SYSTEM FOR EXTRACTING CUSTOMER FEEDBACK FROM A MICROBLOG SITE

• US 20130290333A1
• Filed: 04/27/2012
• Published: 10/31/2013
• Est. Priority Date: 04/27/2012
• Status: Active Grant

• Current Assignee: Benbria Corporation
• Original Assignee: Benbria Corporation
• Inventors: Du, Ying, Fraczak, Wojciech
• Granted Patent: US 8,943,061 B2
• Time in Patent Office: Days
• US Class Current: 707/737
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 16/335 Filtering based on additional data, e.g. user or group profiles filtering in web context G06F16/9535, G06F16/9536
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06Q 10/063 Operations research, analysis or management
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: H04L 43/04 Processing captured monitoring data, e.g. for logfile generation

Abstract

A system for extracting customer feedback from a microblog site includes a retrieval unit coupled to the microblog site to capture microblog updates. A filter unit coupled to the retrieval unit filters the captured microblog updates according to filter criteria that remove non-actionable items from the captured microblog updates. A learning unit coupled to the filter unit prioritizes the filtered microblog updates, and a classification unit coupled to the learning unit classifies the filtered and prioritized microblog updates. An action unit coupled to the classification unit performs appropriate actions based on the classified, filtered and prioritized microblog updates.

Claims

1. A system for extracting customer feedback from a microblog site, the system comprising:

a retrieval unit coupled to the microblog site to capture microblog updates,

a filter unit coupled to the retrieval unit to filter the captured microblog updates according to filter criteria that remove non-actionable items from the captured microblog updates,

a learning unit coupled to the filter unit to prioritize the filtered microblog updates, and

a classification unit coupled to the learning unit to classify the filtered and prioritized microblog updates.

2. The system of claim 1, wherein the classification unit comprises a classification component, and an administrator statistics component.

3. The system of claim 2, wherein the classification component comprises:

a selection unit to select the filtered and prioritized microblog updates from a database, and

a determination unit to determine the actionability of the filtered and prioritized microblog updates.

4. The system of claim 2, wherein the classification component is implemented within at least one web page.

5. The system of claim 2, wherein the administrator statistics component is implemented within at least one web page.

6. The system of claim 1, further comprising an action unit coupled to the classification unit to perform actions based on the actionability of the classified, filtered and prioritized microblog updates.

7. A system for extracting customer feedback from a microblog site, the system comprising:

a retrieval unit coupled to the microblog site to capture microblog updates,

a filter unit coupled to the retrieval unit to filter the captured microblog updates according to filter criteria that remove non-actionable items from the captured microblog updates, and

a classification unit coupled to the learning unit to classify the filtered microblog updates,

wherein said classification unit comprises a classification component to determine the actionability of said filtered microblog updates.

8. The system of claim 7, further including

a learning unit coupled to the filter unit to prioritize the filtered microblog updates, and

wherein the classification component determines the actionability of the filtered and prioritized microblog updates.

9. The system of claim 7, wherein the classification component is implemented within at least one web page.

10. The system of claim 7, further including an administrator statistics component coupled to said classification component for allowing an administrator to monitor the determination of the actionability of the microblog updates.

11. The system of claim 10, wherein the administrator statistics component is implemented within at least one web page.

12. The system of claim 10, wherein the administrator statistics component comprises an activity measurement tool.

13. The system of claim 12, wherein said activity measurement tool includes a temporal measurement tool.

14. The system of claim 12, wherein said activity measurement tool includes a rate measurement tool.

15. The system of claim 12, wherein said activity measurement tool includes a microblog update evaluation tool.

17. The method of claim 15 in which the classifying step includes

selecting the filtered and prioritized microblog updates from a database, and

determining the actionability of the selected microblog updates.

18. The method of claim 15, further including a step of monitoring the results of the determining step.

19. The method of claim 15, further comprising a step of acting, the acting based on the actionability of the selected microblog updates.

16. A method of extracting customer feedback from a microblog site, the method comprising:

capturing microblog updates from said microblog site,

filtering the captured microblog updates according to filter criteria that remove non-actionable items from the captured microblog updates,

prioritizing the filtered microblog updates according to criteria that indicate the probability that each filtered update will be actionable, and

classifying the filtered and prioritized microblog updates.

20. A method for extracting customer feedback from a microblog site, the method comprising:

capturing microblog updates from said microblog site,

filtering the captured microblog updates according to filter criteria that remove non-actionable items from the captured microblog updates,

classifying the captured and filtered microblog updates,

said classifying including determining whether each captured and filtered microblog update is actionable.

21. The method of claim 20, further comprising:

prioritizing the filtered microblog updates.

22. The method of claim 20, further including a step of monitoring the results of the determining step.

23. The method of claim 22, wherein said monitoring includes measuring the time taken by said determining to determine the actionability of a plurality of captured and filtered microblog updates.

24. The system of claim 22, wherein said monitoring includes measuring the rate of performance of said determining.

25. The system of claim 22, wherein said monitoring includes checking for errors made during said determining.