Back to results
US 8,949,243 B1Granted
Systems and methods for determining a rating for an item from user reviews
AssigneeSymantec Corporation
InventorsAnand Kashyap, Karthik Ragunath Balasundaram
Life of this patent
Estimating the term…
Abstract
A computer-implemented method to determine a rating of an item is described. At least one user review with textual information relating to the item is collected. A rating for at least one sentence of the textual information is calculated. An overall rating for the item is determined based on the calculated rating for the at least one sentence of the textual information.
Claims18
A computer-implemented method to determine a rating of an item, comprising:
- collecting a plurality of user reviews with textual information relating to the item;
- identifying a feature descriptor from at least one of the plurality of user reviews;
- obtaining a user assigned non-textual rating for each of the user reviews that contain the feature descriptor;
- assigning a rating to the feature descriptor based on a frequency of occurrence of the feature descriptor in the plurality of user reviews and the user assigned non-textual rating for each of the user reviews that contain the feature descriptor;
- downloading a word sense database from a website, the word sense database being publically available on the website;
- creating a ratings database by modifying the word sense database based on analysis of the plurality of user reviews, wherein the ratings database comprises a list for feature descriptors, each entry of the list of feature descriptors comprising a section for a feature descriptor, a section for a domain associated with the feature descriptor, and a section for the rating associated with the feature descriptor;
- and
- accessing the ratings database to determine an overall rating for the item.
5 more elements
A computing device configured to determine a rating of an item, comprising:
- a processor;
- memory in electronic communication with the processor;
- instructions stored in the memory and executable by the processor to:
- collect a plurality of user reviews with textual information relating to the item;
- identify a feature descriptor from at least one of the plurality of user reviews;
- obtain a user assigned non-textual rating for each of the user reviews that contain the feature descriptor;
- assign a rating to the feature descriptor based on a frequency of occurrence of the feature descriptor in the plurality of user reviews and the user assigned non-textual rating for each of the user reviews that contain the feature descriptor;
- downloading a word sense database from a website, the word sense database being publically available on the website;
- create a ratings database by modifying the word sense database based on analysis of the plurality of user reviews, wherein the ratings database comprises a list for feature descriptors, each entry of the list of feature descriptors comprising a section for a feature descriptor, a section for a domain associated with the feature descriptor, and a section for the rating associated with the feature descriptor;
- and
- access the ratings database to determine an overall rating for the item.
8 more elements
A computer-program product for determining a rating of an item, the computer-program product comprising a non-transitory computer-readable medium storing instructions thereon, the instructions being executable by a processor to:
- collect a plurality of user reviews with textual information relating to the item;
- identify a feature descriptor from at least one of the plurality of user reviews;
- obtain a user assigned non-textual rating for each of the user reviews that contain the feature descriptor;
- assign a rating to the feature descriptor based on a frequency of occurrence of the feature descriptor in the plurality of user reviews and the user assigned non-textual rating for each of the user reviews that contain the feature descriptor;
- downloading a word sense database from a website, the word sense database being publically available on the website;
- create a ratings database by modifying the word sense database based on analysis of the plurality of user reviews, wherein the ratings database comprises a list for feature descriptors, each entry of the list of feature descriptors comprising a section for a feature descriptor, a section for a domain associated with the feature descriptor, and a section for the rating associated with the feature descriptor;
- and
- access the ratings database to determine an overall rating for the item.
5 more elements
Dependencies are inferred from the claim text.