System and method for text categorization and sentiment analysis
AssigneeNewVoiceMedia, Ltd.
InventorsJonathan Kershaw, Ashley Unitt, Alan McCord
Life of this patent
Estimating the term…
Abstract
A system and method for improved categorization and sentiment analysis which is fed textual data such as transcriptions or collated data from a network enabled service, or some other source, which then segments textual data into chunks, parses the data chunks, and analyzes it using a plurality of techniques and metadata gathering methods to determine the sentiment of participating individuals concerning entities mentioned in the textual data and to categorize the discussions, for the purpose of taking actions to improve business outcomes.
Claims8
A system for categorization and sentiment analysis, comprising:
- a chunk parser for
- receiving input text;
- and
- breaking the input text into chunks of text comprising words and phrases;
- a chunk sentiment analyzer for assigning a sentiment to each chunk of text;
- a deterministic rules engine for categorizing each chunk of text into a first set of semantic categories using regular expression rules;
- a semantic similarity engine for
- adding a vector to each chunk of text representing the semantic characteristics of that chunk of text;
- and
- categorizing the chunks of text into a second set of semantic categories based on a threshold semantic distance from one or more category anchor vectors;
- a semantic cluster discover engine for categorizing chunks of text into a third set of semantic categories based on their clustering relative to one another, for those chunks of text which do not fall within the threshold distance from any of the one or more category anchor vectors;
- and
- a category comparator and integrator for
- comparing the first, second, and third sets of semantic categories to identify contextual associations between the chunks of text in each semantic category;
- and
- calculating a sentiment for the input text based on the contextual associations.
A method for categorization and sentiment analysis, comprising the steps of:
- receiving an input text;
- breaking the input text into chunks of text comprising words and phrases;
- assign a sentiment to each chunk of text;
- categorizing each chunk of text into a first set of semantic categories using regular expression rules;
- adding a vector to each chunk of text representing the semantic characteristics of that chunk of text;
- categorizing the chunks of text into a second set of semantic categories based on a threshold semantic distance from one or more category anchor vectors;
- for chunks of text which do not fall within the threshold distance from any of the one or more category anchor vectors, categorizing those chunks of text into a third set of semantic categories based on their clustering relative to one another;
- comparing the first, second, and third sets of semantic categories to identify contextual associations between the chunks of text in each semantic category;
- and
- calculating a sentiment for the input text based on the contextual associations.
Dependencies are inferred from the claim text.