System and method for negation aware sentiment detection
View Patent ↗A method, system and computer-usable medium are disclosed for sentiment detection based on applying an antonym dictionary to a natural language processing (NLP) system. A binary classifier is trained to predict negation cues, where a constituency parse tree is used to create rules for scope detection. The trained binary classifier, a list of conversational negation terms, and a list of antonyms are used to annotate content that considers negation cues and scope for the created rules.
1. A computer-implemented method for improving sentiment detection based on applying an antonym dictionary to a natural language processing (NLP) system comprising:
training a binary classifier to predict negation cues wherein a constituency parse tree is used to create rules for negation scope detection, moving in a linear order on the constituency parse tree;
utilizing the trained binary classifier, a list of conversational negation terms, and a list of antonyms to annotate a content considering the negation cues and scope for the created rules; and
traversing the constituency parse tree in an upward direction until a node or leaf is found with a desired category label, wherein the antonym dictionary is applied for sentiment analysis or prediction to a combination Convolution Neural Network Long Short-Term Memory architecture for sentiment analysis and a restricted and limited scope is implemented as to antonym based sentiment analysis to keep the original meaning of the content.
2. The method of claim 1 , wherein the constituency parse tree is adjusted iteratively based on negation raising predicates, verbs, and scope assessments.
3. The method of claim 1 , wherein the binary classifier is a Support Vector Machine (SVM).
4. The method of claim 1 , wherein in predicting negation cues, false detection is considered.
5. The method of claim 1 further comprising performing sentiment analysis on the annotated content.
6. The method of claim 5 , where the sentiment analysis is performed by a machine learning (ML) model.
7. The method of claim 6 , wherein the ML is a Convolutional Neural Network Long Short-Term Memory (CNN LSTM).
8. A system comprising:
a processor;
a data bus coupled to the processor; and
a computer-usable medium embodying computer program code, the computer-usable medium being coupled to the data bus, the computer program code used for improving sentiment detection based on applying an antonym dictionary to a natural language processing (NLP) system and comprising instructions executable by the processor and configured for:
training a binary classifier to predict negation cues wherein a constituency parse tree is used to create rules for negation scope detection, moving in a linear order on the constituency parse tree;
utilizing the trained binary classifier, a list of conversational negation terms, and a list of antonyms to annotate a content considering the negation cues and scope for the created rules; and
traversing the constituency parse tree in an upward direction until a node or leaf is found with a desired category label, wherein the antonym dictionary is applied for sentiment analysis or prediction to a combination Convolution Neural Network Long Short-Term Memory architecture for sentiment analysis and a restricted and limited scope is implemented as to antonym based sentiment analysis to keep the original meaning of the content.
9. The system of claim 8 , wherein the constituency parse tree is adjusted iteratively based on negation raising predicates, verbs, and scope assessments.
10. The system of claim 8 , wherein the binary classifier is a Support Vector Machine (SVM).
11. The system of claim 8 , wherein in predicting negation cues, false detection is considered.
12. The system of claim 8 further comprising performing sentiment analysis on the annotated content.
13. The system of claim 12 , wherein the sentiment analysis is performed by a Machine Learning (ML) model.
14. A non-transitory, computer-readable storage medium embodying computer program code, the computer program code comprising computer executable instructions configured for:
training a binary classifier to predict negation cues wherein a constituency parse tree is used to create rules for negation scope detection, moving in a linear order on the constituency parse tree;
utilizing the trained binary classifier, a list of conversational negation terms, and a list of antonyms to annotate a content considering the negation cues and scope for the created rules; and
traversing the constituency parse tree in an upward direction until a node or leaf is found with a desired category label, wherein the antonym dictionary is applied for sentiment analysis or prediction to a combination Convolution Neural Network Long Short-Term Memory architecture for sentiment analysis and a restricted and limited scope is implemented as to antonym based sentiment analysis to keep the original meaning of the content.
15. The non-transitory, computer-readable storage medium of claim 14 , wherein the constituency parse tree is adjusted iteratively based on negation raising predicates, verbs, and scope assessments.
16. The non-transitory, computer-readable storage medium of claim 14 , wherein in predicting negation cues, false detection is considered.
17. The non-transitory, computer-readable storage medium of claim 14 , further comprising performing sentiment analysis on the annotated content by a machine learning (ML) model.
18. The non-transitory, computer-readable storage medium of claim 14 , further comprising performing sentiment analysis on the annotated content by a Machine Learning (ML) model.
19. The non-transitory, computer-readable storage medium of claim 14 , wherein the computer executable instructions are deployable to a client system from a server system at a remote location.
20. The non-transitory, computer-readable storage medium of claim 14 , wherein the computer executable instructions are provided by a service provider to a user on an on-demand basis.