SOCIAL MEDIA VARIABLE ANALYTICAL SYSTEM

• US 20120036085A1
• Filed: 08/05/2010
• Published: 02/09/2012
• Est. Priority Date: 08/05/2010
• Status: Abandoned Application

• Current Assignee: Accenture Global Services Limited (Accenture PLC)
• Original Assignee: Accenture Global Services GmbH (Accenture PLC)
• Inventors: SRIVASTAVA, Janmesh Dev, UMBLIJS, Andris, KIRKBY, Stephen Denis, WANG, Chao, KELLETT, Peter Charles, TRAN, Thoai Duy Khang, DUBEY, Dharmendra K.
• Application Number:
  US12/851,461
• Publication Number:
  US 20120036085A1
• Time in Patent Office: Days
• US Class Current: 705/348
• CPC Class Codes: G06Q 10/067 Enterprise or organisation modelling
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

A system is configured to determine aggregated social media variables that may be used for modeling. The system includes an information identifier module determining keywords and phrases. The system also includes an aggregator receiving information collected from social media applications using the keywords and phrases and determining values for social media variables from the collected information. The aggregator aggregates the social media variables based on the values and weightings of the social media variables.

Claims

1. A social media analytical system configured to determine aggregated social media variables, the system comprising:

an information identifier module determining keywords and phrases; and

an aggregator, executed by a computer system, receiving information collected from social media applications using the keywords and phrases, determining values for social media variables from the collected information, and aggregating the social media variables based on the values and weightings of the social media variables.

2. The system of claim 1, wherein the aggregator determines categories, subcategories for each category, and topics for each subcategory associated with a product, and the aggregator uses econometrics to determine aggregation weights for the subcategories and combines the summed values for each subcategory using the aggregation weights to determine aggregated social media variable values for each category.

3. The system of claim 2, wherein the aggregator determines values for aggregated social media variables for each topic by

determining, from the keywords and phrases, a set of keywords and phrases assigned to each of the aggregated social media variables;

determining values for the social media variables based on the sets of keywords and phrases assigned to the aggregated social media variables; and

determining values for the aggregated social media variables using the values for the social media variables.

4. The system of claim 3, wherein the aggregator determines the values for the aggregated social media variables by scaling the values for the social media variables, and combining the scaled values for the social media variables to determine the values for the aggregated social media variables.

5. The system of claim 4, wherein the aggregator determines the scaled values for the social media variables based on the weightings for the social media variables.

6. The system of claim 3, wherein the social media variables includes message level social media variables, and the values for each of the message level social media variables are calculated based on keywords and phrases identified in each message in the topic.

7. The system of claim 3, wherein the social media variables include topic level social media variables, and the values for each of the topic level social media variables are calculated based on information for all the messages in the topic.

8. The system of claim 1, further comprising:

a modeling engine determining a model using the aggregated social media variables, wherein the model is a mixed model including variables for multiple marketing channels.

9. The system of claim 8, wherein the aggregator determines a periodic time series of values for the aggregated social media variables for the model.

10. The system of claim 1, further comprising:

a listening tool collecting the information from the social media applications via the Internet.

11. The system of claim 1, wherein the aggregated social media variables comprise positive, neutral and negative, and each of the aggregated social media variables describes an attitude of users of the social media applications for the social media variables.

12. A method of determining aggregated social media variables comprising:

determining keywords and phrases;

receiving information collected from social media applications via the Internet using the keywords and phrases;

determining values for social media variables from the collected information; and

aggregating, by a computer system, the social media variables based on the values and weightings of the social media variables.

13. The method of claim 12, wherein aggregating the social media variables comprises:

determining categories, subcategories for each category, and topics for each subcategory associated with a product;

determining values for aggregated social media variables for each topic;

summing the values for each of the aggregated social media variables for each topic in each subcategory;

using econometrics to determine aggregation weights for the subcategories; and

combining the summed values for each subcategory using the aggregation weights to determine aggregated social media variable values for each category.

14. The method of claim 13, wherein determining values for aggregated social media variables for each topic comprises:

determining, from the keywords and phrases, a set of keywords and phrases assigned to each of the aggregated social media variables;

determining values for the social media variables based on the sets of keywords and phrases assigned to the aggregated social media variables; and

determining values for the aggregated social media variables using the values for the social media variables.

15. The method of claim 14, wherein determining the values for the aggregated social media variables comprises:

scaling the values for the social media variables; and

combining the scaled values for the social media variables to determine the values for the aggregated social media variables.

16. The method of claim 15, wherein the scaled values for the social media variables are based on the weightings for the social media variables.

17. The method of claim 14, wherein the social media variables includes message level social media variables and determining values for the social media variables comprises:

calculating the values for the message level social media variables based on keywords and phrases identified in each message in the topic.

18. The method of claim 14, wherein the social media variables include topic level social media variables and determining values for the social media variables comprises:

calculating the values for the topic level social media variables based on information for all the messages in the topic.

19. The method of claim 12, further comprising:

determining a model using the aggregated social media variables.

20. A non-transitory computer readable medium storing a computer program that when executed by a computer system performs a method of determining aggregated variables for model building, the method comprising:

collecting information for variables;

determining values for the variables from the collected information; and

aggregating, by a computer system, the variables based on the values and weightings of the variables.