Generating snippet for review on the internet
View Patent ↗A method and system for generating snippet for review on the Internet. The method includes the steps of: receiving a review and a set of feedbacks corresponding to the review, where the review includes a plurality of evaluating sentences that evaluates product features of a product; calculating support degrees of each of the plurality of evaluating sentences by using the set of feedbacks; extracting, by relying on calculated support degrees of each of the evaluating sentences, at least one of the evaluating sentences from the plurality of evaluating sentences; and designating extracted evaluating sentence as a snippet of the review; where at least one of the steps is carried out by using a computer device.
1. A method of generating snippet for review on the Internet, the method comprising the steps of:
receiving a review and a set of feedbacks corresponding to said review, wherein said review comprises a plurality of evaluating sentences that evaluates product features of a product;
calculating support degrees of each of said plurality of evaluating sentences in the review, the support degrees calculated based on an evaluation of the set of feedbacks corresponding to the review;
extracting, by relying on calculated support degrees of each of said evaluating sentences, at least one of said evaluating sentences from said plurality of evaluating sentences; and
designating extracted evaluating sentence as a snippet of said review;
wherein at least one of the steps is carried out by using a computer device.
2. The method according to claim 1 , wherein said step of calculating support degrees comprises the steps of:
identifying related product features in each of said evaluating sentences;
identifying said related product features in each feedback of said set of feedbacks;
associating said evaluating sentences in said review with said feedbacks by relying on said respective related product features; and
determining whether said evaluating sentences are supported by associated feedbacks.
3. The method according to claim 2 , wherein said step of determining whether said evaluating sentences are supported by said associated feedbacks comprises the steps of:
determining a complimentary/critical polarity of each of said evaluating sentences on said related product features;
determining a complimentary/critical polarity of each of said feedbacks on said related product features; and
determining whether said evaluating sentences are supported by said associated feedbacks by evaluating said complimentary/critical polarity of said evaluating sentence and said complimentary/critical polarity of said feedback.
4. The method according to claim 2 , wherein said step of identifying said related product features in each of said evaluating sentences uses a pre-defined feature words library.
5. The method according to claim 2 , wherein said step of identifying said related product features in each feedback of said set of feedbacks uses a pre-defined feature words library.
6. The method according to claim 3 , wherein said complimentary/critical polarity of each of said evaluating sentences on said related product features is determined by a sentiment analysis technique.
7. The method according to claim 6 , wherein said sentiment analysis technique determines complimentary/critical polarity of evaluating words in each of said evaluating sentences on said related product features with a pre-defined sentiment dictionary.
8. The method according to claim 3 , wherein said complimentary/critical polarity of each of said feedbacks on said related product features is determined by a sentiment analysis technique.
9. The method according to claim 8 , wherein said sentiment analysis technique determines complimentary/critical polarity of evaluating words in each of said feedbacks on said related product features with a pre-defined sentiment dictionary.