Method and system for performing analysis of social media messages

• US 9,426,239 B2
• Filed: 03/12/2013
• Issued: 08/23/2016
• Est. Priority Date: 03/12/2013
• Status: Active Grant

• Current Assignee: Oracle International Corporation (Oracle Corporation)
• Original Assignee: Oracle International Corporation (Oracle Corporation)
• Inventors: McCandless, Timothy P., Chen, Duo, Setayesh, Mehrshad
• Primary Examiner(s): Parry, Chris
• Assistant Examiner(s): Lee, Daeoo
• Application Number:
  US13/795,895
• Publication Number:
  US 20140280525A1
• Time in Patent Office: 1,260 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/335 Filtering based on additional data, e.g. user or group profiles filtering in web context G06F16/9535, G06F16/9536
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06Q 10/107 Computer-aided management of electronic mailing [e-mailing]
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: H04L 67/306 User profiles
• CPC Class Codes: H04L 67/52 specially adapted for the location of the user terminal
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34
• CPC Class Codes: H04L 67/564 Enhancement of application control based on intercepted application data

Abstract

Disclosed is an improved method, system, and computer program product for analyzing social media content. Correlation analysis is used to analyze the social media data snippets. The correlation analysis is performed by reviewing other items of data that are outside of the message content itself. The present approach can advantageously be used to analyze and understand the content of social media message even where only very small quantities of data are provided within each message posting.

Claims

1. A computer implemented method for correlating disparate social media data and identifying a context for correlated media data, the method comprising:

analyzing social media messages using an analysis unit, the analysis unit being communicatively coupled to receive inputs from one or more online social data sources and to provide analysis outputs to a workflow engine, the analysis unit correlating the social media messages to identify a context based at least upon analysis of message contents, metadata, and social profile data, the analysis of the social media messages performed by a process comprising;

receiving social media content from the one or more online social data sources transmitted over one or more electronic communications links, the social media content comprising at least message contents, metadata, and social profile data,

determining a geographic location of the message contents,

removing the message contents that are beyond a geographical distance from the geographic location of at least one of the message contents,

performing latent semantic analysis on remaining message contents using the metadata and the social profile data to determine semantic significance of the remaining message contents,

clustering the messages into one or more clusters by classifying the messages based on at least the results of performing latent semantic analysis, and

correlating the at least one of the one or more clusters to identify a context for the remaining message contents using at least the metadata and the remaining message contents to generate correlation results,

processing the correlation results using the workflow engine, the workflow engine processing the correlation results using a set of rules provided in a rulebase, the set of rules identifying how actionable items should be handled or directed within an organization, the correlation results processed by;

receiving the correlation results from the analysis unit transmitted over one or more electronic communications links,

identifying one or more actionable items based at least in part on the received correlation results,

automatically processing at least some of the one or more actionable items using the workflow engine and the set of rules.

2. The method of claim 1, wherein the social profile data comprises demographic or psychographic information about an author of the social media content.

3. The method of claim 1, wherein the social profile data is pre-analyzed to establish analysis data pertaining to an author prior to creation of the social media content.

4. The method of claim 1, wherein correlating comprises using at least one of location data, time data, volume data, and subject matter data.

5. The method of claim 1, in which semantic filtering is performed to reduce occurrence of false positives, false negatives or inappropriate responses.

6. The method of claim 1, wherein the analysis results are obtained that create actionable items for an enterprise software system and the enterprise software system comprises at least one of a customer relations management application, an enterprise resource planning applications, and a supply chain management application.

7. The method of claim 1, further comprising

filtering to reduce occurrences of false positives, false negatives or inappropriate responses, the filtering comprising at least semantic filtering;

storing the correlation results in an electronic database on one or more persistent computer readable storage devices;

wherein correlating comprises using at least one of location data, time data, volume data, and subject matter data;

wherein the workflow engine is part of an enterprise software system comprising at least one of a customer relations management application, enterprise resource planning applications, and a supply chain management application, the actionable items comprising at least one of identification of sales leads, identification of customer relations issues, or identification of dissatisfied customers;

wherein the social media content comprises messages from a messaging system that are distributed based upon identification of followers for the messages, the social media content originating from at least one of public social networks or private social media networks, the public social media networks including at least blog sites, forums, twitter messages, RSS data, and Facebook, and the private social networks including at least internal company social networking sites, emails, chats, transcribed phone conversations, and transcribed videos;

wherein the social profile data comprises at least psychographic information about an authors income, age, profession, geographic location, concerns, affinities, or other areas of interest, and wherein the social profile data is pre-analyzed to establish analysis data pertaining to the author prior to creation of the social media content; and

wherein the geographic location is inferred from author location data or social profile data.

8. A non-transitory computer readable medium having stored thereon a sequence of instructions which, when executed by a processor causes the processor to execute a method for analyzing social media data correlating disparate social media data and identifying a context for correlated media data, the method comprising:

analyzing social media messages using an analysis unit, the analysis unit being communicatively coupled to receive inputs from one or more online social data sources and to provide analysis outputs to a workflow engine, the analysis unit correlating the social media messages to identify a context based at least upon analysis of message contents, metadata, and social profile data, the analysis of the social media messages performed by a process comprising;

receiving social media content from the one or more online social data sources transmitted over one or more electronic communications links, the social media content comprising at least message contents, metadata, and social profile data,

determining a geographic location of the message contents,

removing the message contents that are beyond a geographical distance from the geographic location of at least one of the message contents,

performing latent semantic analysis on remaining message contents using the metadata and the social profile data to determine semantic significance of the remaining message contents,

clustering the messages into one or more clusters by classifying the messages based on at least the results of performing latent semantic analysis, and

correlating the at least one of the one or more clusters to identify a context for the remaining message contents using at least the metadata and the remaining message contents to generate correlation results,

processing the correlation results using the workflow engine, the workflow engine processing the correlation results using a set of rules provided in a rulebase, the set of rules identifying how actionable items should be handled or directed within an organization, the correlation results processed by;

receiving the correlation results from the analysis unit transmitted over one or more electronic communications links,

identifying one or more actionable items based at least in part on the received correlation results,

automatically processing at least some of the one or more actionable items using the workflow engine and the set of rules.

