SYSTEMS AND METHODS FOR DETECTING SENTIMENT-BASED TOPICS

• US 20110137906A1
• Filed: 12/09/2009
• Published: 06/09/2011
• Est. Priority Date: 12/09/2009
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Incorporated (International Business Machines Corporation)
• Inventors: Chen, Ying, Cai, Keke, Zhang, LI, Spangler, W. Scott
• Granted Patent: US 8,356,025 B2
• Time in Patent Office: Days
• US Class Current: 707/740
• CPC Class Codes: G06F 40/30 Semantic analysis

Abstract

A method for analyzing sentiment comprising: collecting an object from an external content repository, the collected objects forming a content database; extracting a snippet related to the subject from the content database; calculating a sentiment score for the snippet; classifying the snippet into a sentiment category; creating sentiment taxonomy using the sentiment categories, the sentiment taxonomy classifying the snippets as positive, negative or neutral; identifying topic words within the sentiment taxonomy; classifying the topic words as a sentiment topic word candidates or a non-sentiment topic word candidate, filtering the non-sentiment topic word candidates; identifying the frequency of the non-sentiment topic words in each of the sentiment categories; identifying the importance of the non-sentiment topic word for each of the sentiment categories; and, ranking the topic word, wherein the rank is calculated by combining the frequency of the topic words in each of the categories with its importance.

Claims

1. A computer implemented method for analyzing sentiment concerning a subject, comprising the steps of:

collecting an object from an external content repository, wherein the collected objects form a content database;

extracting snippets related to the subject from the content database;

calculating a sentiment score for at least one snippet that has been extracted;

for the at least one snippet for which the sentiment score has been calculated, classifying the snippet into an at least one sentiment category;

creating sentiment taxonomy using the sentiment categories, wherein the sentiment taxonomy classifies the snippets as positive, negative or neutral;

identifying topic words within the sentiment taxonomy;

classifying the topic words as a sentiment topic word candidates or a non-sentiment topic word candidate, wherein the non-sentiment topic word candidates are filtered by using a stoplist and a list of sentiment words;

identifying the frequency of the non-sentiment topic words in each of the sentiment categories;

identifying the importance of the non-sentiment topic word for each of the sentiment categories; and

,

ranking the topic word, wherein the rank is calculated by combining the frequency of the topic words in each of the categories with its importance.

2. The computer implemented method as in claim 1 wherein the external content repository is a world wide web.

3. The computer implemented method as in claim 1 wherein the external content selected from the group consisting of a blog, a message board, a comment, an article and a Twitter page.

4. The computer implemented method as in claim 1 wherein the step of identifying the importance of the non-sentiment topic word in each of the sentiment categories is performed by calculating a Pointwise Mutual Information of the non-sentiment topic word.

5. The computer implemented method as in claim 1 wherein the step of identifying the importance of the non-sentiment topic word in each of the sentiment categories is performed by calculating a word support value for the non-sentiment topic word.

6. The computer implemented method as in claim 1 wherein the step of identifying the importance of the non-sentiment topic word in each of the sentiment categories is performed by calculating a Pointwise Mutual Information value and a word support value for the non-sentiment topic word.

12. The computer implemented method as in claim 1 wherein the step of identifying the importance of the non-sentiment topic word in each of the sentiment categories is performed by calculating a Pointwise Mutual Information value and a word support value for the non-sentiment topic word.

7. A method for analyzing sentiment concerning a subject, comprising the steps of:

collecting an object from an external content repository, wherein the collected objects form a content database;

extracting snippets related to the subject from the content database;

calculating a sentiment score for at least one snippet that has been extracted;

for the at least one snippet for which the sentiment score has been calculated, classifying the snippet into an at least one sentiment category;

creating sentiment taxonomy using the sentiment categories, wherein the sentiment taxonomy classifies the snippets as positive, negative or neutral;

identifying topic words within the sentiment taxonomy;

classifying the topic words as a sentiment topic word candidates or a non-sentiment topic word candidate, wherein the non-sentiment topic word candidates are filtered by using a stoplist and a list of sentiment words;

identify the frequency of the non-sentiment topic words in each of the sentiment categories;

identifying the importance of the non-sentiment topic word for each of the sentiment categories; and

,

ranking the topic word, wherein the rank is calculated by combining the frequency of the topic words in each of the categories with its importance.

8. The method as in claim 7 wherein the external content repository is a world wide web.

9. The method as in claim 7 wherein the external content selected from the group consisting of a blog, a message board, a comment, an article and a Twitter page.

10. The method as in claim 7 wherein the step of identifying the importance of the non-sentiment topic word in each of the sentiment categories is performed by calculating a Pointwise Mutual Information of the non-sentiment topic word.

11. The method as in claim 7 wherein the step of identifying the importance of the non-sentiment topic word in each of the sentiment categories is performed by calculating a word support value for the non-sentiment topic word.

13. A computer program product comprising a computer useable storage medium to store a computer readable program, wherein the computer readable program, when executed on a computer, causes the computer to perform for operations for determining analyzing sentiment concerning a subject, comprising the steps of:

collecting an object from an external content repository, wherein the collected objects form a content database;

extracting snippets related to the subject from the content database;

calculating a sentiment score for at least one snippet that has been extracted;

for the at least one snippet for which the sentiment score has been calculated, classifying the snippet into an at least one sentiment category;

creating sentiment taxonomy using the sentiment categories, wherein the sentiment taxonomy classifies the snippets as positive, negative or neutral;

identifying topic words within the sentiment taxonomy;

classifying the topic words as a sentiment topic word candidates or a non-sentiment topic word candidate, wherein the non-sentiment topic word candidates are filtered by using a stoplist and a list of sentiment words;

identifying the frequency of the non-sentiment topic words in each of the sentiment categories;

identifying the importance of the non-sentiment topic word for each of the sentiment categories; and

,

ranking the topic word, wherein the rank is calculated by combining the frequency of the topic words in each of the categories with its importance.

14. The computer program product as in claim 13 wherein the external content repository is a world wide web.

15. The computer program product as in claim 13 wherein the external content selected from the group consisting of a blog, a message board, a comment, an article and a Twitter page.

16. The computer program product as in claim 13 wherein the step of identifying the importance of the non-sentiment topic word in each of the sentiment categories is performed by calculating a Pointwise Mutual Information of the non-sentiment topic word.

17. The computer program product as in claim 13 wherein the step of identifying the importance of the non-sentiment topic word in each of the sentiment categories is performed by calculating a word support value for the non-sentiment topic word.

18. The computer program product as in claim 13 wherein the step of identifying the importance of the non-sentiment topic word in each of the sentiment categories is performed by calculating a Pointwise Mutual Information value and a word support value for the non-sentiment topic word.