Extraction and summarization of sentiment information

• US 20070282867A1
• Filed: 05/30/2006
• Published: 12/06/2007
• Est. Priority Date: 05/30/2006
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: McAllister, Ian A., Ponath, Christoph R., Bao, Ling, Hanks, Steven J.
• Granted Patent: US 7,792,841 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

Methods and systems for extraction and summarization of sentiment information related to a particular research subject are disclosed. A method includes accessing sources of information that contain sentiment information that is related to the research subject and extracting the sentiment information from the sources of information as opinions related to the research subject. Opinion categories related to features of the research subject are identified. From this information a summarization of the sentiment information that is related to the particular research subject that includes the identified opinion categories is generated. Subsequently, access is provided to the summarization for graphical presentation.

Claims

1. Method for extraction and summarization of sentiment information contained in sources of information that is related to a particular research subject, comprising:

accessing said sources of information that contain said sentiment information that is related to said research subject;

extracting said sentiment information from said sources of information as opinions related to said research subject;

identifying opinion categories related to features of said research subject based upon a determined magnitude of the number of opinions obtained that are related to said opinion categories;

generating a summarization of said sentiment information that comprises said opinion categories; and

providing access to said summarization of said sentiment information for graphical presentation.

2. The method of claim 1 further comprising:

accessing updated model parameters and text extracting rules, based on an offline training process and feedback from users, for use in extraction and summarization of said sentiment information.

3. The method of claim 2 wherein said offline training process comprises manual tagging, feature clustering analysis, human evaluation and adjustment and algorithm evaluation.

4. The method of claim 1 wherein said sources of information comprise customer reviews, forums, discussion groups, and blogs.

5. The method of claim 1 wherein said opinions are capable of being accessed and reviewed individually.

6. The method of claim 5 wherein said opinions that are capable of being accessed and reviewed individually are graphically presented.

7. A computer useable medium having computer useable code embodied therein that when executed causes a computer processor to perform operations comprising:

retrieving web-based documents that contain opinions that are related to subject matter under research;

extracting opinions from said documents that are related to said subject matter that is under research;

collecting said opinions as a measure of the collective web-based sentiment related to said subject matter that is registered on the web; and

summarizing said opinions according to the most discussed features of said subject matter.

8. The medium of claim 7 further comprising:

accessing updated model parameters and text extracting rules, based on an offline training process and feedback from users, for use in extraction and summarization of said opinions.

9. The medium of claim 8 wherein said offline training process comprises manual tagging, feature clustering analysis, human evaluation and adjustment and algorithm evaluation.

10. The medium of claim 7 wherein said documents are found at various internet addresses.

11. The medium of claim 7 wherein said documents include customer reviews, forums, discussion groups, and blogs.

12. The medium of claim 7 wherein said features comprise topics related to said subject matter that are discussed most often.

13. The medium of claim 7 wherein said opinions are capable of being accessed and reviewed individually.

14. An apparatus comprising:

a computer readable memory unit;

a processor coupled to said memory unit, said processor for executing a method for extraction and summarization of sentiment information contained in sources of information that is related to a particular research subject, comprising;

collecting opinions about said research subject, that are located in documents, from a plurality of web-based sources;

categorizing groups of said opinions that are related to a specific feature of said research subject; and

distinguishing portions of said groups of said opinions as being either positive, negative or neutral.

15. The apparatus of claim 14 further comprising:

generating and updating model parameters and text extracting rules, based on an offline training process and feedback from users, for use in extraction and summarization of said sentiment information.

16. The apparatus of claim 15 wherein said offline training process comprises manual tagging, feature clustering analysis, human evaluation and adjustment and algorithm evaluation.

17. The apparatus of claim 14 wherein said documents are found at various internet addresses.

18. The apparatus of claim 14 wherein said documents include customer reviews, forums, discussion groups, and blogs.

19. The apparatus of claim 14 wherein said research subject is a product or a service.

20. The apparatus of claim 14 wherein said opinions are capable of being accessed and reviewed individually.