Incorporation of semantic attributes within social media

• US 10,289,727 B2
• Filed: 09/17/2015
• Issued: 05/14/2019
• Est. Priority Date: 09/17/2015
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Bostick, James E., Cunico, Hernan A., Ganci, Jr., John M., Rakshit, Sarbajit K., Trim, Craig M.
• Primary Examiner(s): Channavajjala, Srirama
• Application Number:
  US14/856,715
• Publication Number:
  US 20170083599A1
• Time in Patent Office: 1,335 Days
• CPC Class Codes: G06F 16/23 Updating
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 16/3326 using relevance feedback from the user, e.g. relevance feedback on documents, documents sets, document terms or passages
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06F 16/5866 using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9536 Search customisation based on social or collaborative filtering
• CPC Class Codes: G06F 16/954 Navigation, e.g. using categorised browsing
• CPC Class Codes: G06F 16/955 using information identifiers, e.g. uniform resource locators [URL]
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

In an approach for adding categories to a social media site, a computer identifies one or more semantic attributes of content uploaded on a social media site, wherein the identified one or more semantic attributes correspond to viewable characteristics of the content uploaded on the social media site. The computer maps the identified one or more semantic attributes to one or more categories based on shared viewable characteristics of the identified one or more sematic attributes. The computer associates the one or more mapped categories to the content uploaded on the social media site.

Claims

1. A method for adding categories to a social media site, the method comprising:

identifying, by one or more computer processors, one or more semantic attributes of content uploaded on a social media site, wherein the identified one or more semantic attributes are descriptive subcategories that exist in a hierarchy tiering to a top level sentiment category based on viewable characteristics of the content uploaded that include objects, colors, and boundaries wherein one or more of the viewable characteristics are assigned to a sentiment category that conveys a message represented by a context between signifiers, wherein the signifiers include words, phrases, signs, and symbols that describe the viewable characteristics;

mapping, by one or more computer processors, the identified one or more semantic attributes to the one or more categories based on similarities between the viewable characteristics of the identified one or more semantic attributes;

adding, by one or more computer processors, the one or more mapped categories to the content uploaded on the social media site, wherein the one or more mapped categories add granularity to comment specifically on viewable characteristics within the content uploaded; and

initiating, by one or more computer processors, display of the mapped one or more categories with the derived name that are added to the content uploaded on the social media site.

2. The method of claim 1, wherein the one or more mapped categories with a derived name that are added to the content uploaded on the social media site are each capable of receiving user input from users of the social media site.

3. The method of claim 1, wherein identifying one or more semantic attributes of the content uploaded on the social media site further comprises:

extracting, by one or more computer processors, one or more objects from an image associated with the content uploaded on the social media site utilizing image analysis and one or more rules, wherein the image analysis includes pattern recognition, digital geometry, signal processing, object-based image analysis, and digital image processing with a set of parameters related to the content uploaded;

identifying, by one or more computer processors, the one or more extracted objects by comparing the one or more extracted objects with a repository of known objects;

identifying, by one or more computer processors, one or more co-relationships between the one or more extracted objects;

identifying, by one or more computer processors, one or more semantic attributes of the image that are defined by the identified one or more objects and the identified one or more co-relationships;

creating, by one or more computer processors, one or more categories that correspond to the identified one or more semantic attributes of the image;

sorting, by one or more computer processors, each of the identified one or more objects into the created one or more categories, based on the identified one or more semantic attributes that are associated with the identified one or more objects; and

deriving, by one or more computer processors, a name for each of the one or more categories for each of the identified one or more semantic attributes, wherein the name provides a meaning for focused feedback.

4. The method of claim 1, wherein identifying one or more semantic attributes of the content uploaded on the social media site further comprises:

analyzing, by one or more computer processors, posted text associated with the content uploaded on the social media site utilizing natural language processing;

identifying, by one or more computer processor, one or more sematic attributes of the analyzed posted text associated with the content uploaded on the social media site;

creating, by one or more computer processors, one or more categories that correspond to the identified one or more semantic attributes of the analyzed posted text; and

deriving, by one or more computer processors, a name for each of the one or more categories based in part on the analyzed posted text.

