System and method for automatically summarizing fine-grained opinions in digital text

Inactive Publication Date: 2015-11-19
CORNELL UNIVERSITY
View PDF2 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

This patent text describes a system and method for automatically summarizing fine-grained opinions in digital text. The system analyzes digital content to identify expressions of opinions, which are then stored as data structures called opinion frames. These frames have different components parts that make up the overall opinion, such as the source, trigger, topic, polarity, and strength. Overall opinion summaries are formed by combining multiple opinion frames that share in common a source and topic, averaging their polarities, and linking or associating frames that share in common an opinion source and topic. This system can provide a faster and more efficient way to summarize complex opinions in digital text, making it easier to understand and analyze.

Problems solved by technology

While readers tend to naturally process subjective language when reading, automating the process to summarize and present opinions expressed in documents is a challenge.
The coarse-grained opinion analysis approach can be problematic for a number of reasons.
Consequently, expressing an overall summary at the document level, and attributing the opinion to one source (e.g., the author of the article) fails to recognize the existence of multiple opinion sources in a single article.
For instance, a news article dealing with one or more political issues may express the differing opinions of two opposing politicians, thereby making it difficult to express the overall sentiment of the article in a single summary statement.
Furthermore, expressing an overall opinion summary at the document level fails to recognize that the article may include a variety of opinion expressions on different topics.
Therefore, expressing an overall opinion summary at the document level in a single opinion statement fails to reflect the various opinions on the different political issues.
Consequently, the type and quality of information extracted from documents with course-grained opinion analysis will not enable the types of rich querying applications described above.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • System and method for automatically summarizing fine-grained opinions in digital text
  • System and method for automatically summarizing fine-grained opinions in digital text
  • System and method for automatically summarizing fine-grained opinions in digital text

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0013]An apparatus and method for identifying, extracting, summarizing, and presenting opinions from digital text (documents) are disclosed. For example, a digital text (e.g., an article, blog posting, product review, and / or email) is analyzed to extract opinion expressions. In this context, an opinion expression is simply a phrase, clause, sentence or some combination within the digital text being analyzed that expresses an opinion. The component parts of each opinion expression identified in a document are organized into several data fields of a data structure referred to herein as an opinion frame. Accordingly, each opinion frame includes five data fields—one data field each for the 1) opinion source (e.g., the opinion holder), 2) the opinion target (e.g., the topic, subject, or idea of the opinion), 3) the opinion polarity (e.g., positive, neutral, negative), 4) the opinion strength or intensity (e.g., low, mild, extreme), and 5) the opinion trigger (e.g., the word, words, or ph...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

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.

Description

CROSS REFERENCE TO RELATED APPLICATIONS[0001]The present application is a continuation of U.S. Non-Provisional application Ser. No. 13 / 629,004 filed 27 Sep. 2012; which is a continuation of U.S. Non-Provisional application Ser. No. 11 / 927,456 filed 29 Oct. 2007, issued as U.S. Pat. No. 8,280,885 on 2 Oct. 2012; each of which is incorporated herein by reference in its entirety for all purposes.TECHNICAL FIELD[0002]The invention generally relates to computer-implemented opinion analysis.BACKGROUND[0003]Opinion analysis is concerned with extracting attitudes, beliefs, emotions, opinions, evaluations, and sentiment from digital texts. Opinion analysis has received much research attention lately, motivated by the desire to provide information analysis applications in the arenas of government, business, and politics. The types of applications desired include question answering (QA) applications, for example, that enable complex querying of the form, “How does entity X feel about topic Y?”...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06F17/30G06F17/27G06F40/00
CPCG06F17/30719G06F17/27G06F17/30011G06F16/345G06F16/38G06F16/93
InventorCARDIE, CLAIRESTOYANOV, VASELINBRECK, ERICCHOI, YEJIN
OwnerCORNELL UNIVERSITY