Social media mining system for early detection of civil unrest events

• US 10,255,352 B1
• Filed: 11/07/2014
• Issued: 04/09/2019
• Est. Priority Date: 04/05/2013
• Status: Active Grant

• Current Assignee: HRL Laboratories LLC (The Boeing Co.)
• Original Assignee: HRL Laboratories LLC (The Boeing Co.)
• Inventors: Xu, Jiejun, Lu, Tsai-Ching, Compton, Ryan F., Allen, David L.
• Primary Examiner(s): Wong, Lut
• Application Number:
  US14/535,812
• Time in Patent Office: 1,614 Days
• Field of Search: 706 45
• CPC Class Codes: G06F 16/332 Query formulation
• 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: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06N 5/041 Abduction
• CPC Class Codes: G06Q 10/0635 Risk analysis of enterprise or organisation activities
• CPC Class Codes: G06Q 10/101 Collaborative creation, e.g. joint development of products or services
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: G06Q 50/26 Government or public services business processes related to the transportation industry G06Q50/40

Abstract

Described is a system for early detection of events via social media mining. The system receives, as input, social media blog posts comprising textual data. The system processes the social media blog posts through a cascade of filters. The cascade of filters comprises an event term detection filter, a location term detection filter following the event term detection filter, and a future date detection filter following the location term detection filter. A plurality of candidate social media blog posts describing an event of interest on a future date is output to a user for further analysis.

Claims

1. A social media mining system for early detection of events, the system comprising:

one or more processors and a non-transitory computer-readable medium having executable instructions encoded thereon such that when executed, the one or more processors perform operations of;

receiving, as input, a plurality of social media blog posts comprising textual data;

processing the plurality of social media blog posts through a cascade of filters;

wherein the cascade of filters comprises an event term detection filter, a location term detection filter following the event term detection filter, and a future date detection filter following the location term detection filter;

searching the textual data for month terms, resulting in a set of social media blog posts comprising month terms;

searching the set of social media blog posts comprising month terms for numbers less than 31, resulting in a set of social media blog posts comprising day terms;

searching each social media blog post in the set of social media blog posts comprising day terms for a year which minimizes a number of days between a date mentioned in the social media blog post and a published date of the social media blog post, resulting in a set of social media blog posts comprising date terms;

verifying that the date terms occur after published dates of the social media blog posts; and

outputting a plurality of candidate social media blog posts describing an event of interest on a future date to a user for further analysis.

2. The social media mining system as set forth in claim 1, wherein the one or more processors further perform operations of using a set of user-defined keywords for the event term detection filter to match textual data in the plurality of social media blog posts with the set of user-defined keywords.

3. The social media mining system as set forth in claim 2, wherein the one or more processors further perform an operation of using a set of user-defined location terms for the location term detection filter to match textual data in the plurality of social media blog posts with the set of user-defined location terms.

4. The social media mining system as set forth in claim 1, wherein the one or more processors further perform an operation of customizing at least one of the event term detection filter, the location term detection filter, and the future date detection filter to adjust the number of the plurality of candidate social media blog posts describing the event of interest on the future date.

5. A computer-implemented method for early detection of events via social media mining, comprising:

an act of causing a data processor to execute instructions stored on a non-transitory memory such that upon execution, one or more processors perform operations of;

receiving, as input, a plurality of social media blog posts comprising textual data;

processing the plurality of social media blog posts through a cascade of filters;

wherein the cascade of filters comprises an event term detection filter, a location term detection filter following the event term detection filter, and a future date detection filter following the location term detection filter;

searching the textual data for month terms, resulting in a set of social media blog posts comprising month terms;

searching the set of social media blog posts comprising month terms for numbers less than 31, resulting in a set of social media blog posts comprising day terms;

searching each social media blog post in the set of social media blog posts comprising day terms for a year which minimizes a number of days between a date mentioned in the social media blog post and a published date of the social media blog post, resulting in a set of social media blog posts comprising date terms;

verifying that the date terms occur after published dates of the social media blog posts; and

outputting a plurality of candidate social media blog posts describing an event of interest on a future date to a user for further analysis.

6. The method as set forth in claim 5, wherein the one or more processors perform operations of using a set of user-defined keywords for the event term detection filter to match textual data in the plurality of social media blog posts with the set of user-defined keywords.

7. The method as set forth in claim 6, wherein the one or more processors further perform an operation of using a set of user-defined location terms for the location term detection filter to match textual data in the plurality of social media blog posts with the set of user-defined location terms.

8. The method as set forth in claim 5, wherein the one or more processors further perform an operation of customizing at least one of the event term detection filter, the location term detection filter, and the future date detection filter to adjust the number of the plurality of candidate social media blog posts describing the event of interest on the future date.

9. A computer program product for early detection of events via social media mining, the computer program product comprising computer-readable instructions stored on a non-transitory computer-readable medium that are executable by a computer having a processor for causing the processor to perform operations of:

receiving, as input, a plurality of social media blog posts comprising textual data;

processing the plurality of social media blog posts through a cascade of filters;

wherein the cascade of filters comprises an event term detection filter, a location term detection filter following the event term detection filter, and a future date detection filter following the location term detection filter;

searching the textual data for month terms, resulting in a set of social media blog posts comprising month terms;

searching the set of social media blog posts comprising month terms for numbers less than 31, resulting in a set of social media blog posts comprising day terms;

searching each social media blog post in the set of social media blog posts comprising day terms for a year which minimizes a number of days between a date mentioned in the social media blog post and a published date of the social media blog post, resulting in a set of social media blog posts comprising date terms;

verifying that the date terms occur after published dates of the social media blog posts; and

outputting a plurality of candidate social media blog posts describing an event of interest on a future date to a user for further analysis.

10. The computer program product as set forth in claim 9, further comprising instructions for causing the processor to perform operations of using a set of user-defined keywords for the event term detection filter to match textual data in the plurality of social media blog posts with the set of user-defined keywords.

11. The computer program product as set forth in claim 10, further comprising instructions for causing the processor to perform an operation of using a set of user-defined location terms for the location term detection filter to match textual data in the plurality of social media blog posts with the set of user-defined location terms.

12. The computer program product as set forth in claim 9, further comprising instructions for causing the processor to perform an operation of customizing at least one of the event term detection filter, the location term detection filter, and the future date detection filter to adjust the number of the plurality of candidate social media blog posts describing the event of interest on the future date.

13. A cascade of filters for early detection of events via social media mining, the cascade of filters comprising:

a first event term detection filter;

a second location term detection filter following the first event term detection filter; and

a third future date detection filter following the second location term detection filter;

wherein the cascade of filters receives, as input, a plurality of social media blog posts comprising textual data;

wherein the cascade of filters sequentially processes the plurality of social media blog posts;

wherein the cascade of filters outputs a plurality of candidate social media blog posts describing an event of interest on a future date to a user for further analysis;

wherein the cascade of filters outputs a set of social media blog posts comprising month terms;

wherein the cascade of filters outputs a set of social media blog posts comprising day terms;

wherein the cascade of filters outputs a set of social media blog posts comprising date terms, wherein the set of social media blog posts comprising date terms are obtained by searching each social media blog post in the set of social media blog posts comprising day terms for a year which minimizes a number of days between a date mentioned in the social media blog post and a published date of the social media blog post;

wherein the date terms have been verified to occur after published dates of the social media blog posts; and

wherein the cascade of filters is implemented as computer-readable instructions stored on a non-transitory computer-readable medium that are executable by a computer having a processor.