Method and system for implementing author profiling

US 9,607,340 B2
Filed: 03/12/2013
Issued: 03/28/2017
Est. Priority Date: 03/12/2013
Status: Active Grant

First Claim

Patent Images

1. A computer implemented method for analyzing author data, comprising:

receiving writings created by a plurality of authors;

performing a semantic analysis upon the writings;

generating a plurality of author profiles for the writings using results from the semantic analysis, the plurality of author profiles respectively identifying topics of interest to the plurality of authors, and groups of authors being identified from one or more of the topics of interest;

identifying a first group of multiple authors that corresponds to a first topical subject and multiple author profiles for the multiple authors, the first group of multiple authors identified from the groups and corresponding to the multiple author profiles identified from the plurality of author profiles;

identifying a second topical subject shared among at least some authors of the multiple authors in the first group at least by performing a correlation analysis that analyzes at least some author profiles in the multiple author profiles of the at least some authors;

identifying a second group of authors from the plurality of authors that exhibit affinity for the second topical subject at least by identifying author vectors corresponding to the second group of authors with respect to the second topical subject; and

correlating the first group of multiple authors with the second group of authors in response to the identification of the second topical subject, wherein the writings are received from the plurality of authors without targeting specific groups of authors;

classifying the writings into a plurality of classes based in part or in whole upon topics of interests determined by the semantic analysis, classifying the writing including;

creating a set of themes from results of the semantic analysis;

analyzing the set of themes created from the results of the semantic analysis;

determining subjects of the topics of interest based in part or in whole upon the set of themes;

determining similarity among the subjects of the topics of interest at least by analyzing the plurality of author profiles;

clustering the topics of interests into the plurality of classes based in part or in whole upon the similarity among the subjects;

determining respective strength numbers for the plurality of authors, a strength number for a user indicating relative affinity of the user to a category relative to one or more remaining categories;

associating the respective strength numbers that correspond to the plurality of authors with a plurality of categories;

creating a vector for each author of the plurality of authors, wherein vectors for the plurality of authors indicate respective affinities among the plurality of authors to one or more common topics of interests or one or more subjects;

establishing an author profile for the each author by using the vector for the each author;

storing the author profile for the author in the plurality of author profiles;

reducing noise in the writings at least by performing a semantic filtering process;

improving accuracy of the plurality of classes from classifying the writings at least by reducing false positives, false negatives, and inappropriate contents with the semantic filtering process;

identifying an actionable data based in part or in whole upon results of the semantic analysis, wherein the writings created by the plurality of authors include contents transcribed from non-social data;

determining, at a rule and workflow module stored at least partially in memory, the plurality of computing systems to receive the actionable data based in part or in whole upon a set of rules that identifies how the actionable data is to be handled and directed;

performing the semantic analysis upon the writings at least by performing a statistical language modeling;

performing the semantic analysis upon the writings at least by performing a latent semantic analysis;

preconfiguring a plurality of types of topics of interest;

determining a first set of authors that corresponds to the one or more first types of topics of interest at least by analyzing the plurality of author profiles to identify a first set of author profiles corresponding to the first set of authors;

determining commonality of one or more second types of topics of interest without pre-defining the one or more second types of topics of interest;

identifying commonality among the plurality of writings in response to the one or more second types of topics of interest based in part or in whole upon results of the semantic analysis;

identifying a group of authors that corresponds to a first affinity for a first subject;

determining a second affinity and a third affinity shared by at least a threshold percentage of authors of the group of authors at least by analyzing a set of author profiles corresponding to the group of authors and by performing one or more first correlation analyses, wherein the second affinity and the third affinity are not known or expected in advance;

generating correlation data based in part or in whole upon results of determining the second affinity and the third affinity;

generating an action for the group of authors based on the second affinity and the third affinity;

receiving the writings created by the plurality of authors without targeting one or more specific groups of authors;

generating the plurality of author profiles for the writings based in part or in whole upon respective strength numbers for the plurality of authors;

identifying a plurality of themes from the writings based in part or in whole upon results of the semantic analysis and results of classifying the writings;

performing a themes analysis;

generating the plurality of author profiles for the writing based in part or in whole upon the plurality of themes;

