System and method for negation aware sentiment detection
AssigneeInternational Business Machines Corporation
InventorsAmita Misra, Jalal Mahmud, Saurabh Tripathy
Life of this patent
Estimating the term…
Abstract
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.
Claims20
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.
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.
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.
Dependencies are inferred from the claim text.