DETERMINATION OF DOCUMENT CREDIBILITY

• US 20130054502A1
• Filed: 08/30/2011
• Published: 02/28/2013
• Est. Priority Date: 08/30/2011
• Status: Active Grant

• Current Assignee: Accenture Global Services Limited (Accenture PLC)
• Original Assignee: Accenture Global Services Limited (Accenture PLC)
• Inventors: Fano, Andrew E., Cumby, Chad, Krema, Marko, Kandallu, Sai P.
• Granted Patent: US 8,650,143 B2
• Time in Patent Office: Days
• US Class Current: 706/46
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation

Abstract

A plurality of topics encompassed in a document are determined and, for each such topic, a sentiment for that topic is likewise determined. Thereafter, credibility of the document is determined based on the resulting plurality of sentiments. In one embodiment, credibility of at least one target document is established by first determining, for each of a plurality of portions of the at least one target document, at least one topic encompassed in the portion to provide a plurality of target topics. Likewise, sentiment scores are determined for each portion. Thereafter, for each prior topic of a plurality of prior topics, a topic-sentiment score is determined based on sentiment scores corresponding to those portions of the plurality of portions having a target topic corresponding to the prior topic. A credibility index is determined based on the resulting plurality of topic-sentiment scores.

Claims

1. A method for determining credibility of a document, the method comprising:

determining, by a processing device, a plurality of topics encompassed in the document;

determining, by the processing device and for each topic of the plurality of topics, a sentiment to provide a plurality of sentiments; and

determining, by the processing device, credibility of the document based on the plurality of sentiments.

2. The method of claim 1, wherein the document is at least one proposed communication authored by an entity.

3. The method of claim 2, further comprising:

revising the document based on the credibility of the document.

4. The method of claim 1, wherein the document is authored by someone other than an entity.

5. The method of claim 4, wherein the document is a review of at least one of the entity, a service provided by the entity or a product provided by the entity.

6. The method of claim 1, wherein determining the plurality of topics further comprises analyzing the document according to at least one topic model.

7. The method of claim 1, wherein determining the sentiments corresponding to the plurality of topics further comprises analyzing the document according to at least one sentiment model.

8. The method of claim 1, further comprising:

displaying, via a display operatively connected to the processing device, information regarding one or more of;

the plurality of topics, the plurality of sentiments and the credibility of the document.

9. An apparatus for determining credibility of a document, comprising:

a processor;

a storage device operatively connected to the processor and having stored thereon instructions that, when executed by the processor, cause the processor to;

determine a plurality of topics encompassed in the document;

determine, for each topic of the plurality of topics, a sentiment to provide a plurality of sentiments; and

determine credibility of the document based on the plurality of sentiments.

10. The apparatus of claim 9, wherein those instructions that, when executed by the processor, cause the processor to determine the plurality of topics are further operative to cause the processor to determine the plurality of topics based on at least one topic model.

11. The apparatus of claim 9, wherein those instructions that, when executed by the processor, cause the processor to determine the plurality of sentiments are further operative to cause the processor to determine the plurality of sentiments based on at least one sentiment model.

12. The apparatus of claim 9, the storage device further comprising instructions that, when executed by the processor, cause the processor to:

display, via a display operatively connected to the processor, information regarding one or more of;

the plurality of topics, the plurality of sentiments and the credibility of the document.

13. A method for determining credibility of at least one target document corresponding to an entity, the method comprising:

for each portion of a plurality of portions of the at least one target document, determining, by a processing device, at least one topic encompassed in the portion based on at least one topic model to provide a plurality of target topics;

for each portion of the plurality of portions, determining, by the processing device, a sentiment score for the portion based on at least one sentiment model;

for each prior topic of a plurality of prior topics, determining, by the processing device, a topic-sentiment score based on sentiments scores corresponding to those portions of the plurality of portions having a target topic of the plurality of target topics corresponding to the prior topic, thereby providing a plurality of topic-sentiment scores; and

determining, by the processing device, a credibility index based on at least some of the plurality of topic-sentiment scores.

14. The method of claim 13, wherein the at least one target document is at least one proposed communication authored by the entity.

15. The method of claim 14, further comprising:

revising the at least one target document based on the credibility index.

16. The method of claim 13, wherein the at least one target document is authored by someone other than the entity.

17. The method of claim 16, wherein the at least one target document is a review of at least one of the entity, a service provided by the entity or a product provided by the entity.

18. The method of claim 13, further comprising:

determining, by the processing device, the plurality of prior topics and corresponding prior topic scores based on analysis of prior documents according to the at least one topic model,

wherein determining the credibility index further comprises computing a weighted average of the at least some of the plurality of topic-sentiment scores using, as weights, ones of the plurality of prior topic scores corresponding to the at least some of the plurality of topic-sentiment scores.

19. The method of claim 18, wherein the prior documents are authored by the entity.

20. The method of claim 13, wherein each of the plurality of portions comprises a sentence.

21. The method of claim 13, further comprising:

displaying, by the processing device via a display, the plurality of topic-sentiment scores.

22. The method of claim 21, further comprising:

displaying, by the processing device via the display and for a topic-sentiment score of the plurality of topic-sentiment scores, the sentiments scores used to determine the topic-sentiment score.

23. The method of claim 22, further comprising:

displaying, by the processing device via the display and for a sentiment score of the sentiment scores, that portion of the plurality of portions corresponding to the sentiment score.

24. An apparatus for determining credibility of at least one target document corresponding to an entity, comprising:

a processor;

a storage device operatively connected to the processor and having stored thereon instructions that, when executed by the processor, cause the processor to;

for each portion of a plurality of portions of the at least one target document, determine at least one topic encompassed in the portion based on at least one topic model to provide a plurality of target topics;

for each portion of the plurality of portions, determine a sentiment score for the portion based on at least one sentiment model;

for each prior topic of a plurality of prior topics, determine a topic-sentiment score based on sentiments scores corresponding to those portions of the plurality of portions having a target topic of the plurality of target topics corresponding to the prior topic, thereby providing a plurality of topic-sentiment scores; and

determine a credibility index based on at least some of the plurality of topic-sentiment scores.

25. The apparatus of claim 24, the storage device further comprising instructions that, when executed by the processor, cause the processor to:

determine the plurality of prior topics and corresponding prior topic scores based on analysis of prior documents according to the at least one topic model,

wherein the credibility index is determined by computing a weighted average of the at least some of the plurality of topic-sentiment scores using, as weights, ones of the plurality of prior topic scores corresponding to the at least some of the plurality of topic-sentiment scores.

26. The apparatus of claim 24, further comprising a display operatively coupled to the processor and the storage device further comprising instructions that, when executed by the processor, cause the processor to:

display, via the display, the plurality of topic-sentiment scores.

27. The apparatus of claim 26, the storage device further comprising instructions that, when executed by the processor, cause the processor to:

display, via the display and for a topic-sentiment score of the plurality of topic-sentiment scores, the sentiments scores used to determine the topic-sentiment score.

28. The method of claim 27, the storage device further comprising instructions that, when executed by the processor, cause the processor to:

display, via the display and for a sentiment score of the sentiment scores, that portion of the plurality of portions corresponding to the sentiment score.