determining a first set of actionable data for the plurality of authors based in part or in whole upon results of correlating an at least one group with the authors;

identifying a set of rules from a rulebase;

dispatching, at a rules and workflow engine, actionable data for the plurality of authors to a plurality of computing systems based in part or in whole upon the set of rules, wherein a rule provides how the actionable data is to be dispatched;

determining, at a computer system, contextual and semantic significance in the writings at least by performing classification and filtering on the writings of the plurality of authors;

identifying specific themes within the writings based in part or in whole upon topics and subjects revealed from the semantic analysis and the classification;

performing categorization on the topics and the subjects of the writings to create a number of categories;

associating a set of strength numbers with the number of categories, a strength number indicating relative affinity of each author of the plurality of authors to a particular topic, a particular subject, or a particular theme; and

defining a vector for the each author using at least the set of strength numbers and the number of categories, a vector establishing an author profile for a specific author and being used to describe and analyze the specific author with respect to one or more affinities of the specific author.

View all claims

1 Assignment

Timeline View

Assignment View

0 Petitions

Accused Products

Abstract

Disclosed is an improved method, system, and computer program product for analyzing interests of consumers, where semantic analysis is performed on writings by authors on social media sites. The results of the semantic analysis provide a profile of the authors. These author profiles can be used to identify and correlate topical interests by consumers. An enterprise or business can more effectively market to the consumers based upon this knowledge of the consumers'"'"' interests.

32 Citations

29 Claims

1. A computer implemented method for analyzing author data, comprising:
- receiving writings created by a plurality of authors;
  
  performing a semantic analysis upon the writings;
  
  generating a plurality of author profiles for the writings using results from the semantic analysis, the plurality of author profiles respectively identifying topics of interest to the plurality of authors, and groups of authors being identified from one or more of the topics of interest;
  
  identifying a first group of multiple authors that corresponds to a first topical subject and multiple author profiles for the multiple authors, the first group of multiple authors identified from the groups and corresponding to the multiple author profiles identified from the plurality of author profiles;
  
  identifying a second topical subject shared among at least some authors of the multiple authors in the first group at least by performing a correlation analysis that analyzes at least some author profiles in the multiple author profiles of the at least some authors;
  
  identifying a second group of authors from the plurality of authors that exhibit affinity for the second topical subject at least by identifying author vectors corresponding to the second group of authors with respect to the second topical subject; and
  
  correlating the first group of multiple authors with the second group of authors in response to the identification of the second topical subject, wherein the writings are received from the plurality of authors without targeting specific groups of authors;
  
  classifying the writings into a plurality of classes based in part or in whole upon topics of interests determined by the semantic analysis, classifying the writing including;
  
  creating a set of themes from results of the semantic analysis;
  
  analyzing the set of themes created from the results of the semantic analysis;
  
  determining subjects of the topics of interest based in part or in whole upon the set of themes;
  
  determining similarity among the subjects of the topics of interest at least by analyzing the plurality of author profiles;
  
  clustering the topics of interests into the plurality of classes based in part or in whole upon the similarity among the subjects;
  
  determining respective strength numbers for the plurality of authors, a strength number for a user indicating relative affinity of the user to a category relative to one or more remaining categories;
  
  associating the respective strength numbers that correspond to the plurality of authors with a plurality of categories;
  
  creating a vector for each author of the plurality of authors, wherein vectors for the plurality of authors indicate respective affinities among the plurality of authors to one or more common topics of interests or one or more subjects;
  
  establishing an author profile for the each author by using the vector for the each author;
  
  storing the author profile for the author in the plurality of author profiles;
  
  reducing noise in the writings at least by performing a semantic filtering process;
  
  improving accuracy of the plurality of classes from classifying the writings at least by reducing false positives, false negatives, and inappropriate contents with the semantic filtering process;
  
  identifying an actionable data based in part or in whole upon results of the semantic analysis, wherein the writings created by the plurality of authors include contents transcribed from non-social data;
  
  determining, at a rule and workflow module stored at least partially in memory, the plurality of computing systems to receive the actionable data based in part or in whole upon a set of rules that identifies how the actionable data is to be handled and directed;
  
  performing the semantic analysis upon the writings at least by performing a statistical language modeling;
  
