HYBRID REVIEW SYNTHESIS

• US 20140164302A1
• Filed: 12/07/2012
• Published: 06/12/2014
• Est. Priority Date: 12/07/2012
• Status: Active Grant

• Current Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Di Fabbrizio, Giuseppe, Stent, Amanda Joy
• Granted Patent: US 9,483,730 B2
• Time in Patent Office: Days
• US Class Current: 706/46
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06Q 30/0631 Item recommendations

Abstract

A method of generating a summary review of an entity from a set of reviews includes generating a distribution and determining a polarity of the distribution associated with a plurality of aspect ratings based on the set of reviews. The set of reviews are associated with the entity, and the plurality of aspect ratings are associated with an aspect, or feature, of the entity. The method includes selecting an opinion correlated with the polarity from the set of reviews, and generating the summary review, the summary review comprising: a summary statement based on the distribution and the polarity; and the opinion. An apparatus and computer-readable device are also disclosed.

Claims

1. A method of generating a summary review associated with an entity, the method comprising:

generating, using a processing device, a distribution and determining a polarity of the distribution associated with a plurality of aspect ratings based on a set of reviews, the set of reviews being associated with the entity, the plurality of aspect ratings being associated with an aspect of the entity, the aspect representing a feature associated with the entity;

selecting, using the processing device, an opinion from the set of reviews, the opinion being correlated with the polarity; and

generating, using the processing device, the summary review, the summary review comprising a summary statement and the opinion, the summary statement being based on the distribution and the polarity.

2. The method of claim 1, the summary review comprising a quotable sentence extracted from the set of reviews, the quotable sentence comprising the opinion.

3. The method of claim 1, further comprising defining a plurality of aspects representing a plurality of features associated with the entity, generating the distribution and determining the polarity of the distribution associated with each of the plurality of aspects, selecting a plurality of opinions from the set of reviews, each of the plurality of opinions being correlated with the polarity associated with one of the plurality of aspects, the summary review comprising the plurality of the opinions.

4. The method of claim 3, the plurality of opinions being presented in a predetermined order, the predetermined order being based on a strength of the polarity associated with each of the plurality of aspects.

5. The method of claim 1, further comprising generating the summary review in response to an inquiry from a user, retrieving metadata associated with each of the set of reviews, and calculating a confidence score associated with each of the set of reviews based on the metadata, the opinion selected from the set of reviews being associated with a high confidence score, the high confidence score indicating the opinion includes information targeted to the user.

6. The method of claim 5, wherein the metadata includes a time stamp to indicate timeliness, geographic location, and authorship information associated with the opinion.

7. The method of claim 3, further comprising calculating an overall rating associated with the plurality of aspects based on the plurality of opinions, the summary review including a statement representing the overall rating associated with the entity.

8. A computer-readable device to store instructions that, when executed by a processing device, cause the processing device to perform operations comprising:

generating a distribution and determining a polarity of the distribution associated with a plurality of aspect ratings based on a set of reviews, the set of reviews being associated with an entity, the plurality of aspect ratings being associated with an aspect of the entity, the aspect representing a feature associated with the entity;

selecting an opinion from the set of reviews, the opinion being correlated with the polarity; and

generating a summary review, the summary review comprising a summary statement and the opinion, the summary statement being based on the distribution and the polarity.

9. The computer-readable device of claim 8, wherein the operations further comprise extracting a quotable sentence from the set of reviews, the summary review comprising the quotable sentence, the quotable sentence comprising the opinion.

10. The computer-readable device of claim 8, wherein the operations further comprise:

generating a summary review associated with the entity by defining a plurality of aspects representing a plurality of features associated with the entity;

generating the distribution and determining the polarity of the distribution associated with each of the plurality of aspects; and

selecting a plurality of opinions from the set of reviews, each of the plurality of opinions being correlated with the polarity associated with one of the plurality of aspects, the summary review comprising the plurality of the opinions.

11. The computer-readable device of claim 10, wherein the operations further comprise presenting the plurality of opinions in a predetermined order, the predetermined order being based on a strength of the polarity associated with each of the plurality of aspects.

12. The computer-readable device of claim 8, wherein the operations further comprise:

generating the summary review in response to an inquiry from a user;

retrieving metadata associated with each of the set of reviews; and

calculating a confidence score associated with each of the set of reviews based on the metadata, the opinion selected from the set of reviews being associated with a high confidence score, the high confidence score indicating the opinion includes information targeted to the user.

13. The computer-readable device of claim 12, wherein the metadata includes a time stamp to indicate timeliness, geographic location, and authorship information associated with the opinion.

14. The computer-readable device of claim 10, wherein the operations further comprise generating the summary review by calculating an overall rating associated with the plurality of aspects based on the plurality of opinions, the summary review including a statement representing the overall rating associated with the entity.

15. An apparatus to generate a summary review associated with an entity, the apparatus comprising:

a processing device; and

memory to store instructions that, when executed by the processing device, cause the processing device to perform operations comprising;

generating a distribution and determining a polarity of the distribution associated with a plurality of aspect ratings based on a set of reviews, the set of reviews being associated with the entity, the plurality of aspect ratings being associated with an aspect of the entity, the aspect representing a feature associated with the entity;

selecting an opinion from the set of reviews, the opinion being correlated with the polarity; and

generating the summary review, the summary review comprising a summary statement and the opinion, the summary statement being based on the distribution and the polarity.

16. The apparatus of claim 15, wherein the summary review comprises a quotable sentence extracted from the set of reviews, the quotable sentence comprising the opinion.

17. The apparatus of claim 15, wherein the operations further comprise:

generating the distribution and determining the polarity of the distribution associated with each of a plurality of aspects representing a plurality of features associated with the entity; and

selecting a plurality of opinions from the set of reviews, each of the plurality of opinions being correlated with the polarity associated with one of the plurality of aspects, the summary review comprising the plurality of the opinions.

18. The apparatus of claim 17, wherein the operations further comprise presenting the plurality of opinions in a predetermined order, the predetermined order being based on a strength of the polarity associated with each of the plurality of aspects.

19. The apparatus of claim 15, wherein the operations further comprise:

generating the summary review in response to an inquiry from a user;

retrieving metadata associated with each of the set of reviews;

calculating a confidence score associated with each of the set of reviews based on the metadata; and

selecting the opinion that is associated with a high confidence score from the set of reviews, the high confidence score indicating the opinion includes information targeted to the user.

20. The apparatus of claim 17, wherein the operations further comprise calculating an overall rating associated with the plurality of aspects based on the plurality of opinions, the summary review including a statement representing the overall rating associated with the entity.