System for management of sentiments and methods thereof

摘要

Systems and methods for improved management of sentiments over conventional approaches are disclosed. Supervised approach is used to augment the rule-based approach for classification. Initially, sentiment evaluation is performed by the system using a rule based approach and an interface is provided to the user to give feedback on the correctness of evaluated sentiment. This feedback is used by the sentiment evaluation system to update the set of rule-based and also apply the supervised approach to train the classifier for evaluating complex posts.

主权项

1. A method for optimizing sentiment classification, the method comprising:
performing, by a sentiment management computing device, a classification analysis on a first post received for sentiment evaluation to determine a first sentiment classification; receiving, by the sentiment management computing device, a second sentiment classification related to the first post from at least one user; and updating, by the sentiment management computing device, the classification analysis when the first sentiment classification does not match the second sentiment classification, wherein the updating the sentiment classification analysis comprises:
plotting the first post in a multidimensional feature space, wherein each dimension in the multidimensional feature space represents a unique feature corresponding to the first post;performing a neighborhood operation for the first post to identify a pattern space in the multidimensional feature space containing a plurality of posts associated with the first post; andapplying the second sentiment classification to the plurality of posts in the pattern space, wherein the plurality of posts in the pattern space provide updated training data for the classification analysis.