  performing the semantic analysis upon the writings at least by performing a latent semantic analysis;
  
  preconfiguring a plurality of types of topics of interest;
  
  determining a first set of authors that corresponds to the one or more first types of topics of interest at least by analyzing the plurality of author profiles to identify a first set of author profiles corresponding to the first set of authors;
  
  determining commonality of one or more second types of topics of interest without pre-defining the one or more second types of topics of interest;
  
  identifying commonality among the plurality of writings in response to the one or more second types of topics of interest based in part or in whole upon results of the semantic analysis;
  
  identifying a group of authors that corresponds to a first affinity for a first subject;
  
  determining a second affinity and a third affinity shared by at least a threshold percentage of authors of the group of authors at least by analyzing a set of author profiles corresponding to the group of authors and by performing one or more first correlation analyses, wherein the second affinity and the third affinity are not known or expected in advance;
  
  generating correlation data based in part or in whole upon results of determining the second affinity and the third affinity;
  
  generating an action for the group of authors based on the second affinity and the third affinity;
  
  receiving the writings created by the plurality of authors without targeting one or more specific groups of authors;
  
  generating the plurality of author profiles for the writings based in part or in whole upon respective strength numbers for the plurality of authors;
  
  identifying a plurality of themes from the writings based in part or in whole upon results of the semantic analysis and results of classifying the writings;
  
  performing a themes analysis;
  
  generating the plurality of author profiles for the writing based in part or in whole upon the plurality of themes;
  
  determining a first set of actionable data for the plurality of authors based in part or in whole upon results of correlating an at least one group with the authors;
  
  identifying a set of rules from a rulebase;
  
  dispatching, at a rules and workflow engine, actionable data for the plurality of authors to a plurality of computing systems based in part or in whole upon the set of rules, wherein a rule provides how the actionable data is to be dispatched;
  
  determining, at a computer system, contextual and semantic significance in the writings at least by performing classification and filtering on the writings of the plurality of authors;
  
  identifying specific themes within the writings based in part or in whole upon topics and subjects revealed from the semantic analysis and the classification;
  
  performing categorization on the topics and the subjects of the writings to create a number of categories;
  
  associating a set of strength numbers with the number of categories, a strength number indicating relative affinity of each author of the plurality of authors to a particular topic, a particular subject, or a particular theme; and
  
  defining a vector for the each author using at least the set of strength numbers and the number of categories, a vector establishing an author profile for a specific author and being used to describe and analyze the specific author with respect to one or more affinities of the specific author.
- View Dependent Claims (2, 3, 4, 5, 6, 7)
- - 2. The method of claim 1, wherein an author profile comprises a vector comprising values for the topics of interest for an author, and the vector comprises strength numbers that correspond to an extent or degree of interest by the author for the topics of interest to the plurality of authors.
  - 3. The method of claim 1, in which the semantic analysis comprises a latent semantic analysis that analyzes contextual and semantic significance of terms that appear within the writings.
  - 4. The method of claim 1, wherein semantic filtering is performed to reduce irrelevant data.
  - 5. The method of claim 1, wherein multiple author profiles in the plurality of author profiles for multiple authors of the plurality of authors are correlated to identify commonality of interests.
  - 6. The method of claim 1, wherein actionable data is generated for a business using the plurality of author profiles, wherein the actionable data is supplied to an enterprise software system, and the enterprise software system comprises at least one of a customer relations management (“
    - CRM”
      
      ) application, an enterprise resource planning (“
      
      ERP”
      
      ) application, and a supply chain management application.
  - 7. The method of claim 1, wherein:
    - the writings are retrieved from a social media system and comprise social media data;
      
      an author profile comprises a vector comprising values for the topics of interest for an author and the vector comprises strength numbers that correspond to an extent or degree of interest by the author for the topics of interest to the plurality of authors;
      
      the semantic analysis comprises a latent semantic analysis that analyzes contextual and semantic significance of terms that appear within the writings;
      
      semantic filtering is performed to reduce irrelevant data;
      
      multiple author profiles of the plurality of author profiles for multiple authors of the plurality of authors are correlated to identify commonality of interests; and
      
      actionable data is generated for a business using the author profile and the actionable data is supplied to an enterprise software system comprising at least one of a customer relations management (“
      
      CRM”
      
      ) application, an enterprise resource planning (“
      
      ERP”
      
      ) application, and a supply chain management application.

