Simulation to find user behavior impact in social media network

• US 9,485,319 B1
• Filed: 12/30/2015
• Issued: 11/01/2016
• Est. Priority Date: 12/30/2015
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Cavalin, Paulo R., Gatti De Bayser, Maira, Dos Santos, Cicero N., Valladao, Davi M.
• Primary Examiner(s): Nguyen, Angela
• Application Number:
  US14/984,593
• Time in Patent Office: 307 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: H04L 67/306 User profiles
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34

Abstract

Provided is a mechanism which may use a real Online Social Network (OSN) to simulate user behavior based on what the user(s) post in order to analyze how the information is spread across a network. In various embodiments, the disclosed mechanisms may be implemented via systems, methods and/or computer program products.

Claims

1. A computer-implemented method for determining an impact of a behavior of at least one user in a social media network, the method comprising:

obtaining, by a processor, at least one characteristic describing the behavior of the user in a simulation of the social media network;

determining by the processor, via use of a time series based modeler which uses a linear regression method, a first function of the at least one characteristic, wherein the first function describes a first model of a behavior of the simulated social media network with respect to time;

changing, by the processor, the at least one characteristic to obtain at least one changed characteristic;

determining by the processor, via use of a time series based modeler which uses a linear regression method, a second function of the at least one changed characteristic, wherein the second function describes a second model of the behavior of the simulated social media network with respect to time;

comparing, by the processor, the first function and the second function over time by using a linear or non-linear least squares method to determine at least one difference in at least one impact duration of time, the at least one impact duration of time being an amount of time during which a volume of messages associated with the second function differs, after a point of substantial equality, from a volume of messages associated with the first function;

determining, by the processor, a simulated amount of an effect of the difference in at least one impact duration of time at each of a plurality of nodes within one or more levels of the social media network; and

outputting, by the processor, data indicative of the determined simulated amount of the effect of the difference in at least one impact duration of time at each of the plurality of nodes within one or more levels of the social media network.

2. The method of claim 1, wherein the at least one characteristic comprises at least one of:

(a) a volume of messages of a particular topic that describes the behavior of the user;

(b) a volume of messages of a particular sentiment that describes the behavior of the user; and

(c) any combination thereof.

3. The method of claim 1, wherein the at least one characteristic comprises a plurality of characteristics, each of the plurality of characteristics corresponding to each of a plurality of behaviors of the user.

4. The method of claim 1, wherein the at least one characteristic comprises at least one characteristic for each of a plurality of users, each characteristic associated with a respective user corresponding to each of a plurality of behaviors of the respective user.

5. The method of claim 1, wherein the determining the simulated amount of the effect of the difference in the at least one impact duration of time at each of the plurality of nodes is performed by using a network analyzer.

6. The method of claim 1, wherein the determining the simulated amount of the effect of the difference in the at least one impact duration of time at each of the plurality of nodes comprises measuring a depth of the effect based on a distance between a source of an action and each user who reacted to that action during the observed time of impact.

7. The method of claim 1, wherein the time series based modeler which uses the linear regression method to determine the first function is the same as the time series based modeler which uses the linear regression method to determine the second function.

8. The method of claim 1, wherein the time series based modeler which uses the linear regression method to determine the first function is different from the time series based modeler which uses the linear regression method to determine the second function.

9. The method of claim 1, wherein the at least one impact duration of time is the amount of time during which the volume of messages associated with the second function is greater, after the point of substantial equality, than the volume of messages associated with the first function.

10. The method of claim 2, wherein the sentiment is selected from the group of:

(a) positive;

(b) negative; and

(c) neutral.

11. The method of claim 4, wherein the at least one characteristic for each of the plurality of users comprises a plurality of characteristics for each of the users, each of the plurality of characteristics associated with a respective user corresponding to each of a plurality of behaviors of the respective user.

12. The method of claim 5, wherein the network analyzer determines the simulated amount of the effect of the difference in the at least one impact duration of time at each of the plurality of nodes by reacting to the characteristic being observed.

13. A non-transitory computer readable storage medium, tangibly embodying a program of instructions executable by the computer for determining an impact of a behavior of at least one user in a social media network, the program of instructions, when executing, performing the following steps:

obtaining at least one characteristic describing the behavior of the user in a simulation of the social media network;

determining, via use of a time series based modeler which uses a linear regression method, a first function of the at least one characteristic, wherein the first function describes a first model of a behavior of the simulated social media network with respect to time;

changing the at least one characteristic to obtain at least one changed characteristic;

determining, via use of a time series based modeler which uses a linear regression method, a second function of the at least one changed characteristic, wherein the second function describes a second model of the behavior of the simulated social media network with respect to time;

comparing the first function and the second function over time by using a linear or non-linear least squares method to determine at least one difference in at least one impact duration of time, the at least one impact duration of time being an amount of time during which a volume of messages associated with the second function differs, after a point of substantial equality, from a volume of messages associated with the first function;

determining a simulated amount of an effect of the difference in at least one impact duration of time at each of a plurality of nodes within one or more levels of the social media network; and

outputting data indicative of the determined simulated amount of the effect of the difference in at least one impact duration of time at each of the plurality of nodes within one or more levels of the social media network.

14. The non-transitory computer readable storage medium of claim 13, wherein the determining the simulated amount of the effect of the difference in the at least one impact duration of time at each of the plurality of nodes is performed by using a network analyzer.

15. The non-transitory computer readable storage medium of claim 13, wherein the at least one impact duration of time is the amount of time during which the volume of messages associated with the second function is greater, after the point of substantial equality, than the volume of messages associated with the first function.

16. The non-transitory computer readable storage medium of claim 14, wherein the network analyzer determines the simulated amount of the effect of the difference in the at least one impact duration of time at each of the plurality of nodes by reacting to the characteristic being observed.

17. A computer-implemented system for determining an impact of a behavior of at least one user in a social media network, the system comprising:

a processor; and

a memory storing computer readable instructions that, when executed by the processor, implement steps of;

obtaining at least one characteristic describing the behavior of the user in a simulation of the social media network;

determining, via use of a time series based modeler which uses a linear regression method, a first function of the at least one characteristic, wherein the first function describes a first model of a behavior of the simulated social media network with respect to time;

changing the at least one characteristic to obtain at least one changed characteristic;

determining, via use of a time series based modeler which uses a linear regression method, a second function of the at least one changed characteristic, wherein the second function describes a second model of the behavior of the simulated social media network with respect to time;

comparing the first function and the second function over time by using a linear or non-linear least squares method to determine at least one difference in at least one impact duration of time, the at least one impact duration of time being an amount of time during which a volume of messages associated with the second function differs, after a point of substantial equality, from a volume of messages associated with the first function;

determining a simulated amount of an effect of the difference in at least one impact duration of time at each of a plurality of nodes within one or more levels of the social media network; and

outputting data indicative of the determined simulated amount of the effect of the difference in at least one impact duration of time at each of the plurality of nodes within one or more levels of the social media network.

18. The system of claim 17, wherein the outputting is configured to output the data to at least one of:

(a) a display;

(b) a hardcopy printer;

(c) a data storage device; and

(d) any combination thereof.

19. The system of claim 17, wherein the determining the simulated amount of the effect of the difference in the at least one impact duration of time at each of the plurality of nodes is performed by using a network analyzer.

20. The system of claim 17, wherein the at least one impact duration of time is the amount of time during which the volume of messages associated with the second function is greater, after the point of substantial equality, than the volume of messages associated with the first function.