Automated updating of on-line product and service reviews

• US 10,235,699 B2
• Filed: 11/23/2015
• Issued: 03/19/2019
• Est. Priority Date: 11/23/2015
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Bostick, James E., Ganci, Jr., John M., Rakshit, Sarbajit K., Trim, Craig M.
• Primary Examiner(s): Hayles, Ashford S
• Application Number:
  US14/948,853
• Publication Number:
  US 20170148071A1
• Time in Patent Office: 1,212 Days
• Field of Search: 705 28
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 16/35 Clustering; Classification
• CPC Class Codes: G06Q 10/087 Inventory or stock management, e.g. order filling, procurement or balancing against orders
• CPC Class Codes: G06Q 30/0282 Rating or review of business operators or products

Abstract

The present invention provides a computerized system that analyzes the text of on-line product and service reviews, compares the textual components of the review with a database of manufacturer/service producer updates to the product or service to which the review pertains, provides corrective commentary to the review based upon post-review action taken by the manufacture/service provider, and adjusts the weighting of the review on the basis of the outdated information.

Claims

1. A system for updating on-line product/service reviews for a given product/service, comprising:

i. a server computer;

ii. a web server on which the on-line product/service reviews and corresponding dates on which the on-line product/service reviews were entered are stored in non-transitory memory;

iii. a database on which is stored data representative of;

1. products/services subject to on-line review, and

2. updated and fixed features of said products/services subject to review and corresponding dates from which said updated and fixed features are effective, wherein said data representative of updated and fixed features is automatically updated within said database on a predetermined periodic basis;

iv. software stored in non-transitory memory on said server computer, said software comprising program executable code for performing;

1. natural language processing, including classification, lemmatization and sentiment break-down for each of the on-line product/service reviews to generate analyzed on-line product/service reviews;

2. comparison of said data representative of said updated and fixed features with said analyzed on-line product/service reviews;

3. comparison of said data representative of the effective date from which said updated and fixed features are effective with said dates on which the on-line product/service reviews were entered;

4. generating, automatically, text representative of the updated and fixed feature and a date from which said updated and fixed feature is effective if said data representative of said updated and fixed features matches said analyzed on-line product/service reviews; and

5. inserting the text in said on-line product/service review to automatically generate an altered on-line product/service review.

2. The system according to claim 1, wherein said software further comprises program code for generating a visually observable timeline for each product/service that has been subject to review that contains data representative of the product/service features reviewed and any associated updates or fixes associated with said reviewed product/service features.

3. The system according to claim 2, wherein said software contains program code for aggregating the data associated with at least a portion of the on-line reviews of a product/service for purposes of generating said visually observable timeline.

4. The system according to claim 1, wherein said software further comprises code for adjusting rankings of the products/services subject to review based upon said updated and fixed features of said products/services that occurred after a review that commented negatively about said updated and fixed features of said products/services.

5. The system according to claim 4, wherein said database further stores data representative of individual reviewers'"'"' biases.

6. The system according to claim 5, wherein said software communicates with said database and further comprises program code for determining reviewer bias.

7. The system according to claim 6, wherein said software further comprises program code for adjusting rankings of the products/services subject to review based upon said reviewer bias.

8. The system according to claim 1, wherein said database further stores data representative of individual reviewer'"'"'s product/service preferences.

9. The system according to claim 8, wherein said software communicates with said database and further comprises program code for customizing said product/service review based on said individual reviewer'"'"'s products/services preferences.

10. A method for updating on-line product/service reviews for a given product/service, comprising the steps of:

a) analyzing the on-line product/service reviews by;

i. performing natural language processing techniques to classify the on-line product/service reviews;

ii. performing natural language processing techniques to lemmatize the on-line product/service reviews; and

iii. separating sentiment from the on-line product/service reviews;

b) comparing the analyzed product/service reviews to data stored on a database representative of updated and fixed features of said products/services subject to review and the dates from which said updated and fixed features are effective;

c) generating, automatically, text regarding a product/service feature that was subsequently updated or fixed that indicates the product/service feature has been updated or fixed; and

d) inserting, automatically, the text into any product/service review which contained negative sentiment.

11. The method according to claim 10, further comprising the step of generating a visually observable timeline for each product/service that has been subject to review that contains data representative of the product/service features reviewed and any associated updates or fixes associated with said reviewed product/service features.

12. The method according to claim 11, further comprising the step of aggregating the data associated with at least a portion of the on-line reviews of a product/service for purposes of generating said visually observable timeline.

13. The method according to claim 10, comprising the further step of for adjusting rankings of the products/services subject to review based upon said updated and fixed features of said products/services that occurred after a review that commented negatively about said updated and fixed features of said products/services.

14. The method according to claim 13, comprising the further step of storing in a database data representative of individual reviewers'"'"' biases.

15. The method according to claim 14, comprising the further step of communicating with the database, determining reviewer bias, and adjusting rankings of the products/services subject to review based upon said reviewer bias.

16. A software product stored in non-transitory memory of a computer for updating on-line product/service reviews for a given product/service and that communicates with a database on which is stored data representative of products/services subject to on-line review, and updated and fixed features of the products/services subject to review and the dates from which the updated and fixed features are effective, wherein the data representative of updated and fixed features is automatically updated within the database on a predetermined periodic basis, the software product comprising executable program code for performing:

a) natural language processing, including classification, lemmatization and sentiment break-down for each of the on-line product/service reviews to generate analyzed on-line product/service reviews;

b) comparison of said data representative of said updated and fixed features with said analyzed on-line product/service reviews;

c) comparison of said data representative of the effective date from which said updated and fixed features are effective with said dates on which the on-line product/service reviews were entered;

d) generating, automatically, text representative of the updated and fixed feature and the date from which said updated and fixed feature is effective if said data representative of said updated and fixed features matches said analyzed on-line product/service reviews; and

e) inserting, automatically, the text in said on-line product/service review to generate an altered on-line product/service review.

17. The system according to claim 16, further comprising program code for generating a visually observable timeline for each product/service that has been subject to review that contains data representative of the product/service features reviewed and any associated updates or fixes associated with said reviewed product/service features.

18. The system according claim 17, further comprising program code for aggregating the data associated with at least a portion of the on-line reviews of a product/service for purposes of generating said visually observable timeline.

19. The system according to claim 16, further comprising program code for adjusting rankings of the products/services subject to review based upon said updated and fixed features of said products/services that occurred after a review that commented negatively about said updated and fixed features of said products/services.

20. The system according to claim 19, wherein said database further stores data representative of individual reviewers'"'"' biases, said software communicates with said database and further comprises program code for determining reviewer bias, wherein said software communicates with said database and further comprises program code for determining reviewer bias, and said software further comprises program code for adjusting rankings of the products/services subject to review based upon said reviewer bias.