8. A computer program product embodied on a computer readable non-transitory medium, the computer readable non-transitory medium having stored thereon a sequence of instructions which, when executed by a processor causes the processor to execute a method for analyzing author data, the method comprising:
- receiving writings created by a plurality of authors;
  
  performing a semantic analysis upon the writings;
  
  generating-a plurality of author profiles for the writings using results from the semantic analysis, the plurality of author profiles respectively identifying topics of interest to the plurality of authors;
  
  identifying groups of authors from one or more of the topics of interest;
  
  identifying a first group of multiple authors that corresponds to a first topical subject and multiple author profiles for the multiple authors, the first group of multiple authors identified from the groups and corresponding to the multiple author profiles identified from the plurality of author profiles;
  
  identifying a second topical subject shared among at least some authors of the multiple authors in the first group at least by performing a correlation analysis that analyzes at least some author profiles in the multiple author profiles of the at least some authors;
  
  identifying a second group of authors from the plurality of authors that exhibit affinity for the second topical subject at least by identifying author vectors corresponding to the second group of authors with respect to the second topical subject; and
  
  correlating the first group of multiple authors with the second group of authors in response to the identification of the second topical subject, wherein the writings are received from the plurality of authors without targeting specific groups of authors;
  
  classifying the writings into a plurality of classes based in part or in whole upon topics of interests determined by the semantic analysis, classifying the writing including;
  
  creating a set of themes from results of the semantic analysis;
  
  analyzing the set of themes created from the results of the semantic analysis;
  
  determining subjects of the topics of interest based in part or in whole upon the set of themes;
  
  determining similarity among the subjects of the topics of interest at least by analyzing the plurality of author profiles;
  
  clustering the topics of interests into the plurality of classes based in part or in whole upon the similarity among the subjects;
  
  determining respective strength numbers for the plurality of authors, a strength number for a user indicating relative affinity of the user to a category relative to one or more remaining categories;
  
  associating the respective strength numbers that correspond to the plurality of authors with a plurality of categories;
  
  creating a vector for each author of the plurality of authors, wherein vectors for the plurality of authors indicate respective affinities among the plurality of authors to one or more common topics of interests or one or more subjects;
  
  establishing an author profile for the each author by using the vector for the each author;
  
  storing the author profile for the author in the plurality of author profiles;
  
  reducing noise in the writings at least by performing a semantic filtering process;
  
  improving accuracy of the plurality of classes from classifying the writings at least by reducing false positives, false negatives, and inappropriate contents with the semantic filtering process;
  
  identifying an actionable data based in part or in whole upon results of the semantic analysis, wherein the writings created by the plurality of authors include contents transcribed from non-social data;
  
  determining, at a rule and workflow module stored at least partially in memory, the plurality of computing systems to receive the actionable data based in part or in whole upon a set of rules that identifies how the actionable data is to be handled and directed;
  
  performing the semantic analysis upon the writings at least by performing a statistical language modeling;
  
  performing the semantic analysis upon the writings at least by performing a latent semantic analysis;
  
  preconfiguring a plurality of types of topics of interest;
  
  determining a first set of authors that corresponds to the one or more first types of topics of interest at least by analyzing the plurality of author profiles to identify a first set of author profiles corresponding to the first set of authors;
  
  determining commonality of one or more second types of topics of interest without pre-defining the one or more second types of topics of interest;
  
  identifying commonality among the plurality of writings in response to the one or more second types of topics of interest based in part or in whole upon results of the semantic analysis;
  
  identifying a group of authors that corresponds to a first affinity for a first subject;
  
  determining a second affinity and a third affinity shared by at least a threshold percentage of authors of the group of authors at least by analyzing a set of author profiles corresponding to the group of authors and by performing one or more first correlation analyses, wherein the second affinity and the third affinity are not known or expected in advance;
  
  generating correlation data based in part or in whole upon results of determining the second affinity and the third affinity;
  
  generating an action for the group of authors based on the second affinity and the third affinity;
  
  receiving the writings created by the plurality of authors without targeting one or more specific groups of authors;
  
