Capturing intentions within online text

Patent metadata

Field	Value
Publication number	US-9411860-B2
Application number	US-201114003140-A
Country	US
Kind code	B2
Filing date	Jun 28, 2011
Priority date	Jun 28, 2011
Publication date	Aug 9, 2016
Grant date	Aug 9, 2016

Abstract

A method of capturing intentions within online text comprises with a data mining device ( 105 ), identifying (block 305 ) a number of statements of intention within an online forum ( 110 ), and with the data mining device ( 105 ), extracting (block 310 ) a number of attributes ( 240, 245, 250, 255, 260 ) from the statements of intention. A system ( 100 ) for extracting intentions expressed within an online forum comprises a data mining device ( 105 ), a forum server ( 115 ) comprising a number of online forums ( 110 ) communicatively coupled to the data mining device ( 105 ), in which the data mining device identifies a number of statements of intention within the online forums ( 110 ) and extracts a number of attributes ( 240, 245, 250, 255, 260 ) from the statements of intention.

First claim

What is claimed is:

1. A method of capturing intentions within online text comprising:
with a data mining device, identifying, via a processor, a plurality of statements of intention within an online forum, wherein each statement of intention is a statement by an author in the online forum, and wherein the statement is indicative of an intent to perform an action, wherein the identifying comprises:
populating a list of seed patterns of the statements of intention,
detecting a plurality of sentences within the online forum;
for each sentence detected within the online forum, dividing the sentences into a plurality of tokens;
assigning each of the tokens a part of speech;
and detecting a plurality of statements of intention using the list of seed patterns; and

with the data mining device, extracting, via the processor, a plurality of attributes from the statements of intention.

2. The method of claim 1 , in which identifying a plurality of statements of intention within the online forum further comprises:
identifying a plurality of intention verbs and a plurality of action verbs within the statements of interest; and
determining a plurality of intention objects associated with the intention verbs and action verbs.

3. The method of claim 1 ; further comprising extracting complimentary information from the statements of intention.

4. The method of claim 1 , further comprising storing data representing the attributes extracted from the statements of intention in a data storage device.

5. The method of claim 1 , further comprising classifying detected statements of interest based on a level of certainty of the intention verb contained within the statements of interest.

6. The method of claim 1 , further comprising outputting data representing the attributes extracted from the statements of intention to an output device.

7. The method of claim 1 , in which extracting a plurality of attributes from the statements of intention comprises extracting a plurality of intention verbs, a plurality of action verbs, and a plurality of intention objects from the statements of intention.

8. The method of claim 1 , further comprising obtaining text from a source.

9. A system for extracting intentions expressed within an online forum comprising:
a data mining device;
a forum server comprising a plurality of online forums communicatively coupled to the data mining device,

in which the data mining device identifies, via a processor, a plurality of statements of intention within the online forums and extracts, via the processor, a plurality of attributes from the statements of intention, wherein each statement of intention is a statement by an author in the online forum, wherein the statement is indicative of an intent to perform an action, and wherein the plurality of statements are identified by:
populating a list of seed patterns of the statements of intention;
detecting a plurality of sentences within the online forum;
for each sentence detected within the online forum, dividing the sentences into a plurality of tokens;
assigning each of the tokens a part of speech;
and detecting a plurality of statements of intention using the list of seed patterns.

10. The system of claim 9 , further comprising an online text database communicatively coupled to the data mining device via the network that stores portions of text of a plurality of online forums,
in which the data mining device identifies a plurality of statements of intention within the online forums stored in the online text database, and extracts a plurality of attributes from the statements of intention.

11. The system of claim 9 , further comprising an output device that displays data representing the attributes extracted from the statements of intention.

12. The system of claim 9 , in which the forum server is communicatively coupled to the data mining device via a network.

13. A method of realizing an economic gain from the capture of intentions within online text comprising:
outputting, via a processor, data representing attributes extracted from statements of intention within online forums to a business entity, wherein each statement of intention is a statement by an author in the online forum, wherein the statement is indicative of an intent to perform an action, and wherein the statements are identified by:
populating a list of seed patterns of statements of intention;
detecting a plurality of sentences within the online forums;
for each sentence detected within the online forums, dividing the sentences into a plurality of tokens;
assigning each of the tokens a part of speech;
and detecting a plurality of statements of intention using the list of seed patterns; and
charging, via the processor, the business entity for access to the data representing the attributes extracted from the statements of intention.

14. The method of claim 13 , in which the data representing the attributes extracted from the statements of intention is presented to the business entity within a graphical user interface.

Assignees

• Castellanos Maria G
• Ghosh Riddhiman
• Dekhil Mohamed E
• Dayal Umeshwar
• Hsu Meichun
• Hewlett Packard Entpr Dev Lp

Inventors

• Castellanos Maria G
• Ghosh Riddhiman
• Dekhil Mohamed E
• Dayal Umeshwar
• Hsu Meichun

Classifications

• G06Q30/02 Primary

  Marketing; Price estimation or determination; Fundraising · CPC title

• G06F16/2465 Primary

  Query processing support for facilitating data mining operations in structured databases · CPC title

• G06F17/30539 Primary

  Physics · mapped topic