9. The computer readable medium of claim 8, wherein the social profile data comprises demographic or psychographic information about an author of the social media content.

10. The computer readable medium of claim 8, wherein the social profile data is pre-analyzed to establish analysis data pertaining to an author prior to creation of the social media content.

11. The computer readable medium of claim 8, wherein correlating comprises using at least one of location data, time data, volume data, and subject matter data.

12. The computer readable medium of claim 8 in which semantic filtering is performed to reduce occurrence of false positives, false negatives or inappropriate responses.

13. The computer readable medium of claim 8, wherein the analysis results are obtained that create actionable items for an enterprise software system and the enterprise software system comprises at least one of a customer relations management application, an enterprise resource planning applications, and a supply chain management application.

14. The computer readable medium of claim 8, the method further comprising

filtering to reduce occurrences of false positives, false negatives or inappropriate responses, the filtering comprising at least semantic filtering;

storing the correlation results in an electronic database on one or more persistent computer readable storage devices;

wherein correlating comprises using at least one of location data, time data, volume data, and subject matter data;

wherein the workflow engine is part of an enterprise software system comprising at least one of a customer relations management application, enterprise resource planning applications, and a supply chain management application, the actionable items comprising at least one of identification of sales leads, identification of customer relations issues, or identification of dissatisfied customers;

wherein the social media content comprises messages from a messaging system that are distributed based upon identification of followers for the messages, the social media content originating from at least one of public social networks or private social media networks, the public social media networks including at least blog sites, forums, twitter messages, RSS data, and Facebook, and the private social networks including at least internal company social networking sites, emails, chats, transcribed phone conversations, and transcribed videos;

wherein the social profile data comprises at least psychographic information about an authors income, age, profession, geographic location, concerns, affinities, or other areas of interest, and wherein the social profile data is pre-analyzed to establish analysis data pertaining to the author prior to creation of the social media content; and

wherein the geographic location is inferred from author location data or social profile data.

15. A computer system for analyzing social media 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 acts comprising;

analyzing social media messages using an analysis unit, the analysis unit being communicatively coupled to receive inputs from one or more online social data sources and to provide analysis outputs to a workflow engine, the analysis unit correlating the social media messages to identify a context based at least upon analysis of message contents, metadata, and social profile data, the analysis of the social media messages performed by a process comprising;

receiving social media content from the one or more online social data sources transmitted over one or more electronic communications links, the social media content comprising at least message contents, metadata, and social profile data,

determining a geographic location of the message contents,

removing the message contents that are beyond a geographical distance from the geographic location of at least one of the message contents,

performing latent semantic analysis on remaining message contents using the metadata and the social profile data to determine semantic significance of the remaining message contents,

clustering the messages into one or more clusters by classifying the messages based on at least the results of performing latent semantic analysis, and

correlating the at least one of the one or more clusters to identify a context for the remaining message contents using at least the metadata and the remaining message contents to generate correlation results, processing the correlation results using the workflow engine, the workflow engine processing the correlation results using a set of rules provided in a rulebase, the set of rules identifying how actionable items should be handled or directed within an organization, the correlation results processed by;

receiving the correlation results from the analysis unit transmitted over one or more electronic communications links,

identifying one or more actionable items based at least in part on the received correlation results,

automatically processing at least some of the one or more actionable items using the workflow engine and the set of rules.

16. The system of claim 15, wherein the social profile data is pre-analyzed to establish analysis data pertaining to an author prior to creation of the social media content.

17. The system of claim 15, wherein correlating comprises using at least one of location data, time data, volume data, and subject matter data.

18. The system of claim 15 in which semantic filtering is performed to reduce occurrence of false positives, false negatives or inappropriate responses.

19. The system of claim 15, wherein the analysis results are obtained that create actionable items for an enterprise software system and the enterprise software system comprises at least one of a customer relations management application, an enterprise resource planning applications, and a supply chain management application.

20. The system of claim 15, the actions further comprising

filtering to reduce occurrences of false positives, false negatives or inappropriate responses, the filtering comprising at least semantic filtering;

storing the correlation results in an electronic database on one or more persistent computer readable storage devices;

wherein correlating comprises using at least one of location data, time data, volume data, and subject matter data;

wherein the workflow engine is part of an enterprise software system comprising at least one of a customer relations management application, enterprise resource planning applications, and a supply chain management application, the actionable items comprising at least one of identification of sales leads, identification of customer relations issues, or identification of dissatisfied customers;

wherein the social media content comprises messages from a messaging system that are distributed based upon identification of followers for the messages, the social media content originating from at least one of public social networks or private social media networks, the public social media networks including at least blog sites, forums, twitter messages, RSS data, and Facebook, and the private social networks including at least internal company social networking sites, emails, chats, transcribed phone conversations, and transcribed videos;

wherein the social profile data comprises at least psychographic information about an authors income, age, profession, geographic location, concerns, affinities, or other areas of interest, and wherein the social profile data is pre-analyzed to establish analysis data pertaining to the author prior to creation of the social media content; and

wherein the geographic location is inferred from author location data or social profile data.