# US 2021/0334466 A1 · Systems and methods of artificially intelligent sentiment analysis

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0334466 A1
- Document ID: US20210334466A1
- Status: Published application
- Kind: A1
- Application number: 16/859,301
- Filed: 2020-04-27
- Published: 2021-10-28
- Earliest claimed: 2020-04-27
- Assignees: Early Warning Services, LLC
- Applicants: Early Warning Services, LLC
- Inventors: Edwin F. Campos Ortega; Eric D. First; Deepakshi Aswal; Jie He
- Web page: https://patentgrep.com/patent/US20210334466A1

## CPC

- G06F 40/30: Semantic analysis
- G06F 40/289: Phrasal analysis, e.g. finite state techniques or chunking
- G06N 20/00: Machine learning
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A method of providing sentiment analysis includes training a computer system to identify a polarity of a sentiment for a plurality of phrases and receiving, at the computer system, an input from a website. The input includes a text string including a phrase. The method includes determining, by the computer system, the polarity of the sentiment of the phrase by comparing the phrase to the plurality of phrases and sending, by the computer system, a command to the website that causes the website to display predetermined content based on the determined polarity of the sentiment of the phrase.

## Claims

### Claim 1

A method of providing sentiment analysis, comprising:
training a computer system to identify a polarity of a sentiment for a plurality of phrases;
receiving, at the computer system, an input from a website, the input comprising a text string including a phrase;
determining, by the computer system, the polarity of the sentiment of the phrase by comparing the phrase to the plurality of phrases; and
sending, by the computer system, a command to the website that causes the website to display predetermined content based on the determined polarity of the sentiment of the phrase.

### Claim 2 (depends on 1)

The method of providing sentiment analysis of claim 1, wherein:
training the computer system comprises:
classifying each of a plurality of comments as being positive or negative based on scores associated with each of the plurality of comments;
generating the plurality of phrases from the plurality of comments; and
assigning each of the plurality of phrases the polarity of the sentiment based at least in part on the scores associated with each of the plurality of comments.

### Claim 3 (depends on 2)

The method of providing sentiment analysis of claim 2, wherein:
generating the plurality of phrases comprises:
removing one or more of single-letter words, two-letter words, words on a pre-defined list, punctuation, or numbers from each of the plurality of comments to form sets of remaining words for each of the plurality of comments; and
lemmatizing the sets of remaining words for each of the plurality of comments to generate the plurality of phrases.

### Claim 4 (depends on 2)

The method of providing sentiment analysis of claim 2, wherein:
training the computer system further comprises removing comments that are classified as being neutral.

### Claim 5 (depends on 1)

The method of providing sentiment analysis of claim 1, wherein:
the predetermined content comprises a pre-determined text-based message that is selected based at least in part on the polarity of the sentiment of the phrase.

### Claim 6 (depends on 1)

The method of providing sentiment analysis of claim 1, further comprising:
extracting the phrase from the text string by removing one or more of single-letter words, two-letter words, words on a pre-defined list, punctuation, or numbers from the text string; and
lemmatizing any remaining words of the phrase prior to determining the polarity of the sentiment of the phrase.

### Claim 7 (depends on 1)

The method of providing sentiment analysis of claim 1, wherein:
the predetermined content comprises a textual response to the phrase.

### Claim 8

A computing system for providing sentiment analysis, comprising:
a communications interface that is in communication with a website;
a processor; and
a memory having instructions stored thereon that, when executed by the processor, cause the processor to:
train the computer system to identify a polarity of a sentiment for a plurality of phrases;
receive, using the communications interface, an input from the website, the input comprising a text string including a phrase;
determine the polarity of the sentiment of the phrase by comparing the phrase to the plurality of phrases; and
send, using the communications interface, a command to the website that causes the website to display predetermined content based on the determined polarity of the sentiment of the phrase.

### Claim 9 (depends on 8)

The computing system for providing sentiment analysis of claim 8, wherein:
the predetermined content is selected based at least in part on the polarity of the sentiment of the phrase and on the content of the phrase.

### Claim 10 (depends on 8)

The computing system for providing sentiment analysis of claim 8, wherein:
the predetermined content comprises a color being displayed around the input, the color being selected based on the polarity of the sentiment of the phrase.

### Claim 11 (depends on 8)

The computing system for providing sentiment analysis of claim 8, wherein the instructions are further configured to cause the processor to:
translate the text string into a different language prior to determining the polarity of the sentiment of the phrase.

### Claim 12 (depends on 8)

The computing system for providing sentiment analysis of claim 8, wherein:
training the computer system comprises:
classifying each of a plurality of comments as being positive or negative based on scores associated with each of the plurality of comments;
generating the plurality of phrases from the plurality of comments; and
assigning each of the plurality of phrases the polarity of the sentiment based at least in part on the scores associated with each of the plurality of comments.

### Claim 13 (depends on 12)

The computing system for providing sentiment analysis of claim 12, wherein:
generating the plurality of phrases comprises:
removing one or more of single-letter words, two-letter words, words on a pre-defined list, punctuation, or numbers from each of the plurality of comments to form sets of remaining words for each of the plurality of comments; and
lemmatizing the sets of remaining words for each of the plurality of comments to generate the plurality of phrases.

### Claim 14 (depends on 8)

The computing system for providing sentiment analysis of claim 8, wherein the instructions further cause the processor to:
extract the phrase from the text string by removing one or more of single-letter words, two-letter words, words on a pre-defined list, punctuation, or numbers from the text string; and
lemmatize any remaining words of the phrase prior to determining the polarity of the sentiment of the phrase.

### Claim 15

A non-transitory computer-readable medium having instructions stored thereon that, when executed, cause a computing device to:
train the computer system to identify a polarity of a sentiment for a plurality of phrases;
receive an input from the web site, the input comprising a text string including a phrase;
determine the polarity of the sentiment of the phrase by comparing the phrase to the plurality of phrases; and
send a command to the website that causes the website to display predetermined content based on the determined polarity of the sentiment of the phrase.

### Claim 16 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the instructions are further configured to cause the computing device to:
translate the text string into a different language prior to determining the polarity of the sentiment of the phrase.

### Claim 17 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein:
training the computer system comprises:
classifying each of a plurality of comments as being positive or negative based on scores associated with each of the plurality of comments;
generating the plurality of phrases from the plurality of comments; and
assigning each of the plurality of phrases the polarity of the sentiment based at least in part on the scores associated with each of the plurality of comments.

### Claim 18 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein:
generating the plurality of phrases comprises:
removing one or more of single-letter words, two-letter words, words on a pre-defined list, punctuation, or numbers from each of the plurality of comments to form sets of remaining words for each of the plurality of comments; and
lemmatizing the sets of remaining words for each of the plurality of comments to generate the plurality of phrases.

### Claim 19 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the instructions further cause the computing device to:
extract the phrase from the text string by removing one or more of single-letter words, two-letter words, words on a pre-defined list, punctuation, or numbers from the text string; and
lemmatize any remaining words of the phrase prior to determining the polarity of the sentiment of the phrase.

### Claim 20 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein:
the predetermined content comprises one or more of a textual response to the phrase or a color being displayed around the input, the color being selected based on the polarity of the sentiment of the phrase.
