SENTIMENT ANALYSIS BASED ON DEMOGRAPHIC ANALYSIS

• US 20140214408A1
• Filed: 03/27/2014
• Published: 07/31/2014
• Est. Priority Date: 11/13/2012
• Status: Abandoned Application

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Bhatt, Dhruv A.
• Application Number:
  US14/227,983
• Publication Number:
  US 20140214408A1
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G06F 16/353 into predefined classes
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0282 Rating or review of business operators or products

Abstract

A method, apparatus and article of manufacture for analyzing product or service reviews is disclosed. In one embodiment, the method comprises the steps of performing a demographic text analysis on a product or service review generated by a reviewer, wherein the demographic text analysis examines the product or service review to determine demographic information of the reviewer. A sentiment text analysis is performed on the product or service review, wherein the sentiment text analysis examines the product or service review to determine a sentiment of the product or service review. The sentiment of the product or service review is categorized based on the demographic information of the reviewer.

Claims

1. A computer implemented method for analyzing a product or service review, comprising:

performing, on one or more computers, a demographic text analysis on a review generated by a reviewer, wherein the demographic text analysis examines the review to determine demographic information of the reviewer;

performing, on one or more computers, a sentiment text analysis on the review, wherein the sentiment text analysis examines the review to determine a sentiment of the review; and

categorizing, on one or more computers, the sentiment of the review based on the demographic information of the reviewer.

2. The method of claim 1, further comprising generating a report of the sentiment of a plurality of reviews categorized by the demographic information of the reviewers.

3. The method of claim 1, wherein the demographic information is an age range.

4. The method of claim 1, wherein the demographic information is one of a gender, race, age, disability, mobility, home ownership, employment status, and location.

5. The method of claim 1, wherein the sentiment is a positive sentiment.

6. The method of claim 1, wherein the sentiment is a negative sentiment.

7. The method of claim 1, wherein the demographic text analysis and sentiment text analysis utilize an Unstructured Information Management Architecture (UIMA) dictionary and parsing rules to examine the product review.