System and method of sentiment data generation

• US 10,198,506 B2
• Filed: 04/20/2012
• Issued: 02/05/2019
• Est. Priority Date: 07/11/2011
• Status: Active Grant

• Current Assignee: Lexxe Pty Ltd
• Original Assignee: Lexxe Pty Ltd
• Inventors: Qiao, Hong Liang
• Primary Examiner(s): Channavajjala, Srirama
• Application Number:
  US13/452,718
• Publication Number:
  US 20130018894A1
• Time in Patent Office: 2,482 Days
• Field of Search: 707739
• CPC Class Codes: G06F 16/30 of unstructured textual data document management systems G06F16/93
• CPC Class Codes: G06F 16/332 Query formulation
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/3334 Selection or weighting of terms from queries, including natural language queries
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 16/345 Summarisation for human users
• CPC Class Codes: G06F 16/35 Clustering; Classification
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 40/131 Fragmentation of text files, e.g. creating reusable text-blocks; Linking to fragments, e.g. using XInclude; Namespaces
• CPC Class Codes: G06F 40/211 Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
• CPC Class Codes: G06F 40/30 Semantic analysis

Abstract

A method, computer-readable medium, and a computer system for automatically generating sentiment data are disclosed. One or more portions of at least one document may be determined to be associated with at least one sentiment of one or more other portions of the at least one document. One or more scores associated with the at least one sentiment may be automatically determined based on at least one respective attribute of the one or more portions. The at least one respective attribute may include a positive category, a negative category, a neutral category, a degree associated with a positive sentiment, a degree associated with a negative sentiment, some combination thereof, etc. In this manner, data associated with sentiment of one or more portions of at least one document may be generated.

Claims

1. A method of automatically generating sentiment data, said method comprising:

configuring a database to store said sentiment data and location data of said sentiment data, wherein said location data comprises a document identification, a sentence number identification with respect to said document identification, and a word number identification with respect to said sentence number identification;

processing at least one document by using a grammatical analyzer to identify a plurality of portions and said sentiment data related to said portions regardless of portion position with respect to a sentence, a sentence fragment, a paragraph, and a proximity between said portions, wherein said processing includes;

ignoring a sentence type that represents a question in said at least one document;

determining respective part of speech for said plurality of portions; and

identifying selective ones of said portions that modify others of said portions, wherein said identifying includes;

determining a first portion of said at least one document represents a first sentiment that refers to a second portion of said at least one document;

automatically determining, based on at least one attribute of said first portion, a first score for said first sentiment that refers to said second portion;

determining a third portion of said at least one document represents a second sentiment that refers to a fourth portion of said at least one document; and

automatically determining, based on at least one attribute of said third portion, a second score for said second sentiment that refers to said fourth portion;

storing said sentiment data comprising said first, second, third, and fourth portions, said first and second scores, and said at least one attributes in said database and storing said location data further comprising first location data of said first and second portions and second location data of said third and fourth portions in said database;

in response to a search result, modifying said search result by using said sentiment data to alter a visual rendering on a display of original text format and original display color of said search result and to insert visual indicators of said sentiment data in said visual rendering on said display;

determining that said second portion and said fourth portion are semantic sub-keys associated with a semantic key;

determining a third score associated with said semantic key by adding said first and second scores;

storing said semantic key and said third score in said database;

determining a first classification associated with said first portion;

determining a second classification associated with said third portion; and

storing said first and second classifications in said database, and

wherein said first and second classifications are each selected from a group consisting of an action taker, an action receiver, a description, and an identity.

2. The method of claim 1, wherein said at least one attribute of said first portion and said at least one attribute of said third portion each comprise a respective category selected from a group consisting of positive, negative and neutral.

3. The method of claim 1 further comprising:

determining that said second portion and said fourth portion are associated with a phrase;

determining a third score associated with said phrase by adding said first and second scores; and

storing said phrase and said third score in said database.

4. The method of claim 1 further comprising:

determining that said second portion and said fourth portion are theme elements associated with a theme;

determining a third score associated with said theme by adding said first and second scores; and

storing said theme and said third score in said database.

