Method for identifying emerging issues from textual customer feedback
View Patent ↗Systems, methods and software products identify emerging issues from textual customer feedback. A message stream of customer feedback is received. The message stream includes a plurality of unstructured text messages from at least one homogeneous source. A time interval is established. The volume of text messages for the time interval is determined to establish a reference volume. The volume of text messages in subsequent time intervals is measured to establish a trend volume. The trend volume is compared to the reference volume to determine a volumetric change. At least one action is initiated in response to a volumetric change above a pre-determined threshold. At least one action is initiated in response to a volumetric change below a pre-determined threshold.
1. A method for identifying emerging issues from textual customer feedback, comprising:
receiving a message stream of customer feedback, the message stream including a plurality of unstructured text messages from at least one homogeneous source;
establishing a time interval;
determining the volume of text messages for the time interval to establish a reference volume;
measuring the volume of text messages in subsequent time intervals to establish a trend volume;
comparing the trend volume to the reference volume to determine a volumetric change;
initiating in response to a volumetric change above a pre-determined threshold at least one action; and
initiating in response to a volumetric change below a pre-determined threshold at least one action.
2. The method of claim 1 , wherein the method is stored on a computer-readable medium as a computer program which, when executed by a computer will perform the steps of identifying emerging issues from textual customer feedback.
3. The method of claim 1 , wherein the textual customer feedback is selected from the group consisting of email, web feedback form entries, internet messaging, web log posts, and combinations thereof.
4. The method of claim 1 , wherein the method further includes:
capturing within the time interval a subset of the text messages as a reference set;
identifying at least one text category common in the reference set to establish a key term set;
identifying emerging issues from the stream of text messages, the identification including;
capturing within subsequent a time interval a subset of the text messages as a sample set;
evaluating the text messages of the sample set to determine a change in the frequency of occurrences of members of the key term set;
initiating in response to a frequency change above a pre-determined threshold at least one action; and
initiating in response to a frequency change below a pre-determined threshold at least one action.
5. The method of claim 4 , wherein the method is repeated, the key term set augmented with terms from at least one sample set.
6. A method for identifying emerging issues from textual customer feedback, comprising:
receiving a message stream of customer feedback, the message stream including a plurality of unstructured text messages from at least one homogeneous source;
evaluating the volume of customer feedback to establish a time interval;
capturing within a first time interval a subset of the text messages as a reference set;
establishing from the reference set a key term set including the frequency of occurrence for each key term;
capturing within a second time interval a subset of the text messages as a sample set;
evaluating the text messages of the sample set to determine a change in the frequency of occurrences of members of the key term set;
initiating in response to a frequency change above a pre-determined threshold at least one action; and
initiating in response to a frequency change below a pre-determined threshold at least one action.
7. The method of claim 6 , wherein the method is repeated, the key term set augmented with terms from at least one sample set.
8. The method of claim 6 , wherein the method is stored on a computer-readable medium as a computer program which, when executed by a computer will perform the steps of identifying emerging issues from textual customer feedback.
9. The method of claim 6 , wherein the textual customer feedback is selected from the group consisting of email, web feedback form entries, internet messaging, web log posts, and combinations thereof.
10. A computer implemented method for identifying emerging issues from textual customer feedback, comprising:
receiving a message stream of customer feedback, the message stream including a plurality of unstructured text messages from at least one homogeneous source;
evaluating the volume of customer feedback to establish a time interval;
capturing within a first time interval a subset of the text messages as a reference set;
establishing from the reference set a key term set, the key term set including the frequency of occurrence for each key term;
identifying emerging issues from the stream of text messages, the identification including;
capturing within a second time interval a subset of the text messages as a sample set;
evaluating the text messages of the sample set to determine a change in the frequency of occurrences of members of the key term set;
initiating in response to a frequency change above a pre-determined threshold at least one action; and
initiating in response to a frequency change below a pre-determined threshold at least one action.
11. The computer implemented method of claim 10 , wherein the identifying of emerging is repeated until the message stream terminates or the method is halted by a system user, the key term set augmented with terms from at least one sample set.
12. The computer implemented method of claim 10 , wherein the method is stored on a computer-readable medium as a computer program which, when executed by a computer will perform the steps of identifying emerging issues from textual customer feedback.
13. The computer implemented method of claim 10 , wherein the textual customer feedback is selected from the group consisting of email, web feedback form entries, internet messaging, web log posts, and combinations thereof.
14. A computer-readable medium on which is stored a computer program for identifying emerging issues from textual customer feedback, the computer program comprising instructions which, when executed by a computer, perform the steps of:
receiving a message stream of customer feedback, the message stream including a plurality of unstructured text messages from at least one homogeneous source;
evaluating the volume of customer feedback to establish a time interval;
capturing within a first time interval a subset of the text messages as a reference set;
establishing from the reference set a key term set including the frequency of occurrence for each key term;
identifying emerging issues from the stream of text messages, the identifying including;
capturing within a second time interval a subset of the text messages as a sample set;
evaluating the text messages of the sample set to determine a change in the frequency of occurrences of members of the key term set;
initiating in response to a frequency change above a pre-determined threshold at least one action;
initiating in response to a frequency change below a predetermined threshold at least one action;
repeating the identifying of emerging issues until the message stream terminates or halted by a system user.
15. A method for identifying emerging issues from textual customer feedback, comprising:
receiving a message stream, the message stream including a plurality of unstructured text messages originating from at least one homogeneous source;
establishing a time interval by evaluating the volume of customer feedback;
establishing from the message stream a distinct training set during a first time interval having at least one text message as a training message;
establishing from the message stream a distinct audit set during a second time interval having at least one text message as an audit message;
receiving from an analyst at least one text category, the text category common in the training set, and at least one target category;
concurrently displaying to the analyst a training message and an audit message;
requesting the analyst to indicate the presence or absence of at least one target category in each displayed text message;
in response to an indicated presence, recording a positive association of the text message and the pseudo target category;
repeating the concurrent display of a training message and an audit message until all members of both sets have been displayed;
reviewing the recorded positive association text messages and associated pseudo target categories to establish a text classifier;
identifying emerging issues from the stream of text messages utilizing the text classifier in an automated process, the identifying including;
capturing within a third time interval a subset of the text messages as a sample set;
evaluating the text messages of the sample set to determine a change in the frequency of occurrences of members of the key term set;
initiating in response to a frequency change above a pre-determined threshold at least one action;
initiating in response to a frequency change below a pre-determined threshold at least one action;
repeating the identifying of emerging issues until the message stream terminates or is halted by a system user.
16. The method of claim 15 , wherein the method is stored on a computer-readable medium as a computer program which, when executed by a computer will perform the steps of identifying emerging issues from textual customer feedback.