System for extracting customer feedback from a microblog site

• US 8,943,061 B2
• Filed: 04/27/2012
• Issued: 01/27/2015
• Est. Priority Date: 04/27/2012
• Status: Expired due to Fees

• Current Assignee: Benbria Corporation
• Original Assignee: Benbria Corporation
• Inventors: Fraczak, Wojciech, Du, Ying
• Primary Examiner(s): Saeed, Usmaan
• Assistant Examiner(s): VO, CECILE H
• Application Number:
  US13/458,527
• Publication Number:
  US 20130290333A1
• Time in Patent Office: 1,005 Days
• Field of Search: 707/1/1, 707/748, 707/754, 707/737, 707/E17.089, 707/E17.046, 707/999.001, 705/26.7, 705/347, 705/348, 705/7.29, 705/7.33, 705/45, 706/45, 706/20, 709/219
• 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 method for extracting customer feedback from a first microblog site, the method comprising:

capturing microblog updates posted by customers from said first 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, wherein said prioritizing comprises

assigning probabilities to corresponding filtered microblog updates, said assigning based on

influence scores of the customers determined using one or more scoring services different from the first microblog site,

popularity of each of the customers based on number of followers of said customer on said first microblog site,

results from monitoring one or more microblog sites different from said first microblog site for one or more postings made by the customers, and

proximities of the customers to businesses associated with the filtered microblog updates, said proximities determined by analyzing

metadata,

hashtags associated with said filtered microblog updates, and

check-in information obtained from one or more sites different from said microblog site,

further wherein each said probability is used to indicate confidence that the corresponding filtered microblog update is actionable, and

assigning priorities to said corresponding filtered microblog updates based on said assigned probabilities;

tagging the filtered microblog updates based on the corresponding assigned priorities, and

discarding at least one of the filtered microblog updates based on said tagging,

wherein said discarding is based on an intelligent dropping policy and congestion levels; and

classifying the prioritized microblog updates, said classifying comprising

selecting at least some of the prioritized microblog updates based on said tagging, and

determining whether each selected microblog update is actionable.

2. The method of claim 1, wherein the classifying further comprises monitoring the results of the determining whether each selected microblog update is actionable.

3. The method of claim 2, wherein said monitoring includes measuring time taken by said determining.

4. The method of claim 2, wherein said monitoring includes measuring a rate of performance of said determining.

5. The method of claim 2, wherein said monitoring includes checking of errors made during said determining.

6. The method of claim 2, wherein said monitoring comprises

viewing at least one of said selected microblog updates after said determining;

and

using one or more results from said viewing as feedback to improve performance of said determining.

7. The method of claim 2, wherein said monitoring is implemented using a web page.

8. The method of claim 3, wherein said classifying is implemented using a web page.

9. The method of claim 5, wherein said monitoring is implemented using a web page.

10. The method of claim 6, wherein said monitoring is implemented using a web page.

11. The method of claim 1, further comprising performing one or more actions based on said determining whether each selected microblog update is actionable.