Processing transactional feedback
Disclosed are systems and methods for receiving a plurality of comments at a particular phase of a transaction with a member of a networked system, classifying one or more of the plurality of comments into one of a set of predetermined sentiment classifications, applying a trained machine learning system to select a category from a set of predefined categories for each of the one or more comments, applying a natural language processing module to generate a sub-category for each of the one or more comments, associating the generated sub-categories with their respective categories for the one or more comments, and generating a display of the determined categories for the particular transaction with the generated sub-categories, each generated sub-category being graphically connected to their respective categories.
1. A system comprising:
a machine-readable memory having instructions stored thereon, which, when executed by a processor, cause the system to perform operations comprising:
receiving a plurality of comments at a particular phase of a transaction with a member of a networked system;
classifying one or more of the plurality of comments into one of a set of predetermined sentiment classifications according to terms included in the respective comments matching terms associated with the sentiment classifications;
applying a trained machine learning system to select a category from a set of predefined categories for each of the one or more comments in the plurality of comments, the trained machine learning system accepting the terms in the respective comments and outputting the selected category;
applying a natural language processing module to each of the one or more comments to generate a sub-category for each of the one or more comments;
associating the generated sub-categories with their respective categories for the one or more comments; and
generating a display of the determined categories for the transaction with the generated sub-categories, each generated sub-category being graphically connected to their respective categories.
2. The system of claim 1 , wherein the operations further comprise receiving a selection of a category from the member and displaying a filtered set of comments associated with the selected category.
3. The system of claim 1 , wherein the operations further comprise receiving a selection of a sub-category from the member and displaying a filtered set of comments associated with the selected sub-category.
4. The system of claim 1 , wherein classifying the one or more comments comprises applying a trained machine learning system to output a sentiment classification using text from a comment of the one or more comments.
5. The system of claim 1 , wherein the operations further comprise alerting the member in response to a change in a trend in comments for one of the categories.
6. The system of claim 1 , wherein the operations further comprise applying a weight for each comment according to a user feedback score for a user providing a corresponding comment.
7. The system of claim 1 , wherein the operations further comprise selecting the natural language processing module according to the determined category.
8. A computer-implemented method comprising:
receiving a plurality of comments at a particular phase of a transaction with a member of a networked system;
classifying one or more of the plurality of comments into one of a set of predetermined sentiment classifications according to terms included in the respective comments matching terms associated with the sentiment classifications;
applying a trained machine learning system to select a category from a set of predefined categories for each of the one or more comments in the plurality of comments, the trained machine learning system accepting the terms in the respective comments and outputting the selected category;
applying a natural language processing module to each of the one or more comments to generate a sub-category for each of the one or more comments;
associating the generated sub-categories with their respective categories for the one or more comments; and
generating a display of the determined categories for the transaction with the generated sub-categories, each generated sub-category being graphically connected to their respective categories.
9. The method of claim 8 , further comprising receiving a selection of the category from the member and displaying a filtered set of comments associated with the selected category.
10. The method of claim 8 , further comprising receiving a selection of a sub-category from the member and displaying a filtered set of comments associated with the selected sub-category.
11. The method of claim 8 , wherein classifying the one or more comments comprises applying a trained machine learning system to output a sentiment classification using text from a comment of the one or more comments.
12. The method of claim 8 , further comprising alerting the member in response to a change in a trend in one of the categories.
13. The method of claim 8 , further comprising applying a weight for each comment according to a user feedback score for a user providing a corresponding comment.
14. The method of claim 8 , further comprising selecting the natural language processing module according to the determined category.
15. A machine-readable hardware memory having instructions stored thereon, which, when executed by one or more processors of a machine, cause the machine to perform operations comprising:
receiving a plurality of comments at a particular phase of a transaction with a member of a networked system;
classifying one or more of the plurality of comments into one of a set of predetermined sentiment classifications according to terms included in the respective comments matching terms associated with the sentiment classifications;
applying a trained machine learning system to select a category from a set of predefined categories for each of the one or more comments in the plurality of comments, the trained machine learning system accepting the terms in the respective comments and outputting the selected category;
applying a natural language processing module to each of the one or more comments to generate a sub-category for each of the one or more comments;
associating the generated sub-categories with their respective categories for the one or more comments; and
generating a display of the determined categories for the transaction with the generated sub-categories, each generated sub-category being graphically connected to their respective categories.
16. The machine-readable hardware memory of claim 15 , wherein the operations further comprise receiving a selection of a category from the member and displaying a filtered set of comments associated with the selected category.
17. The machine-readable hardware memory of claim 15 , wherein the operations further comprise further comprising receiving a selection of a sub-category from the member and displaying a filtered set of comments associated with the selected sub-category.
18. The machine-readable hardware memory of claim 15 , wherein classifying the one or more comments comprises applying a trained machine learning system to output a sentiment classification using text from a comment of the one or more comments.
19. The machine-readable hardware memory of claim 15 , wherein the operations further comprise alerting the member in response to a change in a trend in one of the categories.
20. The machine-readable hardware memory of claim 15 , wherein the operations further comprise applying a weight for each comment according to a user feedback score for a user providing a corresponding comment.