5. A non-transitory computer-readable medium having computer-readable program code embodied therein for causing a computer system to perform a method of automatically generating sentiment data, said method comprising:

configuring a database to store said sentiment data and location data of said sentiment data, wherein said location data comprises a document identification, a sentence number identification with respect to said document identification, and a word number identification with respect to said sentence number identification;

processing at least one document by using a grammatical analyzer to identify a plurality of portions and said sentiment data related to said portions regardless of portion position with respect to a sentence, a sentence fragment, a paragraph, and a proximity between said portions, wherein said processing includes;

ignoring a sentence type that represents a question in said at least one document;

determining respective part of speech for said plurality of portions; and

identifying selective ones of said portions that modify others of said portions, wherein said identifying includes;

determining a first portion of said at least one document represents a first sentiment that refers to a second portion of said at least one document;

automatically determining, based on at least one attribute of said first portion, a first score for said first sentiment that refers to said second portion;

determining a third portion of said at least one document represents a second sentiment that refers to a fourth portion of said at least one document; and

automatically determining, based on at least one attribute of said third portion, a second score for said second sentiment that refers to said fourth portion;

storing said sentiment data comprising said first, second, third, and fourth portions, said first and second scores, and said at least one attributes in said database and storing said location data further comprising first location data of said first and second portions and second location data of said third and fourth portions in said database;

in response to a search result, modifying said search result by using said sentiment data to alter a visual rendering on a display of original text format and original display color of said search result and to insert visual indicators of said sentiment data in said visual rendering on said display;

determining that said second portion and said fourth portion are semantic sub-keys associated with a semantic key;

determining a third score associated with said semantic key by adding said first and second scores;

storing said semantic key and said third score in said database;

determining a first classification associated with said first portion;

determining a second classification associated with said third portion; and

storing said first and second classifications in said database, and

wherein said first and second classifications are each selected from a group consisting of an action taker, an action receiver, a description, and an identity.

6. The non-transitory computer-readable medium of claim 5, wherein said at least one attribute of said first portion and said at least one attribute of said third portion each comprise a respective category selected from a group consisting of positive, negative and neutral.

7. The non-transitory computer-readable medium of claim 5, wherein said method further comprises:

determining that said second portion and said fourth portion are associated with a phrase;

determining a third score associated with said phrase by adding said first and second scores; and

storing said phrase and said third score in said database.

8. The non-transitory computer-readable medium of claim 5, wherein said method further comprises:

determining that said second portion and said fourth portion are theme elements associated with a theme;

determining a third score associated with said theme by adding said first and second scores; and

storing said theme and said third score in said database.

9. A system comprising a processor and a memory, wherein said memory comprises instructions that when executed by said processor implement a method of automatically generating sentiment data, said method comprising:

configuring a database to store said sentiment data and location data of said sentiment data, wherein said location data comprises a document identification, a sentence number identification with respect to said document identification, and a word number identification with respect to said sentence number identification;

processing at least one document by using a grammatical analyzer to identify a plurality of portions and said sentiment data related to said portions regardless of portion position with respect to a sentence, a sentence fragment, a paragraph, and a proximity between said portions, wherein said processing includes;

ignoring a sentence type that represents a question in said at least one document;

determining respective part of speech for said plurality of portions; and

identifying selective ones of said portions that modify others of said portions, wherein said identifying includes;

determining a first portion of said at least one document represents a first sentiment that refers to a second portion of said at least one document;

automatically determining, based on at least one attribute of said first portion, a first score for said first sentiment that refers to said second portion;

determining a third portion of said at least one document represents a second sentiment that refers to a fourth portion of said at least one document; and

automatically determining, based on at least one attribute of said third portion, a second score for said second sentiment that refers to said fourth portion;

storing said sentiment data comprising said first, second, third, and fourth portions, said first and second scores, and said at least one attributes in said database and storing said location data further comprising first location data of said first and second portions and second location data of said third and fourth portions in said database;

in response to a search result, modifying said search result by using said sentiment data to alter a visual rendering on a display of original text format and original display color of said search result and to insert visual indicators of said sentiment data in said visual rendering on said display;

determining that said second portion and said fourth portion are semantic sub-keys associated with a semantic key;

determining a third score associated with said semantic key by adding said first and second scores;

storing said semantic key and said third score in said database;

determining a first classification associated with said first portion;

determining a second classification associated with said third portion; and

storing said first and second classifications in said database, and

wherein said first and second classifications are each selected from a group consisting of an action taker, an action receiver, a description, and an identity.

10. The system of claim 9, wherein said at least one attribute of said first portion and said at least one attribute of said third portion each comprise a respective category selected from a group consisting of positive, negative and neutral.

11. The system of claim 9, wherein said method further comprises:

determining that said second portion and said fourth portion are associated with a phrase;

determining a third score associated with said phrase by adding said first and second scores; and

storing said phrase and said third score in said database.

12. The system of claim 9, wherein said method further comprises:

determining that said second portion and said fourth portion are theme elements associated with a theme;

determining a third score associated with said theme by adding said first and second scores; and

storing said theme and said third score in said database.