SENTIMENT CUBE

• US 20120197950A1
• Filed: 01/30/2011
• Published: 08/02/2012
• Est. Priority Date: 01/30/2011
• Status: Active Grant

• Current Assignee: Valtrus Innovations Limited (f/k/a Dolya Holdco 9 Limited) (Key Patent Innovations Limited)
• Original Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Inventors: Dayal, Umeshwar, Castellanos, Maria G., Gupta, Chetan Kumar, Wang, Song, Hsu, Meichun
• Granted Patent: US 8,725,781 B2
• Time in Patent Office: Days
• US Class Current: 707/822
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

A sentiment cube system is disclosed. In one example, the system discloses a sentiment storage, including a sentiment cube data structure having a set of cells arranged by a set of dimensions. The system includes a computer programmed with executable instructions which operate a set of modules, wherein the modules comprise: a sentiment storage module which receives sentiment values associated with a set of entity features, and then populates a hierarchy of the cells in the sentiment cube with the sentiment values. A sentiment analysis module effecting a set of operations on the sentiment cube.

Claims

1. A sentiment cube system, comprising:

a sentiment storage, including a sentiment cube data structure having a set of cells arranged by a set of dimensions; and

a computer programmed with executable instructions which operate a set of modules, wherein the modules comprise;

a sentiment storage module for;

receiving sentiment values associated with a set of entity features; and

populating a hierarchy of the cells in the sentiment cube with the sentiment values; and

a sentiment analysis module for effecting a set of operations on the sentiment cube.

2. The system of claim 1:

wherein the cells are arranged into an N-dimensional data structure, where N is any integer.

3. The system of claim 1:

wherein the entity is one from a group including;

a product, a service, and a subject; and

wherein the feature is a sub-set of the entity.

4. The system of claim 1:

wherein the dimensions include a metadata dimension defined by metadata associated with information sources from which the sentiment values are derived.

5. The system of claim 1:

wherein the dimensions include a feature dimension derived from the entity features.

6. The system of claim 1:

wherein the dimensions include a Document Object Model (DOM) dimension derived from an information source hierarchy from which the sentiment values are derived.

7. The system of claim 6:

wherein the information source is a text document and the DOM dimension is defined as at least one from a group including;

a section, a chapter, a paragraph, a sentence, a clause, and a phrase.

8. The system of claim 1:

wherein the sentiment cube data structure is modeled as;

9. The system of claim 1:

wherein the sentiment cube implemented in a database includes;

a fact table defined as;

10. A system, comprising:

a sentiment storage, including a sentiment cube data structure having a set of cells populated with sentiment values and arranged by a set of hierarchical dimensions; and

a computer programmed with executable instructions which operate a set of modules comprising;

a sentiment analysis module for effecting a set of operations on the sentiment cube which access and aggregate sentiment values.

11. The system of claim 10:

wherein the sentiment analysis module selects a set of hierarchically disconnected cells; and

wherein the operations include a roll-up operation which aggregates sentiment values from the hierarchically disconnected cells according to a user defined aggregation function.

12. The system of claim 10:

wherein the set of hierarchical dimensions include at least one from a group including;

a metadata dimension, a feature dimension, and a document object model dimension; and

wherein the operations perform a roll-up aggregation along the set of hierarchical dimensions.

13. The system of claim 10:

wherein a roll-up aggregation on the sentiment cube is defined as;

Roll-up (sentiment_cube, [{dimension}, {aggregation function}])

wherein;

sentiment_cube;

specifies the sentiment cube on which the roll-up is performed;

dimension;

specifies one or more dimensions on which sentiment value aggregation is performed, and up to which levels in a corresponding feature hierarchy; and

aggregation function;

specifies an aggregation function for the roll-up.

14. An article comprising at least one computer-readable storage medium storing instructions that upon execution cause a computer system to:

arranging cells in a sentiment cube in a feature hierarchy;

populating the cells with sentiment values; and

correlating sentiment values from a first cell and a second cell in the sentiment cube based upon an equality operator.

15. The instructions of claim 14:

wherein the equality operator permits the sentiment value in the first cell to be correlated with the sentiment value in the second cell if the second cell is at-most a k^th hierarchical ancestor of the first cell, where k is an integer.

16. The instructions of claim 14:

wherein the equality operator permits the sentiment value in the first cell to be correlated with the sentiment value in the second cell if the second cell exists in a sub-tree rooted at a k^th hierarchical ancestor of first cell, where k is an integer.

17. The instructions of claim 14:

wherein the equality operator permits the sentiment value in the first cell to be correlated with the sentiment value in the second cell if the second cell is one of a k^th hierarchical descendents of the first cell, where k is an integer.

18. The instructions of claim 14:

wherein the equality operator permits the sentiment value in the first cell to be correlated with the sentiment value in the second cell if the second cell is contained in a sub-tree rooted at one of a k^th hierarchical descendents of the first cell, where k is an integer.