Social intelligence architecture using social media message queues

• US 9,418,389 B2
• Filed: 05/07/2012
• Issued: 08/16/2016
• Est. Priority Date: 05/07/2012
• Status: Active Grant

• Current Assignee: Nasdaq, Inc.
• Original Assignee: Nasdaq, Inc.
• Inventors: Chandrasekaran, Deepak, Stubbs, Paul
• Primary Examiner(s): Kim, Taelor
• Application Number:
  US13/465,307
• Publication Number:
  US 20130297618A1
• Time in Patent Office: 1,562 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/22 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: H04L 51/52 for supporting social networking services

Abstract

A social intelligence system is presented that streams information from a source, queues the streamed information, analyzes/scores the queued data, and stores the analyzed/scored data in an analysis database. The analyzed/scored data can then be retrieved from the database for post-processing and stored in a client specific database for further reporting. By streaming the data into various message queues and scoring the data before storing in the analysis database, large volumes of data can be efficiently processed and analyzed for a particular person and/or entity.

Claims

1. A method for analyzing social media data, comprising:

at an information processing apparatus having at least one or more processors and a transceiver;

receiving, using the transceiver, social media data streams from one or more social media sources as social media data segments, wherein the social media data segments include social media data segments related to the entity;

queuing, using the one or more processors, the received social media data segments into one or more social media message queues, the one or more social media message queues queuing the social media data segments as the segments are streamed from the one or more social media sources;

assigning, using the one or more processors, a score and a polarity for each of the queued social media data segments from a viewpoint of the entity for which the sentiment analysis is being performed, the score and polarity for each social media data segment including at least one of a positive, neutral, or negative sentiment determined based on the viewpoint of the entity for which the sentiment analysis is being performed;

generating, using the one or more processors, a resultant sentiment based on the score and the polarity assigned to the queued social media data segments; and

storing, using the one or more processors, the social media data segments and their associated resultant sentiment into an analysis database specific to the entity.

2. The method for analyzing social media data according to claim 1, further comprising:

parsing and scoring the social media data segments using a natural language processor.

3. The method for analyzing social media data according to claim 1, wherein the multiple social media sources comprises at least one of publications, social media websites, forums, blogs, radio broadcasts, and/or television broadcasts.

4. The method for analyzing social media data according to claim 1, further comprising moving the social media data segments and their associated resultant sentiment from the analysis database into a historical database after a predetermined period of time.

5. The method for analyzing social media data according to claim 1, further comprising generating a sentiment report based on the resultant sentiment.

16. The method for analyzing social media data according to claim 1, wherein the entity is a client and the resultant sentiment for the queued social media data segments vary depending upon the client.

17. The method for analyzing social media data according to claim 1, wherein the score and polarity varies depending upon content in the social media data segment with respect to the viewpoint of the entity.

18. The method for analyzing social media data according to claim 1, wherein a score and polarity normally indicating negative sentiment indicates positive sentiment when content in the social media data segment relates to a competitor of the entity.

19. The method for analyzing social media data according to claim 1, wherein a score and polarity normally indicating positive sentiment indicates negative sentiment when content in the social media data segment relates to a competitor of the entity.

6. A non-transitory computer-readable storage medium comprising computer readable code embodied therein which, when executed by a computer having one or more processors, causes the computer to:

receive social media data streams from one or more social media sources as social media data segments, wherein the social media data segments include social media data segments related to the entity;

queue the received social media data segments into one or more social media message queues, the one or more social media message queues queuing the social media data segments as the segments are streamed from the one or more social media sources;

assign a score and a polarity for each of the queued social media data segments from a viewpoint of the entity for which the sentiment analysis is being performed, the score and polarity for each social media data segment including at least one of a positive, neutral, or negative sentiment determined based on the viewpoint of the entity for which the sentiment analysis is being performed;

generate a resultant sentiment based on the score and the polarity assigned to the queued social media data segments; and

store the social media data segments and their associated resultant sentiment into an analysis database specific to the entity.

7. A social intelligence apparatus, comprising:

a transceiver;

a memory having one or more social media message queues; and

one or more processors, coupled to the memory, configured to execute social media data analysis in the social intelligence apparatus and configured to;

receive, using the transceiver, social media data streams from one or more social media sources as social media data segments, wherein the social media data segments include social media data segments related to an entity,

queue the received social media data segments into one or more social media message queues, the one or more social media message queues queuing the social media data segments as the segments are streamed from the one or more social media sources,

assign a score and a polarity for each of the queued social media data segments from a viewpoint of the entity for which the sentiment analysis is being performed, the score and polarity for each social media data segment including at least one of a positive, neutral, or negative sentiment determined based on the viewpoint of the entity for which the sentiment analysis is being performed,

generate a resultant sentiment based on the score and the polarity assigned to the queued social media data segments, and

store the social media data segments and their associated resultant sentiment into an analysis database specific to the entity.

8. The social intelligence apparatus according to claim 7, wherein the one or more processors are further configured to:

parse and score the social media data segments using a natural language processor.

9. The social intelligence apparatus according to claim 7, wherein the multiple social media sources comprises at least one of publications, social media websites, forums, blogs, radio broadcasts, and/or television broadcasts.

10. The social intelligence apparatus according to claim 7, wherein the one or more processors are further configured to move the social media data segments and their associated resultant sentiment from the analysis database into a historical database after a predetermined period of time.

11. The social intelligence apparatus according to claim 7, wherein the one or more processors are further configured to generate a sentiment report based on the resultant sentiment.

12. A social intelligence system, comprising:

one or more social media devices having;

a memory configured to store social media data,

one or more processors configured to process social media data, and

a transceiver configured to transmit social media data; and

a social intelligence apparatus having;

a memory having multiple social media message queues,

a transceiver configured to receive social media data from the one or more social media devices, and

one or more processors, coupled to the memory, configured to execute social media data analysis in the social intelligence apparatus and configured to;

receive, using the transceiver, social media data streams from one or more social media sources as social media data segments, wherein the social media data segments include social media data segments related to an entity,

queue the received social media data segments into one or more social media message queues, the one or more social media message queues queuing the social media data segments as the segments are streamed from the one or more social media sources,

assign a score and a polarity for each of the queued social media data segments from a viewpoint of the entity for which the sentiment analysis is being performed, the score and polarity for each social media data segment including at least one of a positive, neutral, or negative sentiment determined based on the viewpoint of the entity for which the sentiment analysis is being performed,

generate a resultant sentiment based on the score and the polarity assigned to the queued social media data segments, and

store the social media data segments and their associated resultant sentiment into an analysis database specific to the entity.

13. The social intelligence system of claim 12, wherein the one or more processors are further configured to:

parse and score the social media data segments using a natural language processor.

14. The social intelligence system of claim 12, wherein the multiple social media sources comprises at least one of publications, social media websites, forums, blogs, radio broadcasts, and/or television broadcasts.

15. The social intelligence system of claim 12, wherein the one or more processors in the social intelligence apparatus are further configured to move the social media data segments and their associated resultant sentiment from the analysis database into a historical database after a predetermined period of time.