  generating the plurality of author profiles for the writings based in part or in whole upon respective strength numbers for the plurality of authors;
  
  identifying a plurality of themes from the writings based in part or in whole upon results of the semantic analysis and results of classifying the writings;
  
  performing a themes analysis;
  
  generating the plurality of author profiles for the writing based in part or in whole upon the plurality of themes;
  
  determining a first set of actionable data for the plurality of authors based in part or in whole upon results of correlating an at least one group with the authors;
  
  identifying a set of rules from a rulebase;
  
  dispatching, at a rules and workflow engine, actionable data for the plurality of authors to a plurality of computing systems based in part or in whole upon the set of rules, wherein a rule provides how the actionable data is to be dispatched;
  
  determining, at a computer system, contextual and semantic significance in the writings at least by performing classification and filtering on the writings of the plurality of authors;
  
  identifying specific themes within the writings based in part or in whole upon topics and subjects revealed from the semantic analysis and the classification;
  
  performing categorization on the topics and the subjects of the writings to create a number of categories;
  
  associating a set of strength numbers with the number of categories, a strength number indicating relative affinity of each author of the plurality of authors to a particular topic, a particular subject, or a particular theme; and
  
  defining a vector for the each author using at least the set of strength numbers and the number of categories, a vector establishing an author profile for a specific author and being used to describe and analyze the specific author with respect to one or more affinities of the specific author.
- View Dependent Claims (9, 10, 11, 12, 13, 14, 15, 16, 17, 18)
- - 9. The computer program product of claim 8, wherein an author profile comprises a vector comprising values for the topics of interest for an author.
  - 10. The computer program product of claim 8, wherein the vector comprises strength numbers that correspond to an extent or degree of interest by the author for the topics of interest to the plurality of authors.
  - 11. The computer program product of claim 8, in which the semantic analysis comprises a latent semantic analysis that analyzes contextual and semantic significance of terms that appear within the writings.
  - 12. The computer program product of claim 8, wherein semantic filtering is performed to reduce irrelevant data.
  - 13. The computer program product of claim 8, wherein multiple author profiles of the plurality of author profiles for multiple authors of the plurality of authors are correlated to identify commonality of interests.
  - 14. The computer program product of claim 8, wherein actionable data is generated for a business using the plurality of author profiles.
  - 15. The computer program product of claim 14, wherein the actionable data is supplied to an enterprise software system.
  - 16. The computer program product of claim 15, wherein the enterprise software system comprises at least one of a customer relations management (“
    - CRM”
      
      ) application, an enterprise resource planning (“
      
      ERP”
      
      ) application, and a supply chain management application.
  - 17. The computer program product of claim 8, wherein the writings are retrieved from a social media system and comprise social media data.
  - 18. The computer program product of claim 8, further comprising:
    - retrieving the writings, comprising social media data, from a social media system;
      
      storing an author profile as a vector comprising (a) values for the topics of interest for an author and (b) strength numbers that correspond to an extent or degree of interest by the author for the topics of interest to the plurality of authors;
      
      performing, as a part of the semantic analysis, a latent semantic analysis that analyzes contextual and semantic significance of terms that appear within the writings;
      
      reducing irrelevant data through semantic filtering;
      
      identifying commonality of interests by correlating multiple author profiles of the plurality of author profiles for multiple authors of the plurality of authors;
      
      generating actionable data for a business using the author profile; and
      
      supplying the actionable data to an enterprise software system comprising at least one of a customer relations management (“
      
      CRM”
      
      ) application, an enterprise resource planning (“
      
      ERP”
      
      ) application, and a supply chain management (“
      
      SCM”
      
      ) application.

