METHOD AND SYSTEM FOR SENTIMENT ANALYSIS OF INFORMATION

• US 20180239815A1
• Filed: 08/12/2015
• Published: 08/23/2018
• Est. Priority Date: 08/12/2015
• Status: Active Grant

• Current Assignee: Hithink Royalflush Information Network Co., Ltd.
• Original Assignee: Hithink Royalflush Information Network Co., Ltd.
• Inventors: YI, Zheng, XIA, Wei
• Granted Patent: US 10,437,871 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/35 Clustering; Classification
• CPC Class Codes: G06F 16/958 Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06F 18/2411 based on the proximity to a decision surface, e.g. support vector machines
• CPC Class Codes: G06F 18/2413 based on distances to training or reference patterns
• CPC Class Codes: G06F 40/242 Dictionaries
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06V 10/75 Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
• CPC Class Codes: G06V 10/764 using classification, e.g. of video objects
• CPC Class Codes: G06V 30/373 using a special pattern or subpattern alphabet

Abstract

One aspect of the present disclosure relates to a method of sentiment analysis based on ambiguity analysis, which includes analyzing information with the sentiment analysis models and the ambiguity analysis models. Another aspect of the present disclosure relates to a method of training the sentiment analysis models and ambiguity analysis models, which includes acquiring information, constructing lexicons, conducting sentiment analysis and ambiguity analysis with said lexicons, acquiring corpus, and training models, etc. Meanwhile, another aspect of the present disclosure relates to a system of sentiment analysis, which includes input, and output modules, acquisition modules, processing modules and database.

Claims

1. A system comprising:

a computer readable storage medium storing executable modules comprising;

an acquisition module, wherein the acquisition module is configured to acquire information and construct a first lexicon, a second lexicon, and at least one repository;

a processing module, wherein the processing modules is configured to conduct an ambiguity analysis of the information, conduct a sentiment analysis of the analyzed information, and acquire a corpus;

a database storing the lexicons and the repository; and

a processor configured to execute the executable modules.

2. The system according to claim 1 further comprising an update module configured to expand the first lexicon, the second lexicon, and the at least one repository.

3. The system according to claim 1, wherein the acquisition module further analyzes ambiguity of words in the first lexicon to construct an ambiguity list.

4. The system according to claim 1, wherein the processing module comprises an ambiguity analysis module configured to conduct the ambiguity analysis of information.

6. The system according to claim 1, wherein the processing module comprises an ambiguity analysis model.

7. The system according to claim 6, wherein the ambiguity analysis model comprises a Maximum entropy algorithm training model.

8. The system according to claim 1, wherein the processing module comprises a sentiment analysis module configured to conduct the sentiment analysis of information.

10. The system according to claim 1, wherein the processing module further comprises a sentiment analyzer.

11. The system according to claim 10, wherein the sentiment analyzer comprises at least one of a Maximum entropy algorithm training model or a support vector machine (SVM) model.

5. (canceled)

9. (canceled)

12. A method implemented on at least one device each of which has at least one processor and a storage medium, the method comprising:

obtaining a user input;

querying a database according to the user input to retrieve non-ambiguous information marked with a sentiment type, the non-ambiguous information containing the user input; and

classifying the non-ambiguous information based on the sentiment type.

13. The method according to claim 12, wherein the non-ambiguous information is marked by the following steps:

retrieving a first lexicon and a repository;

matching and scoring information in the repository with the first lexicon; and

identifying a group of ambiguous information and a group of non-ambiguous information according to the scores.

14. The method according to claim 12, wherein the non-ambiguous information is marked according to an ambiguity analysis model.

15. The method according to claim 14, wherein the ambiguity analysis model comprises a Maximum entropy algorithm training model.

16. The method according to claim 12, wherein the sentiment type is marked by the following steps:

retrieving a second lexicon and a repository;

matching information in the repository with the second lexicon to obtain a set of sentimental sentences; and

analyzing the set of sentimental sentences and marking with corresponding sentiment types.

17. The method according to claim 12, wherein the sentiment type is marked using a sentiment analyzer.

18. The method according to claim 17, wherein the sentiment analyzer comprises at least one of a Maximum entropy algorithm training model or a support vector machine (SVM) model.

19. A method implemented on at least one device each of which has at least one processor and a storage medium, the method comprising:

acquiring information, constructing and/or expanding a first lexicon and a repository,

matching and scoring the information in the repository with the first lexicon,

recognizing a set of ambiguous information and a set of non-ambiguous information according to the scores,

retrieving a corpus from the set of ambiguous information and the set of non-ambiguous information, and

training an ambiguity analysis model with the corpus.

20. The method according to claim 19, wherein the ambiguity analysis model comprises a Maximum entropy algorithm training model.

21. The method according to claim 19, wherein the first lexicon further comprises an ambiguity list.

22. The method according to claim 19, wherein the training an ambiguity analysis model further comprises determining whether information is ambiguous by an operator.

23-25. -25. (canceled)