System and method for actionizing comments
A system and method for processing and actionizing structured and unstructured experience data is disclosed herein. In some embodiments, a system may include a natural language processing (NLP) engine configured to transform a data set into a plurality of concepts within a plurality of distinct contexts, and a data mining engine configured to process the relationships of the concepts and to identify associations and correlations in the data set. In some embodiments, the method may include the steps of receiving a data set, scanning the data set with an NLP engine to identify a plurality of concepts within a plurality of distinct contexts, and identifying patterns in the relationships between the plurality of concepts.
1. A method for processing and actionizing experience data, the method comprising:
receiving, by a server, a plurality of communications, wherein each of the plurality of communications comprises comment data, wherein the comment data comprises structured or unstructured data;
parsing, by the server, the comment data from each of the plurality of communications for individual phrases to generate a plurality of phrases in response to receiving the plurality of communications;
predicting, by the server with a natural language processing (NLP) engine, one or more annotations for each of the plurality of phrases based upon a machine learning score in response to parsing the comment data, wherein each of the one or more annotations comprises a sentiment of the corresponding phrase and a primary tag indicative of a subject matter of the corresponding phrase, other than sentiment
determining, by the server, whether a certainty associated with the one or more annotations is less than a predetermined threshold based on the machine learning score; and
predicting, by the server, the one or more annotations for the plurality of phrases based upon a reference score in response to determining that the certainty is less than the predetermined threshold.
2. The method of claim 1 , wherein predicting the one or more annotations comprises classifying the plurality of phrases to identify the primary tag based on a predetermined ontology.
3. The method of claim 2 , wherein the predetermined ontology comprises a healthcare domain ontology.
4. The method of claim 1 , further comprising generating, by the server, a dashboard web page for a user that includes the one or more annotations in response to predicting the one or more annotations.
5. The method of claim 1 , further comprising:
determining, by the server, whether a certainty associated with the one or more annotations is less than a predetermined threshold based on the machine learning score; and
predicting, by the server, the one or more annotations for the plurality of phrases based upon a reference score in response to determining that the certainty is less than the predetermined threshold.
6. The method of claim 1 , further comprising receiving, by the server, the reference score from an individual review.
7. The method of claim 1 , further comprising:
storing, by the server, the comment data of each of the plurality of communications at a relational database; and
storing, by the server, the one or more annotations at the relational database, wherein each record corresponds to an annotation, and wherein each record includes the sentiment and the primary tag.
8. The method of claim 1 , wherein predicting the one or more annotations comprises identifying a named entity in the plurality of phrases.
9. The method of claim 1 , wherein predicting the one or more annotations comprises extracting a secondary tag indicative of a theme from the plurality of phrases.
10. A system for processing and actionizing experience data, the system comprising a server having a natural language processing (NLP) engine, wherein:
the server is to:
receive a plurality of communications, wherein each of the plurality of communications comprises comment data, wherein the comment data comprises structured or unstructured data; and
parse the comment data from each of the plurality of communications for individual phrases to generate a plurality of phrases in response to receiving the plurality of communications;
the NLP engine is to predict one or more annotations for each of the plurality of phrases based upon a machine learning score in response to parsing the comment data, wherein each of the one or more annotations comprises a sentiment of the corresponding phrase and a primary tag indicative of a subject matter of the corresponding phrase, other than sentiment
determine whether a certainty associated with the one or more annotations is less than a predetermined threshold based on the machine learning score; and
predict the one or more annotations for the plurality of phrases based upon a reference score in response to a determination that the certainty is less than the predetermined threshold.
11. The system of claim 10 , wherein to predict the one or more annotations comprises to classify the plurality of phrases to identify the primary tag based on a predetermined ontology.
12. The system of claim 11 , wherein the predetermined ontology comprises a healthcare domain ontology.
13. The system of claim 10 , wherein the server is further to generate a dashboard web page for a user that includes the one or more annotations in response to prediction of the one or more annotations.
14. The system of claim 10 , wherein the server is further to:
determine whether a certainty associated with the one or more annotations is less than a predetermined threshold based on the machine learning score; and
predict the one or more annotations for the plurality of phrases based upon a reference score in response to a determination that the certainty is less than the predetermined threshold.
15. The system of claim 10 , wherein the server is further to receive the reference score from an individual review.
16. The system of claim 10 , further comprising a relational database, wherein the server is further to:
store the comment data of each of the plurality of communications at the relational database; and
store the one or more annotations at the relational database, wherein each record corresponds to an annotation, and wherein each record includes the sentiment and the primary tag.
17. The system of claim 10 , wherein to predict the one or more annotations comprises to identify a named entity in the plurality of phrases.
18. The system of claim 10 , wherein to predict the one or more annotations comprises to extract a secondary tag indicative of a theme from the plurality of phrases.
19. One or more non-transitory computer-readable storage media comprising a plurality of instructions stored thereon that, in response to being executed, cause a server to:
receive a plurality of communications, wherein each of the plurality of communications comprises comment data, wherein the comment data comprises structured or unstructured data;
parse the comment data from each of the plurality of communications for individual phrases to generate a plurality of phrases in response to receiving the plurality of communications;
predict one or more annotations for each of the plurality of phrases based upon a machine learning score in response to parsing the comment data, wherein each of the one or more annotations comprises a sentiment of the corresponding phrase and a primary tag indicative of a subject matter of the corresponding phrase, other than sentiment;
determine whether a certainty associated with the one or more annotations is less than a predetermined threshold based on the machine learning score; and
predict the one or more annotations for the plurality of phrases based upon a reference score in response to determining that the certainty is less than the predetermined threshold.
20. The one or more non-transitory computer-readable storage media of claim 19 , further comprising a plurality of instructions stored thereon that, in response to being executed, cause the server to:
determine whether a certainty associated with the one or more annotations is less than a predetermined threshold based on the machine learning score; and
predict the one or more annotations for the plurality of phrases based upon a reference score in response to determining that the certainty is less than the predetermined threshold.