19. A computer system for analyzing author data, comprising:
- a computer processor to execute a set of program code instructions; and
  
  a memory to hold the program code instructions, in which the program code instructions comprises program code to perform, wherein the program code instructions comprises instructions which, when executed by the computer processor, cause the computer processor at least to;
  
  receive writings created by a plurality of authors,perform a semantic analysis upon the writings,generate a plurality of author profiles for the writings using results from the semantic analysis, the plurality of author profiles respectively identifying topics of interest to the plurality of authors, and groups of authors being identified from one or more of the topics of interest, andidentify a first group of multiple authors that corresponds to a first topical subject and multiple author profiles for the multiple authors, the first group of multiple authors identified from the groups and corresponding to the multiple author profiles identified from the plurality of author profiles;
  
  identify a second topical subject shared among at least some authors of the multiple authors in the first group at least by performing a correlation analysis that analyzes at least some author profiles in the multiple author profiles of the at least some authors;
  
  identify a second group of authors from the plurality of authors that exhibit affinity for the second topical subject at least by identifying author vectors corresponding to the second group of authors with respect to the second topical subject; and
  
  correlate the first group of multiple authors with the second group of authors in response to the identification of the second topical subject, wherein the writings are received from the plurality of authors without targeting specific groups of authors;
  
  classifying the writings into a plurality of classes based in part or in whole upon topics of interests determined by the semantic analysis, classifying the writing including;
  
  creating a set of themes from results of the semantic analysis;
  
  analyzing the set of themes created from the results of the semantic analysis;
  
  determining subjects of the topics of interest based in part or in whole upon the set of themes;
  
  determining similarity among the subjects of the topics of interest at least by analyzing the plurality of author profiles;
  
  clustering the topics of interests into the plurality of classes based in part or in whole upon the similarity among the subjects;
  
  determining respective strength numbers for the plurality of authors, a strength number for a user indicating relative affinity of the user to a category relative to one or more remaining categories;
  
  associating the respective strength numbers that correspond to the plurality of authors with a plurality of categories;
  
  creating a vector for each author of the plurality of authors, wherein vectors for the plurality of authors indicate respective affinities among the plurality of authors to one or more common topics of interests or one or more subjects;
  
  establishing an author profile for the each author by using the vector for the each author;
  
  storing the author profile for the author in the plurality of author profiles;
  
  reducing noise in the writings at least by performing a semantic filtering process;
  
  improving accuracy of the plurality of classes from classifying the writings at least by reducing false positives, false negatives, and inappropriate contents with the semantic filtering process;
  
  identifying an actionable data based in part or in whole upon results of the semantic analysis, wherein the writings created by the plurality of authors include contents transcribed from non-social data;
  
  determining, at a rule and workflow module stored at least partially in memory, the plurality of computing systems to receive the actionable data based in part or in whole upon a set of rules that identifies how the actionable data is to be handled and directed;
  
  performing the semantic analysis upon the writings at least by performing a statistical language modeling;
  
  performing the semantic analysis upon the writings at least by performing a latent semantic analysis;
  
  preconfiguring a plurality of types of topics of interest;
  
  determining a first set of authors that corresponds to the one or more first types of topics of interest at least by analyzing the plurality of author profiles to identify a first set of author profiles corresponding to the first set of authors;
  
  determining commonality of one or more second types of topics of interest without pre-defining the one or more second types of topics of interest;
  
  identifying commonality among the plurality of writings in response to the one or more second types of topics of interest based in part or in whole upon results of the semantic analysis;
  
  identifying a group of authors that corresponds to a first affinity for a first subject;
  
  determining a second affinity and a third affinity shared by at least a threshold percentage of authors of the group of authors at least by analyzing a set of author profiles corresponding to the group of authors and by performing one or more first correlation analyses, wherein the second affinity and the third affinity are not known or expected in advance;
  
  generating correlation data based in part or in whole upon results of determining the second affinity and the third affinity;
  
  generating an action for the group of authors based on the second affinity and the third affinity;
  
  receiving the writings created by the plurality of authors without targeting one or more specific groups of authors;
  
  generating the plurality of author profiles for the writings based in part or in whole upon respective strength numbers for the plurality of authors;
  
  identifying a plurality of themes from the writings based in part or in whole upon results of the semantic analysis and results of classifying the writings;
  
  performing a themes analysis;
  
  generating the plurality of author profiles for the writing based in part or in whole upon the plurality of themes;
  
  determining a first set of actionable data for the plurality of authors based in part or in whole upon results of correlating an at least one group with the authors;
  
  identifying a set of rules from a rulebase;
  
  dispatching, at a rules and workflow engine, actionable data for the plurality of authors to a plurality of computing systems based in part or in whole upon the set of rules, wherein a rule provides how the actionable data is to be dispatched;
  
