# US 8,280,885 B2 · System and method for automatically summarizing fine-grained opinions in digital text

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

- Number: US 8,280,885 B2
- Document ID: US8280885B2
- Status: Granted
- Kind: B2
- Application number: 11/927,456
- Filed: 2007-10-29
- Published: 2009-04-30
- Granted: 2012-10-02
- Earliest claimed: 2007-10-29
- Assignees: Cornell University; Cornell Center for Technology, Enterprise & Commercialization
- Inventors: Claire Cardie; Veselin Stoyanov; Yejin Choi; Eric Breck
- Web page: https://patentgrep.com/patent/US8280885B2

## CPC

- G06F 16/345: {Summarisation for human users}
- G06F 16/38: Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F 16/93: Document management systems
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A method and system for automatically summarizing fine-grained opinions in digital text are disclosed. Accordingly, a digital text is analyzed for the purpose of extracting all opinion expressions found in the text. Next, the extracted opinion expressions (referred to herein as opinion frames) are analyzed to generate opinion summaries. In forming an opinion summary, those opinion frames sharing in common an opinion source and/or opinion topic may be combined, such that an overall opinion summary indicates an aggregate opinion held by the common source toward the common topic.

## Claims

### Claim 1

A computer-implemented method, using a processor, for generating an opinion summary from a document, said method comprising:
using at least one of syntactic analysis, semantic analysis and discourse analysis to assist in automatically extracting a plurality of opinion expressions from the document using the processor, each opinion expression identified by a grammatical element and associated with an opinion source, opinion topic, opinion polarity and opinion strength, wherein for each opinion expression the opinion source is at least one person or entity to which such opinion expression is to be attributed and wherein the document includes opinion expressions from a plurality of opinion sources;
identifying those opinion expressions that share a common opinion source and a common opinion topic using the processor; and
combining the opinion polarities and opinion strengths of those opinion expressions that share a common opinion source to form an overall opinion summary with one aggregate opinion frame for each common opinion source-topic pairing.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein identifying those opinion expressions that share a common opinion source includes identifying those opinion expressions that have a common real-world opinion source expressed in the document with different language.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, wherein identifying those opinion expressions that share a common opinion topic includes identifying those opinion expressions that have a common real-world opinion topic expressed in the document with different language.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, further comprising:
for those opinion expressions that share a common opinion source and common opinion topic, generating an overall opinion summary having opinion polarities and opinion strengths based on averaging those opinion polarities of the opinion expressions that share the common opinion source and common opinion topic, wherein the averaging takes into consideration the opinion strength associated with each opinion polarity.

### Claim 5 (depends on 1)

The computer-implemented method of claim 1, further comprising:
for those opinion expressions that share a common opinion source and a common opinion topic, generating an overall opinion summary having an opinion polarity and opinion strength based on the opinion polarity and opinion strength of the opinion expression identified as having the most extreme opinion polarity and opinion strength of the opinion expressions that share a common opinion source and common opinion topic.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, further comprising:
for those opinion expressions that share a common opinion source and a common opinion topic, generating an overall opinion summary which indicates whether there is a conflict between any two opinion polarities of any two opinion expressions that share a common opinion source and common opinion topic.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1, wherein each opinion expression is associated with an author of the document in which the opinion expression is located.

### Claim 8 (depends on 1)

The computer-implemented method of claim 1, wherein each opinion expression is associated with a publisher of the document in which the opinion expression is located.

### Claim 9 (depends on 1)

The computer-implemented method of claim 1, wherein the grammatical element is at least one of a word, a plurality of words, and a phrase.

### Claim 10 (depends on 1)

The computer-implemented method of claim 1, further comprising:
for those opinion expressions that share a common opinion source, generating an overall opinion summary having opinion polarities and opinion strengths based on averaging those opinion polarities of the opinion expressions that share the common opinion source, wherein the averaging takes into consideration the opinion strength associated with each opinion polarity.

### Claim 11 (depends on 1)

The computer-implemented method of claim 1, further comprising:
for those opinion expressions that share a common opinion source, generating an overall opinion summary having an opinion polarity and opinion strength based on the opinion polarity and opinion strength of the opinion expression identified as having the most extreme opinion polarity and opinion strength of the opinion expressions that share a common opinion source.

### Claim 12 (depends on 1)

The computer-implemented method of claim 1, further comprising:
for those opinion expressions that share a common opinion source, generating an overall opinion summary which indicates whether there is a conflict between any two opinion polarities of any two opinion expressions that share a common opinion source.

### Claim 13 (depends on 1)

The computer-implemented method of claim 1, further comprising:
for each overall opinion summary associated with a unique opinion source, determining the number of positive opinion expressions and/or negative opinion expressions associated with the unique opinion source.

### Claim 14 (depends on 1)

The computer-implemented method of claim 1, further comprising:
for each overall opinion summary associated with a unique opinion source, determining the percentage of positive opinion expressions and/or negative opinion expressions associated with the unique opinion source.

### Claim 15 (depends on 1)

The computer-implemented method of claim 1, wherein identifying and grouping those opinion expressions that share at least one of a common opinion source and a common opinion topic includes identifying those opinion expressions that have at least one of a common real-world opinion source and a common real-world opinion topic expressed in the document with different language.

### Claim 16 (depends on 1)

The computer-implemented method of claim 1, wherein identifying and grouping those opinion expressions that share at least one of a common opinion source and a common opinion topic includes identifying those opinion expressions that have a common real-world opinion topic expressed in the document with different language.