5. The method of claim 1, wherein mapping the identified one or more semantic attributes to the one or more categories based on shared viewable characteristics of the identified one or more sematic attributes further comprises:

storing, by one or more computer processors, the identified one or more sematic attributes in a list;

receiving, by one or more computer processors, a category threshold that identifies a maximum number of categories associated with the content uploaded;

determining, by one or more computer processors, that the one or more categories include one or more static categories;

receiving, by one or more computer processors, a ranking of the one or more static categories from one or more of;

a social media site and a user;

determining, by one or more computer processors, one or more semantic attributes that are associated with the one or more static categories utilizing natural language processing and lemmatization of the stored list of the identified one or more sematic attributes, wherein the lemmatization groups different inflected forms of a word associated with the identified one or more semantic attributes into a single sentiment category;

storing, by one or more computer processors, the determined one or more sematic attributes that are associated with the one or more static categories in a hash table based on the received ranking, wherein the hash table combines one or more semantic attributes from an image analysis and one or more semantic attributes from natural language processing; and

updating, by one or more computer processors, the ranked one or more categories based on the received category threshold.

6. The method of claim 1, wherein mapping the identified one or more semantic attributes to the one or more categories based on shared viewable characteristics of the identified one or more sematic attributes further comprises:

storing, by one or more computer processors, the identified one or more sematic attributes in a list;

receiving, by one or more computer processors, a category threshold that identifies a maximum number of categories associated with the content uploaded;

determining, by one or more computer processors, that the one or more categories include one or more dynamic categories;

determining, by one or more computer processors, a ranking of the stored list of the identified one or more sematic attributes based on streaming data from the social media site and user feedback from the social media site;

creating, by one or more computer processors, one or more categories based on the received category threshold and the determined ranking of the stored list;

assigning, by one or more computer processors, the one or more semantic attributes to the created one or more categories; and

updating, by one or more computer processors, the ranked one or more categories based on the received category threshold.

7. The method of claim 1, further comprises:

receiving, by one or more computer processors, user feedback input into the added mapped one or more categories to the content uploaded on the social media site, wherein the user feedback includes one or more of;

comments, likes, and ratings;

receiving, by one or more computer processors, user input on content of the social media site, wherein the input includes one or more of;

grouping content, filtering content, and searching content; and

organizing, by one or more computer processors, the received user feedback into one or more stacks of content on the social media site based on the received input and a stacking rule, wherein the stacking rule defines an order for viewing and a presentation manner associated with the order for viewing, wherein the order for viewing is based on one or more of a chronological order, a highest to lowest number of likes, most comments, unread comments, a date range, one or more specific users, a group, and one or more specified sentiment categories, wherein the presentation manner includes one of;

overlapping posts and selectable tabs.

8. The method of claim 7, further comprises:

initiating, by one or more computer processor, display of one or more stacks of content on the social media site, wherein the one or more stacks of content include the organized user feedback;

receiving, by one or more computer processors, a user selection from within the initiated display of one or more stacks of content on the social media site;

reorganizing, by one or more computer processors, the initiated display of one or more stacks of content on the social media site based on the received user selection; and

initiating, by one or more computer processors, display of the reorganized one or more stacks of content on the social media site.

9. A computer program product for adding categories to a social media site, the computer program product comprising:

one or more computer readable storage media and program instructions stored on the one or more computer readable storage media, the program instructions comprising;

program instructions to identify one or more semantic attributes of the content uploaded on a social media site, wherein the identified one or more semantic attributes are descriptive subcategories that exist in a hierarchy tiering to a top level sentiment category based on viewable characteristics of the content uploaded that include objects, colors, and boundaries, wherein one or more of the viewable characteristics are assigned to a sentiment category that conveys a message represented by a context between signifiers, wherein the signifiers include words, phrases, signs, and symbols that describe the viewable characteristics;

program instructions to map the identified one or more semantic attributes to the one or more categories based on similarities between the viewable characteristics of the identified one or more semantic attributes;

program instructions to add the one or more mapped categories to the content uploaded on the social media site; and

program instructions initiate display of the mapped one or more categories with the derived name that are added to the content uploaded on the social media site, wherein the one or more mapped categories add granularity to comment specifically on viewable characteristics within the content uploaded.

