Back to results
US 2019/0171660 A1Published application
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.
Claims2
A system for categorization and sentiment analysis, comprising:
- a chunk parser comprising at least a plurality of programming instructions stored in a memory and operating on at least one processor of a computer, wherein the programmable instructions, when operating on the at least one processor, cause the at least one processor to:
- receive input in text form;
- break the text into chunks of text comprising words and phrases;
- and
- compute sentiment on the text at the chunk level;
- and
- a deterministic rules engine comprising at least a plurality of programming instructions stored in a memory and operating on at least one processor of a computer, wherein the programmable instructions, when operating on the processor, cause the processor to:
- categorize the text into pre-defined categories using regular expression rules and store the categorization;
- if no regular expression rule is matched, forward the chunked text to a semantic similarity engine;
- and
- a semantic similarity engine comprising at least a plurality of programming instructions stored in a memory and operating on at least one processor of a computer, wherein the programmable instructions, when operating on the at least one processor, cause the at least one processor to:
- receive chunked text;
- represent each chunk of text as a vector embedded in a high dimensional space representing semantic characteristics of the chunked text;
- categorize the chunked text into pre-defined categories using a threshold semantic similarity distance (hypersphere radius) from any of a set of pre-defined anchor word sequences for each category;
- and
- if no sufficiently close match is found to any pre-defined category anchor word sequences, forward the chunked text with embedded vector dimensions to a semantic cluster discovery engine;
- and
- a semantic cluster discovery engine comprising at least a plurality of programming instructions stored in a memory and operating on at least one processor of a computer, wherein the programmable instructions, when operating on the at least one processor, cause the at least one processor to:
- receive chunked text with embedded vector dimensions;
- determine additional new categorizations for the chunked text by analyzing the text for contextual associations using a semantic clustering analysis and store the additional cluster categories;
- and
- a category and sentiment analysis engine comprising at least a plurality of programming instructions stored in a memory and operating on at least one processor of a computer, wherein the programmable instructions, when operating on the at least one processor, cause the at least one processor to:
- receive the input text;
- retrieve the categorizations of the chunked text;
- analyze the sentiment of categories of interest to a user of the system;
- and
- output the results of the analysis to the user in the form of text, graphics, or both.
24 more elements
A method for categorization and sentiment analysis, comprising the steps of:
- receiving input in text form;
- breaking the text into chunks of text comprising words and phrases, using a chunk parser;
- computing sentiment on the text at the chunk level, using a chunk parser;
- categorizing text into pre-defined categories using regular expression rules and storing the categorization, using a deterministic rules engine;
- forwarding the chunked text to a semantic similarity engine if no regular expression rule is matched, using a deterministic rules engine;
- representing each chunk of text as a vector embedded in a high dimensional space representing semantic characteristics of the chunked text, using a semantic similarity engine;
- categorizing the chunked text into pre-defined categories using a threshold semantic similarity distance from any of a set of pre-defined anchor word sequences for each category, using a semantic similarity engine;
- forwarding the chunked text with embedded vector dimensions to a semantic cluster discovery engine if no sufficiently close match is found to a pre-defined category anchor word sequence, using a semantic similarity engine;
- determining additional new categorizations for the chunked text by analyzing the text for contextual associations, using a semantic cluster discovery engine;
- storing the additional cluster categories, using a semantic cluster discovery engine;
- retrieving the categorizations of the chunked text, using a category and sentiment analysis engine;
- analyzing the sentiment of categories of interest to a user of the system, using a category and sentiment analysis engine;
- and
- outputting the results of the analysis to the user in the form of text, graphics, or both, using a category and sentiment analysis engine.
11 more elements
Dependencies are inferred from the claim text.