Large-scale sentiment analysis

• US 7,996,210 B2
• Filed: 04/24/2007
• Issued: 08/09/2011
• Est. Priority Date: 04/24/2007
• Status: Active Grant

• Current Assignee: The Research Foundation for The State University of New York (State University of New York)
• Original Assignee: The Research Foundation for The State University of New York (State University of New York)
• Inventors: Godbole, Namrata, Srinivasaiah, Manjunath, Skiena, Steven
• Primary Examiner(s): Hudspeth; David R
• Assistant Examiner(s): Spooner; Lamont M
• Application Number:
  US11/739,187
• Publication Number:
  US 20080270116A1
• Time in Patent Office: 1,568 Days
• Field of Search: 704/1, 704/9, 704/10, 715/255, 715/256, 715/259, 707706-708
• US Class Current: 704/9
• CPC Class Codes: G06F 40/10 Text processing natural language analysis G06F40/20; semantic analysis G06F40/30; processing or translation of natural language G06F40/40
• CPC Class Codes: G06F 40/35 Discourse or dialogue representation

Abstract

A method for determining a sentiment associated with an entity includes inputting a plurality of texts associated with the entity, labeling seed words in the plurality of texts as positive or negative, determining a score estimate for the plurality of words based on the labeling, re-enumerating paths of the plurality of words and determining a number of sentiment alternations, determining a final score for the plurality of words using only paths whose number of alternations is within a threshold, converting the final scores to corresponding z-scores for each of the plurality of words, and outputting the sentiment associated with the entity.

Claims

1. A computer readable medium embodying instructions executable by a processor to perform a method for determining a sentiment lexicon associated with an entity, the method steps comprising:

inputting a plurality of texts associated with the entity;

labeling seed words in the plurality of texts as positive or negative;

determining a score estimate for the plurality of words based on the labeling;

re-enumerating paths of the plurality of words and determining a number of sentiment alternations;

determining a final score for the plurality of words using only paths whose number of alternations is within a threshold;

converting the final scores to corresponding s-scores for each of the plurality of words; and

outputting the sentiment lexicon associated with the entity.

2. The method of claim 1, further comprising:

determining synonyms and antonyms of the plurality of words;

ordering the synonyms and the antonyms of the plurality of words by sense; and

adding a set of the synonyms and the antonyms to the seed words, wherein the set is limited by a threshold prior to the converting of the final scores.

3. The method of claim 1, further comprising discarding ambiguous words of the plurality of words.

4. The method of claim 1, wherein the re-enumeration is independent of how the sentiment lexicon is used.

5. The method of claim 1, wherein the entity is a document.

6. The method of claim 1, wherein the entity is a relationship between component entities.

7. The method of claim 1, wherein the entity is a group of component entities.