  determining, at a computer system, contextual and semantic significance in the writings at least by performing classification and filtering on the writings of the plurality of authors;
  
  identifying specific themes within the writings based in part or in whole upon topics and subjects revealed from the semantic analysis and the classification;
  
  performing categorization on the topics and the subjects of the writings to create a number of categories;
  
  associating a set of strength numbers with the number of categories, a strength number indicating relative affinity of each author of the plurality of authors to a particular topic, a particular subject, or a particular theme; and
  
  defining a vector for the each author using at least the set of strength numbers and the number of categories, a vector establishing an author profile for a specific author and being used to describe and analyze the specific author with respect to one or more affinities of the specific author.
- View Dependent Claims (20, 21, 22, 23, 24, 25, 26, 27, 28, 29)
- - 20. The system of claim 19, wherein an author profile comprises a vector comprising values for the topics of interest for an author.
  - 21. The system of claim 19, wherein the vector comprises strength numbers that correspond to an extent or degree of interest by the author for the topics of interest to the plurality of authors.
  - 22. The system of claim 19, in which the semantic analysis comprises a latent semantic analysis that analyzes contextual and semantic significance of terms that appear within the writings.
  - 23. The system of claim 19, wherein semantic filtering is performed to reduce irrelevant data.
  - 24. The system of claim 19, wherein multiple author profiles of the plurality of author profiles for multiple authors of the plurality of authors are correlated to identify commonality of interests.
  - 25. The system of claim 19, wherein actionable data is generated for a business using the author profile.
  - 26. The system of claim 25, wherein the actionable data is supplied to an enterprise software system.
  - 27. The system of claim 26, wherein the enterprise software system comprises at least one of a customer relations management (“
    - CRM”
      
      ) application, an enterprise resource planning (“
      
      ERP”
      
      ) application, and a supply chain management application.
  - 28. The system of claim 19, wherein the writings are retrieved from a social media system and comprise social media data.
  - 29. The system of claim 19, wherein:
    - the writings are retrieved from a social media system and comprise social media data;
      
      an author profile comprises a vector comprising values for the topics of interest for the author, and the vector comprises strength numbers that correspond to an extent or degree of interest by the author for the topics of interest to the plurality of authors;
      
      the semantic analysis comprises a latent semantic analysis that analyzes contextual and semantic significance of terms that appear within the writings;
      
      semantic filtering is performed to reduce irrelevant data;
      
      multiple author profiles of the plurality of author profiles for multiple authors of the plurality of authors are correlated to identify commonality of interests; and
      
      actionable data is generated for a business using the author profile and the actionable data is supplied to an enterprise software system comprising at least one of a customer relations management (“
      
      CRM”
      
      ) application, an enterprise resource planning (“
      
      ERP”
      
      ) application, and a supply chain management application.

Specification

Resources

Litigation Campaign Assessment

Current Assignee
Oracle International Corporation (Oracle Corporation)
Original Assignee
Oracle International Corporation (Oracle Corporation)
Inventors
Setayesh, Mehrshad, McCandless, Timothy P.
Primary Examiner(s)
Singh, Amresh
Assistant Examiner(s)
Jacobs, Edward

Application Number

US13/795,699
Publication Number

US 20140280168A1
Time in Patent Office

1,477 Days
Field of Search

707/739
US Class Current

1/1
CPC Class Codes

G06F 16/285   Clustering or classification

G06F 16/3344   using natural language anal...

G06F 16/335   Filtering based on addition...

G06F 16/35   Clustering; Classification

G06Q 10/10   Office automation; Time man...

G06Q 30/0201   Market modelling; Market an...

G06Q 30/0276   Advertisement creation

G06Q 50/01   Social networking

Method and system for implementing author profiling

First Claim

1 Assignment

0 Petitions

Accused Products

Abstract

32 Citations

29 Claims

Specification

Solutions

Use Cases

Quick Links

Method and system for implementing author profiling

First Claim

1 Assignment

Subscription Required

Subscription Required

0 Petitions

Subscription Required

Accused Products

Subscription Required

Abstract

32 Citations

29 Claims

Specification

Subscription Required

Solutions

Use Cases

Quick Links