Assessing quality of reviews based on online reviewer generated content

1. A computer-implemented method of assessing the quality of a review, the method comprising:

accessing, by one or more computing devices, a review provided by a reviewer in an online review platform;

accessing, by the one or more computing devices, reviewer generated content provided by the reviewer, the reviewer generated content comprising social media content about a product or service posted in a social media platform outside of the review platform;

analyzing, by the one or more computing devices, the reviewer generated content posted in the social media platform to extract product review data;

matching, by the one or more computing devices, the product review data with the review provided by the reviewer in the online review platform; and

determining, by the one or more computing devices, a quality score for the review based on the product review data extracted from the reviewer generated content, the quality score providing a measure of a degree of consistency between a sentiment associated with the product review data extracted from the reviewer generated content and a sentiment associated with the review.

2. The computer-implemented method of claim 1 , wherein the method comprises prioritizing a plurality of reviews based at least in part on the quality score determined for the review.

3. The computer-implemented method of claim 1 , wherein the method comprises providing indicia in conjunction with the review based on the quality score for the review.

4. The computer-implemented method of claim 1 , wherein the product review data is related to a product or to a service.

5. The computer-implemented method of claim 1 , wherein analyzing the reviewer generated content to extract product review data comprises:

performing a sentiment analysis on the reviewer generated content to identify a sentiment expression;

analyzing the reviewer generated content surrounding the sentiment expression to identify a product or service; and

extracting the product review data from the reviewer generated content, the product review data comprising the sentiment expression and an identity of the product or service.

6. The computer-implemented method of claim 1 , wherein the reviewer generated content comprises textual content, audio content, or video content.

7. The computer-implemented method of claim 5 , wherein the product review data and the review are matched based on identity of the reviewer and the identity of the product or service extracted as part of the product review data and the product or service that is the subject of the review.

8. The computer-implemented method of claim 5 , wherein determining a quality score for the review based on the product review data comprises:

determining a review sentiment classification for the review, the review sentiment classification indicative of whether the review is a positive review or a negative review;

determining a sentiment expression classification of the sentiment expression in the product review data, the sentiment expression classification indicative of whether the sentiment expression in the product review data is a positive sentiment expression or a negative sentiment expression; and

determining a quality score for the review based on the review sentiment classification and the sentiment expression classification.

9. The computer-implemented method of claim 5 , wherein determining a quality score for the review based on the product review data comprises:

determining a first sentiment score for the review, the first sentiment score indicative of a type and a magnitude of a sentiment expressed in the review;

determining a second sentiment score for the product review data, the second sentiment score indicative of a type and a magnitude of a sentiment expression in the product review data; and

determining the quality score based at least in part on the first sentiment score and the second sentiment score.

10. The computer-implemented method of claim 9 , wherein the quality score is determined based at least in part on a difference between the first sentiment score and the second sentiment score.

11. The computer-implemented method of claim 1 , wherein the method comprises determining a rating for the reviewer based on the quality score, the rating being determined based at least in part on quality scores associated with a plurality of reviews submitted by the reviewer.

12. A computing system for assessing the quality of a review, the system comprising:

one or more memory devices storing instructions; and

one or more processors, configured to execute the instructions stored in the one or more memory devices in order to execute a method, the method comprising:

accessing a review of a product or service provided by a reviewer in an online review platform;

accessing reviewer generated content provided by the reviewer, the reviewer generated content comprising information about the product or service posted in a social media platform outside of the review platform;

analyzing the reviewer generated content posted in the social media platform to extract product review data;

matching the product review data with the review provided by the reviewer in the online review platform; and

determining a quality score for the review based on the product review data extracted from the reviewer generated content, the quality score providing a measure of a degree of consistency between a sentiment associated with the product review data extracted from the reviewer generated content and a sentiment associated with the review.

13. The computing system of claim 12 , wherein analyzing the reviewer generated content to extract product review data comprises:

performing a sentiment analysis on the reviewer generated content to identify a sentiment expression;

analyzing the reviewer generated content surrounding the sentiment expression to identify a product or service; and

extracting the product review data from the reviewer generated content, the product review data comprising the sentiment expression and an identity of the product or service.

14. The computing system of claim 12 , wherein the product review data and the review are matched based on identity of the reviewer and the identity of the product or service extracted as part of the product review data and the product or service that is the subject of the review.

15. The computing system of claim 13 , wherein determining a quality score for the review based on the product review data comprises:

determining a first sentiment score for the review, the first sentiment score indicative of a type and a magnitude of a sentiment expressed in the review;

determining a second sentiment score for the product review data, the second sentiment score indicative of a type and a magnitude of a sentiment expression in the product review data; and

determining the quality score based at least in part on the first sentiment score and the second sentiment score.

16. One or more tangible, non-transitory computer-readable media storing computer-readable instructions that when executed by one or more processors cause the one or more processors to perform operations, the operations comprising:

accessing a review of a product or service provided by a reviewer in an online review platform;

accessing reviewer generated content provided by the reviewer, the reviewer generated content comprising information about the product or service posted in a social media platform outside of the review platform;

analyzing the reviewer generated content to extract product review data;

matching the product review data with the review provided by the reviewer in the online review platform; and

determining a quality score for the review based on the product review data extracted from the reviewer generated content, the quality score providing a measure of a degree of consistency between a sentiment associated with the product review data extracted from the reviewer generated content and a sentiment associate with the review.

17. The one or more tangible, non-transitory computer-readable media of claim 16 , wherein the operation of analyzing the social media content to extract product review data comprises:

performing a sentiment analysis on the reviewer generated content to identify a sentiment expression;

analyzing the reviewer generated content surrounding the sentiment expression to identify a product or service; and

extracting the product review data from the reviewer generated content, the product review data comprising the sentiment expression and an identity of the product or service.

18. The one or more tangible, non-transitory computer-readable media of claim 16 , wherein the operation of determining a quality score for the review based on the product review data extracted from the social media platform comprises:

determining a first sentiment score for the review, the first sentiment score indicative of a type and a magnitude of a sentiment expressed in the review;

determining a second sentiment score for the product review data, the second sentiment score indicative of a type and a magnitude of a sentiment expression in the product review data; and

determining the quality score based at least in part on the first sentiment score and the second sentiment score.