10. The computer program product of claim 9, wherein the one or more mapped categories with the derived name that are added to the content uploaded on the social media site are each capable of receiving user input from users of the social media site.

11. The computer program product of claim 9, wherein to identify one or more semantic attributes of the content uploaded on the social media site further comprises program instructions, stored on the one or more computer readable storage media, to:

extract one or more objects from an image associated with the content uploaded on the social media site utilizing image analysis and one or more rules, wherein the image analysis includes one or more of;

pattern recognition, digital geometry, signal processing, object-based image analysis, and digital image processing with a set of parameters related to the content uploaded;

identify the one or more extracted objects by comparing the one or more extracted objects with a repository of known objects;

identify one or more co-relationships between the one or more extracted objects;

identify one or more semantic attributes of the image that are defined by the identified one or more objects and the identified one or more co-relationships;

create one or more categories, that correspond to the identified one or more semantic attributes;

sort each of the identified one or more objects into the created one or more categories, based on the identified one or more semantic attributes that are associated with the identified one or more objects; and

derive a name for each of the one or more categories for each of the identified one or more semantic attributes, wherein the name provides a meaning for focused feedback.

12. The computer program product of claim 9, wherein to identify one or more semantic attributes of the content uploaded on the social media site further comprises program instructions, stored on the one or more computer readable storage media, to:

analyze posted text associated with the content uploaded on the social media site utilizing natural language processing;

identify one or more sematic attributes of the analyzed posted text associated with the content uploaded on the social media site;

create one or more categories that correspond to the identified one or more semantic attributes of the analyzed posted text; and

derive a name for each of the one or more categories based in part on the analyzed posted text.

13. The computer program product of claim 9, wherein to map the identified one or more semantic attributes to the one or more categories based on shared viewable characteristics of the identified one or more sematic attributes further comprises program instructions, stored on the one or more computer readable storage media, to:

store the identified one or more sematic attributes in a list;

receive a category threshold that identifies a maximum number of categories associated with the content uploaded;

determine that the one or more categories include one or more static categories;

receive a ranking of the one or more static categories from one or more of;

a social media site and a user;

determine one or more semantic attributes that are associated with the one or more static categories utilizing natural language processing and lemmatization of the stored list of the identified one or more sematic attributes, wherein the lemmatization groups different inflected forms of a word associated with the identified one or more semantic attributes into a single sentiment category;

store the determined one or more sematic attributes that are associated with the one or more static categories in a hash table based on the received ranking, wherein the hash table combines one or more semantic attributes from an image analysis and one or more semantic attributes from natural language processing; and

update the ranked one or more categories based on the received category threshold.

14. The computer program product of claim 9, wherein to map the identified one or more semantic attributes to the one or more categories based on shared viewable characteristics of the identified one or more sematic attributes further comprises program instructions, stored on the one or more computer readable storage media, to:

store, the identified one or more sematic attributes in a list;

receive a category threshold that identifies a maximum number of categories associated with the content uploaded;

determine that the one or more categories include one or more dynamic categories;

determine a ranking of the stored list of the identified one or more sematic attributes based on streaming data from the social media site and user feedback from the social media site;

create one or more categories based on the received category threshold and the determined ranking of the stored list;

assign the one or more semantic attributes to the created one or more categories; and

update the ranked one or more categories based on the received category threshold.

