OBJECTIVE-FUNCTION BASED SENTIMENT

• US 20120197903A1
• Filed: 01/31/2011
• Published: 08/02/2012
• Est. Priority Date: 01/31/2011
• 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: Lu, Yue, Castellanos, Maria G., Dayal, Umeshwar
• Granted Patent: US 8,949,211 B2
• Time in Patent Office: Days
• US Class Current: 707/748
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

A system and article are disclosed for objective-function based sentiment. In one example, the system includes a set of domain information, and a computer programmed with executable instructions which operate a set of modules. The modules include a sentiment polarization module for identifying a domain-aspect opinion-word pair within a set of domain data, and assigning a sentiment polarity score to the domain-aspect opinion-word pair based on an objective function which includes sentiment data from the domain information.

Claims

1. A system, comprising:

a set of domain information; and

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

a sentiment polarization module for;

identifying a domain-aspect opinion-word pair within a set of domain data; and

assigning a sentiment polarity score to the domain-aspect opinion-word pair based on an objective function which includes sentiment data from the domain information.

2. The system of claim 1:

wherein the domain information includes;

a set of domain-independent information; and

a set of domain-dependent information; and

wherein assigning further includes, assigning the sentiment polarity score based on the domain-independent information and domain-dependent information.

3. The system of claim 1:

wherein the objective function is optimized using a set of constraints associated with the domain information.

4. The system of claim 3:

wherein one of the constraints ensures that the sentiment polarity score is positively correlated with an overall sentiment rating associated with the set of domain data.

5. The system of claim 3:

wherein one of the constraints ensures that the sentiment polarity score is close to another sentiment polarity score assigned by a domain-independent sentiment lexicon associated with the domain information.

6. The system of claim 3:

wherein one of the constraints ensures that a first sentiment polarity score assigned to a first domain-aspect opinion-word pair is same as a second sentiment polarity score assigned to a second domain-aspect opinion-word pair, if the first opinion-word is synonymous with the second opinion-word.

7. The system of claim 3:

wherein one of the constraints ensures that a first sentiment polarity score assigned to a first domain-aspect opinion-word pair is different from a second sentiment polarity score assigned to a second domain-aspect opinion-word pair, if the first opinion-word is an antonym of the second opinion-word.

8. The system of claim 3:

wherein the objective function includes constraints having weighting parameters set based on a trust-level of each constraint.

9. A sentiment polarity system comprising:

a set of domain information; and

a sentiment polarization module for;

identifying a first domain-aspect opinion-word pair within a first set of domain data;

assigning a first sentiment polarity score to the domain-aspect opinion-word pair based on an objective function which includes sentiment data from the set of domain information;

populating a domain-dependent sentiment lexicon with the first domain-aspect opinion-word pair and the first sentiment polarity score; and

assigning a second sentiment polarity score to a second domain-aspect opinion-word pair within a second set of domain data based on the domain-dependent sentiment lexicon.

10. The system of claim 9:

wherein the sentiment polarity score is one from a group including;

a set of opinion states;

positive and negative;

a opinion range;

a score, 0-100; and

a rational number.

11. The system of claim 9:

wherein the domain data is one from a group including;

a document;

a file;

a clause;

a set of information;

a product review, a service quality;

customer feedback;

user opinions;

performance data;

cloud service data;

a topic;

opinionated review text;

opinions; and

a subject.

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

identify a domain-aspect opinion-word pair within a set of domain data; and

assign a sentiment polarity score to the domain-aspect opinion-word pair based on an objective function which includes sentiment data from a set of domain-independent information and a set of domain-dependent information.

13. The system of claim 12:

wherein the domain-independent information is one from a group including;

a domain-independent sentiment lexicon;

a dictionary;

a synonym dictionary;

an antonym dictionary;

a thesaurus;

a set of language clues;

an “

and”

language clue;

a “

but”

language clue; and

a “

negation”

language clue.

14. The system of claim 12:

wherein the domain-dependent information is one from a group including;

a domain-dependent sentiment lexicon;

domain-aspects;

word-clusters;

an overall sentiment ratings; and

a document-level overall sentiment rating.

15. The identify instructions of claim 12, further comprising:

parsing the set of domain data into a set of sentence clauses;

tagging each clause with a domain-aspect having a word-cluster which overlaps with words in the clause; and

identifying opinion-words within the clauses.