caused to receive an update to at least one sentiment criteria.
20. The non-transitory computer readable medium of claim 15 , wherein the ghost text is captured at predetermined intervals.