15. A computer system for adding categories to a social media site, the computer system comprising:

one or more computer processors, one or more computer readable storage media, and program instructions stored on the computer readable storage media for execution by at least one of the one or more processors, the program instructions comprising;

program instructions to identify one or more semantic attributes of the content uploaded on a social media site, wherein the identified one or more semantic attributes are descriptive subcategories that exist in a hierarchy tiering to a top level sentiment category based on viewable characteristics of the content uploaded that include objects, colors, and boundaries, wherein one or more of the viewable characteristics are assigned to a sentiment category that conveys a message represented by a context between signifiers, wherein the signifiers include words, phrases, signs, and symbols that describe the viewable characteristics;

program instructions to map the identified one or more semantic attributes to the one or more categories based on similarities between the viewable characteristics of the identified one or more semantic attributes;

program instructions to add the one or more mapped categories to the content uploaded on the social media site, wherein the one or more mapped categories add granularity to comment specifically on viewable characteristics within the content uploaded; and

program instructions initiate display of the mapped one or more categories with the derived name that are added to the content uploaded on the social media site.

16. The computer system of claim 15, wherein the one or more mapped categories with the derived name that are added to the content uploaded on the social media site are each capable of receiving user input from users of the social media site.

17. The computer system of claim 15, wherein to identify one or more semantic attributes of the content uploaded on the social media site further comprises program instructions, stored on the one or more computer readable storage media, to:

extract one or more objects from an image associated with the content uploaded on the social media site utilizing image analysis and one or more rules, wherein the image analysis includes one or more of;

pattern recognition, digital geometry, signal processing, object-based image analysis, and digital image processing with a set of parameters related to the content uploaded;

identify the one or more extracted objects by comparing the one or more extracted objects with a repository of known objects;

identify one or more co-relationships between the one or more extracted objects;

identify one or more semantic attributes of the image that are defined by the identified one or more objects and the identified one or more co-relationships;

create one or more categories, that correspond to the identified one or more semantic attributes;

sort each of the identified one or more objects into the created one or more categories, based on the identified one or more semantic attributes that are associated with the identified one or more objects; and

derive a name for each of the one or more categories for each of the identified one or more semantic attributes, wherein the name provides a meaning for focused feedback.

18. The computer system of claim 15, wherein to identify one or more semantic attributes of the content uploaded on the social media site further comprises program instructions, stored on the one or more computer readable storage media, to:

analyze posted text associated with the content uploaded on the social media site utilizing natural language processing;

identify one or more sematic attributes of the analyzed posted text associated with the content uploaded on the social media site;

create one or more categories that correspond to the identified one or more semantic attributes of the analyzed posted text; and

derive a name for each of the one or more categories based in part on the analyzed posted text.

19. The computer system of claim 15, wherein to map the identified one or more semantic attributes to the one or more categories based on shared viewable characteristics of the identified one or more sematic attributes further comprises program instructions, stored on the one or more computer readable storage media, to:

store the identified one or more sematic attributes in a list;

receive a category threshold that identifies a maximum number of categories associated with the content uploaded;

determine that the one or more categories include one or more static categories;

receive a ranking of the one or more static categories from one or more of;

a social media site and a user;

determine one or more semantic attributes that are associated with the one or more static categories utilizing natural language processing and lemmatization of the stored list of the identified one or more sematic attributes, wherein the lemmatization groups different inflected forms of a word associated with the identified one or more semantic attributes into a single sentiment category;

store the determined one or more sematic attributes that are associated with the one or more static categories in a hash table based on the received ranking, wherein the hash table combines one or more semantic attributes from an image analysis and one or more semantic attributes from natural language processing; and

update the ranked one or more categories based on the received category threshold.

20. The computer system of claim 15, wherein to map the identified one or more semantic attributes to the one or more categories based on shared viewable characteristics of the identified one or more sematic attributes further comprises program instructions, stored on the one or more computer readable storage media, to:

store, the identified one or more sematic attributes in a list;

receive a category threshold that identifies a maximum number of categories associated with the content uploaded;

determine that the one or more categories include one or more dynamic categories;

determine a ranking of the stored list of the identified one or more sematic attributes based on streaming data from the social media site and user feedback from the social media site;

create one or more categories based on the received category threshold and the determined ranking of the stored list;

assign the one or more semantic attributes to the created one or more categories; and

update the ranked one or more categories based on the received category threshold.