Systems and methods for classifying media according to user negative propensities

1. A system for classifying media according to user for addictive behavior, the system comprising a computing device, the computing device further configured to:

obtain a physiological state data as a function of a physical sample;

identify a user propensity for addictive behavior associated with a human subject as a function of the physiological state data and a behavior model, wherein the user propensity for addictive behavior identifies an addictive behavior from a predetermined plurality of addictive behaviors;

generate, using thematic training data including a plurality of media items and a plurality of correlated items, and using a classification algorithm, a media theme classifier,

wherein the media theme classifier inputs media items and outputs principal themes of the media item;

receive a media item to be transmitted to a device operated by the human subject;

identify, using the media theme classifier, a principal theme of the media item,

wherein identifying the principal theme further comprises:

extracting, from the media item, a plurality of media item content elements;

classifying each content element of the plurality of media item content elements to a media item object of a plurality of media item objects using an object classifier; and

inputting the plurality of objects to the media theme classifier; and

determine if the principal theme matches the user propensity for addictive behavior.

2. The system of claim 1 , wherein the computing device is further configured to identify the user propensity for addictive behavior by:

generating, using a first feature learning algorithm, in training data containing a plurality of pairs of physiological data sets and propensities for addictive behavior, a behavioral model correlating physiological data sets with propensities for addictive behavior;

receiving a biological extraction of a human subject; and

identifying, using the biological extraction and the behavioral model, the user propensity for addictive behavior.

3. The system of claim 2 , wherein the first feature learning algorithm further comprises a k-means clustering algorithm.

4. The system of claim 2 , wherein the classification algorithm further comprises a k-nearest neighbors classification algorithm.

5. The system of claim 1 , wherein the computing device is further configured to generate the media theme classifier by:

extracting, from each media item, a plurality of training item content elements;

classifying each content element of the plurality of training item content elements to a training item object of a plurality of training item objects using the object classifier; and

replacing the media item with the plurality of training item objects in the thematic training data.

6. The system of claim 5 , wherein the object classifier further comprises a visual object classifier, and the computing device is further configured to:

extract the plurality of training item content elements by extracting a plurality of geometric forms from a visual component of the media item; and

classify the plurality of geometric forms using the visual object classifier.

7. The system of claim 5 , wherein the object classifier further comprises a linguistic object classifier, and the computing device is further configured to:

extract the plurality of training item content elements by extracting a plurality of textual elements from a verbal component of the media item; and

classify the plurality of textual elements using the linguistic object classifier.

8. The system of claim 1 , wherein the computing device is further configured to determine if the principal theme matches the user propensity for addictive behavior by:

matching the principal theme to the user propensity for addictive behavior; and

blocking transmission of the media item to the device.

9. The system of claim 1 , wherein the computing device is further configured to:

extract, from the media item, a plurality of content elements;

determine that the principal theme does not match the user propensity for addictive behavior;

classify each content element of the plurality of content elements to an object of a plurality of objects using an object classifier; and

determine that an object of the plurality of objects matches the user propensity for addictive behavior.

10. The system of claim 9 , wherein the computing device is further configured to:

receive, from a remote device, an indication that the human subject is engaging in a problematic behavior associated with the user propensity for addictive behavior; and

block transmission of the media to the device operated by the human subject.

11. A method of classifying media according to user propensities for addictive behavior, the method comprising:

obtaining, by the computing device, a physiological state data as a function of a physical sample;

identifying, by the computing device, a user propensity for addictive behavior associated with a human subject as a function of the physiological state data and a behavior model, wherein the user propensity for addictive behavior identifies an addictive behavior from a predetermined plurality of addictive behaviors;

generating, by the computing device using thematic training data including a plurality of media items and a plurality of correlated items, and using a classification algorithm, a media theme classifier, wherein the media theme classifier inputs media items and outputs principal themes of the media item;

receiving, by the computing device, a media item to be transmitted to a device operated by the human subject;

identifying, by the computing device and using the media theme classifier, a principal theme of the media item, wherein identifying the principal theme further comprises:

extracting, from the media item, a plurality of media item content elements;

classifying each content element of the plurality of media item content elements to a media item object of a plurality of media item objects using an object classifier; and

inputting the plurality of objects to the media theme classifier; and

determining, by the computing device, if the principal theme matches the user propensity for addictive.

12. The method of claim 11 , wherein the identifying the user propensity for addictive behavior further comprises:

generating, using a first feature learning algorithm, in training data containing a plurality of pairs of genetic sequences and propensities for addictive behavior, a genetic behavioral model correlating gene combinations with propensities for addictive behavior;

receiving a genetic sequence, wherein the genetic sequence further comprises a series of genes identified in a nucleotide sequence of chromosomal nucleic acid of a human subject; and

identifying, using the genetic sequence and the genetic behavioral model, the user propensity for addictive behavior.

13. The method of claim 12 , wherein the first feature learning algorithm further comprises a k-means clustering algorithm.

14. The method of claim 12 , wherein the classification algorithm further comprises a k-nearest neighbors classification algorithm.

15. The method of claim 11 , wherein generating the media theme classifier further comprises:

extracting, from each media item, a plurality of training item content elements;

classifying each content element of the plurality of training item content elements to a training item object of a plurality of training item objects using the object classifier; and

replacing the media item with the plurality of training item objects in the thematic training data.

16. The method of claim 15 , wherein the object classifier further comprises a visual object classifier, and classifying each element further comprises:

extracting the plurality of training item content elements by extracting a plurality of geometric forms from a visual component of the media item; and

classifying each geometric form of the plurality of geometric forms using the visual object classifier.

17. The method of claim 15 , wherein the object classifier further comprises a linguistic object classifier, and classifying each element further comprises:

extracting the plurality of training item content elements by extracting a plurality of textual elements from a verbal component of the media item; and

classifying each textual element of the plurality of textual elements using the linguistic object classifier.

18. The method of claim 11 , wherein determining if the principal theme matches the user propensity for addictive behavior further comprises:

matching the principal theme to the user propensity for addictive behavior; and

blocking transmission of the media item to the device.

19. The method of claim 11 further comprising:

extracting, from the media item, a plurality of content elements;

determining that the principal theme does not match the user propensity for addictive behavior;

classifying each content element of the plurality of content elements to an object of a plurality of objects using an object classifier; and

determining that an object of the plurality of objects matches the user propensity for addictive behavior.

20. The method of claim 19 further comprising:

receiving, from a remote device, an indication that the human subject is engaging in a problematic behavior associated with the user propensity for addictive behavior; and

blocking transmission of the media to the device operated by the human subject.