Reconciling detailed transaction feedback

• US 9,495,695 B2
• Filed: 03/31/2016
• Issued: 11/15/2016
• Est. Priority Date: 04/12/2013
• Status: Active Grant

• Current Assignee: eBay Inc.
• Original Assignee: eBay Inc.
• Inventors: Maddali, Lakshman Shyam Sundar, Sharma, Avani Goel
• Primary Examiner(s): YEN, ERIC L
• Application Number:
  US15/086,858
• Publication Number:
  US 20160210673A1
• Time in Patent Office: 229 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/2465 Query processing support for facilitating data mining operations in structured databases
• CPC Class Codes: G06F 40/279 Recognition of textual entities
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06Q 30/0282 Rating or review of business operators or products

Abstract

Reconciling detailed transaction feedback by detecting a rating of a transaction, where the rating indicates a negative experience, mining the sentiment of words in feedback text that is included with or as part of the rating to detect whether the words indicate positive sentiment or negative sentiment, responsive to determining that the words in the feedback text indicate that the feedback text connotes a positive sentiment, adjusting the rating of the transaction. The mining may include testing words in the feedback text to detect whether the words indicate positive sentiment or negative sentiment by calculating a sentiment score.

Claims

1. A method for reconciling detailed user transaction feedback with a numerical seller rating that rates a seller of a product, comprising:

detecting, by one or more computer processors, that the numerical seller rating indicates a negative experience;

mining a sentiment of words in the feedback and detecting that the words in the feedback indicate positive sentiment;

responsive to detecting that the words in the feedback indicate positive sentiment, mining the sentiment of words in the feedback and detecting that the words in the feedback do not indicate any negative sentiment; and

responsive to detecting that the words in the feedback do not indicate any negative sentiment, transforming a state of the numerical seller rating from a state that is inconsistent with the words in the feedback to a state that is reconciled with the words in the feedback.

2. The method of claim 1 wherein mining a sentiment of words in the feedback and detecting that the words in the feedback indicate a positive sentiment is done by using a positive sentiment mining tool.

3. The method of claim 1 wherein mining the sentiment of words in the feedback and detecting that the words in the feedback do not indicate any negative sentiment is done by using a negative sentiment mining tool.

4. The method of claim 1 wherein transforming a state of the numerical seller rating from a state that is inconsistent with the words in the feedback to a state that is reconciled with the words in the feedback is done by weighting the numerical seller rating.

5. The method of claim 4 wherein weighting the numerical seller rating is based on detecting previous numerical seller ratings given by the user by analyzing transaction logs.

6. The method of claim 4 wherein weighting the numerical seller rating is based on one of geography, product listing category or average selling price.

7. The method of claim 4 wherein weighting the seller rating comprises lowering the weight of the numerical seller rating.

8. One or more computer-readable hardware storage device having stored therein a set of instructions which;

when executed by one or more hardware computer processors cause the one or more hardware computer processors to perform operations comprising;

detecting, by one or more computer processors, that the numerical seller rating indicates a negative experience;

mining a sentiment of words in the feedback and detecting that the words in the feedback indicate positive sentiment;

responsive to detecting that the words in the feedback indicate positive sentiment, mining the sentiment of words in the feedback and detecting that the words in the feedback do not indicate any negative sentiment; and

responsive to detecting that the words in the feedback do not indicate any negative sentiment, transforming a state of the numerical seller rating from a state that is inconsistent with the words in the feedback to a state that is reconciled with the words in the feedback.

9. The one or more computer-readable hardware storage device of claim 8 wherein mining a sentiment of words in the feedback and detecting that the words in the feedback indicate a positive sentiment is done by using a positive sentiment mining tool.

10. The one or more computer-readable hardware storage device of claim 8 wherein mining the sentiment of words in the feedback and detecting that the words in the feedback do not indicate any negative sentiment is done by using a negative sentiment mining tool.

11. The one or more computer-readable hardware storage device of claim 8 wherein transforming a state of the numerical seller rating from a state that is inconsistent with the words in the feedback to a state that is reconciled with the words in the feedback is done by weighting the numerical seller rating.

12. The one or more computer-readable hardware storage device of claim 11 wherein weighting the numerical seller rating is based on detecting previous numerical seller ratings given by the user by analyzing transaction logs.

13. The one or more computer-readable hardware storage device of claim 11 wherein weighting the numerical seller rating is based on one of geography, product listing category or average selling price.

14. The one or more computer-readable hardware storage device of claim 11 wherein weighting the seller rating comprises lowering the weight of the numerical seller rating.

15. A system for reconciling detailed user transaction feedback with a numerical seller rating that rates a seller of a product, the system comprising one or more hardware processors configured to include:

comparison circuitry that compares the numerical seller rating to a predetermined number to detect that the numerical seller rating indicates a negative experience;

a positive sentiment mining tool to mine sentiment of words in the feedback and detect that the words in the feedback indicate positive sentiment;

a negative sentiment mining tool;

responsive to detection that the words in the feedback indicate positive sentiment, to mine the sentiment of words in the feedback and detect that the words in the feedback do not indicate any negative sentiment; and

a sentiment extraction and reconciliation application responsive to detection that the words in the feedback do not indicate any negative sentiment, to transform a state of the numerical seller rating from a state that is inconsistent with the words in the feedback to a state that is reconciled with the words in the feedback.

16. The system of claim 15 wherein the positive sentiment mining tool tests for words in the feedback that indicate positive sentiment.

17. The system of claim 15 wherein the negative sentiment mining tool tests for words in the feedback that indicate negative sentiment.

18. The system of claim 15 wherein transformation of a state of the numerical seller rating from a state that is inconsistent with the words in the feedback to a state that is reconciled with the words in the feedback is done by weighting the numerical seller rating.

19. The system of claim 18 wherein weighting the numerical seller rating is based on one of geography, product listing category or average selling price.

20. The system of claim 18 wherein weighting the seller rating comprises lowering the weight of the numerical seller rating.