### Claim 17 (depends on 1)

The computer-implemented method of claim 1, further comprising:
for those opinion expressions that share a common opinion source and a common opinion topic, generating an overall opinion summary having an opinion polarity and opinion strength based on the opinion polarity and opinion strength of the opinion expression identified as having the highest opinion polarity and opinion strength of the opinion expressions that share a common opinion source and a common opinion topic.

### Claim 18

A computer-implemented method, using a processor, for generating an opinion summary from a document, said method comprising:
using at least one of syntactic analysis, semantic analysis and discourse analysis to assist in automatically extracting a plurality of opinion expressions from the document using the processor, each opinion expression identified by a grammatical element and associated with an opinion source, opinion topic, opinion polarity and opinion strength, wherein for each opinion expression the opinion source is at least one person or entity to which such opinion expression is to be attributed and wherein the document includes opinion expressions from a plurality of opinion sources;
organizing the plurality of opinion expressions into data fields, including an opinion source field, using the processor;
identifying those opinion expressions that share a common opinion topic using the processor; and
combining the opinion polarities and opinion strengths of those opinion expressions that share a common opinion topic to form an overall opinion summary with one aggregate opinion frame for each unique opinion topic.

### Claim 19 (depends on 18)

The computer-implemented method of claim 18, wherein identifying those opinion expressions that share a common opinion topic includes identifying those opinion expressions that have a common real-world opinion topic expressed in the document with different language.

### Claim 20 (depends on 18)

The computer-implemented method of claim 18, further comprising:
for those opinion expressions that share a common opinion topic, generating an overall opinion summary having opinion polarities and opinion strengths based on averaging those opinion polarities of the opinion expressions that share the common opinion topic, wherein the averaging takes into consideration the opinion strength associated with each opinion polarity.

### Claim 21 (depends on 18)

The computer-implemented method of claim 18, further comprising:
for those opinion expressions that share a common opinion topic, generating an overall opinion summary having an opinion polarity and opinion strength based on the opinion polarity and opinion strength of the opinion expression identified as having the most extreme opinion polarity and opinion strength of the opinion expressions that share a common opinion topic.

### Claim 22 (depends on 18)

The computer-implemented method of claim 18, further comprising:
for those opinion expressions that share a common opinion topic, generating an overall opinion summary which indicates whether there is a conflict between any two opinion polarities of any two opinion expressions that share a common opinion topic.

### Claim 23 (depends on 18)

The computer-implemented method of claim 18, further comprising:
for each overall opinion summary associated with a unique topic, determining the number of positive opinion expressions and/or negative opinion expressions directed toward the unique topic.

### Claim 24 (depends on 18)

The computer-implemented method of claim 18, further comprising:
for each overall opinion summary associated with a unique topic, determining the percentage of positive opinion expressions and/or negative opinion expressions directed toward the unique topic.

### Claim 25

A computer program product used with a processor, the computer program product comprising:
a computer-readable medium including computer readable program code stored therein used when generating an opinion summary from a document, the computer-readable medium including:
computer readable program code that uses when processed by the processor at least one of syntactic analysis, semantic analysis and discourse analysis to assist in automatically extracting a plurality of opinion expressions from the document, each opinion expression identified by a grammatical element and associated with an opinion source, opinion topic, opinion polarity and opinion strength, wherein for each opinion expression the opinion source is at least one person or entity to which such opinion expression is to be attributed and wherein the document includes opinion expressions from a plurality of opinion sources;
computer readable program code that identifies and groups those opinion expressions that share a common opinion source and a common opinion topic; and
computer readable program code that combines the opinion polarities and opinion strengths of those opinion expressions that share a common opinion source to form an overall opinion summary with one aggregate opinion frame for each common opinion source-topic pairing.

### Claim 26

A computer-implemented method, using a processor, for generating an opinion summary from a plurality of documents, said method comprising:
using at least one of syntactic analysis, semantic analysis and discourse analysis to assist in automatically extracting at least one opinion expression from each of the plurality of documents using the processor, each opinion expression identified by a grammatical element and associated with an opinion source, opinion topic, opinion polarity and opinion strength, wherein for each opinion expression the opinion source is at least one person or entity to which such opinion expression is to be attributed and wherein each document includes opinion expressions from a plurality of opinion sources;
identifying those opinion expressions that share a common opinion source and a common opinion topic using the processor; and
combining the opinion polarities and opinion strengths of those opinion expressions that share a common opinion source to form an overall opinion summary with one aggregate opinion frame for each common opinion source-topic pairing.

### Claim 27 (depends on 26)

The computer-implemented method of claim 26, wherein identifying those opinion expressions that share a common opinion source includes identifying those opinion expressions that have a common real-world opinion source expressed in the document with different language.

### Claim 28 (depends on 26)

The computer-implemented method of claim 26, further comprising:
for those opinion expressions that share a common opinion source and a common opinion topic, generating an overall opinion summary having opinion polarities and opinion strengths based on averaging those opinion polarities of the opinion expressions that share the common opinion source and common opinion topic, wherein the averaging takes into consideration the opinion strength associated with each opinion polarity.

### Claim 29 (depends on 26)

The computer-implemented method of claim 26, further comprising:
for those opinion expressions that share a common opinion source and a common opinion topic, generating an overall opinion summary which indicates whether there is a conflict between any two opinion polarities of any two opinion expressions that share a common opinion source and opinion topic.

### Claim 30 (depends on 26)

The computer-implemented method of claim 26, further comprising:
for each overall opinion summary associated with a unique opinion source, determining the number of positive opinion expressions and/or negative opinion expressions associated with the unique opinion source.

### Claim 31 (depends on 26)

The computer-implemented method of claim 26, further comprising:
for each overall opinion summary associated with a unique opinion source, determining the percentage of positive opinion expressions and/or negative opinion expressions associated with the unique opinion source.
