Method and apparatus for detecting fake news in a social media network

1. A method applied to a plurality of messages in a social media network, the method comprising:

transmitting the plurality of messages in the social media network;

receiving essential characteristics of social media network users in the social media network, the essential characteristics representing both local proximity and community structures detected within the social media network including an average distance between nodes and community-wise similarity among the social media network users within the local proximity and community structures detected;

classifying propagation pathways each comprising a sequence of users via which the plurality of messages are transmitted through the social media network;

determining a spreader of the plurality of messages spread on the social media network and classifying the plurality of messages based on (i) which social media network user spread the plurality of messages and (ii) when the social media network user spread the plurality of messages; and

taking an action on one or more of the plurality of messages that are transmitted through the social media network based on the classification of the propagation pathways via which the plurality of messages are transmitted through the social media network and the received essential characteristics of the social media network users including the social media network user determined to be the spreader of the plurality of messages; and

wherein taking the action on the one or more of the plurality of messages that are transmitted through the social media network based on the classification of the propagation pathways, comprises filtering out the one or more of the plurality of messages that are transmitted in the social media network over a propagation pathway that is classified as a fake news propagation pathway.

2. The method of claim 1 , wherein receiving essential characteristics of social media network users in the social media network comprises receiving essential characteristics of social media network users using Large-Scale Information Network Embedding (LINE) and incorporating community information.

3. The method of claim 1 , wherein classifying propagation pathways each comprising a sequence of users via which the plurality of messages are transmitted through the social media network comprises classifying the propagation pathways utilizing a Long Short-Term Memory Recurrent Neural Network (LSTM-RNN).

4. The method of claim 1 , wherein classifying propagation pathways each comprising a sequence of users via which the plurality of messages are transmitted through the social media network comprises classifying the propagation pathways as one of: a pathway for spreading fake news or spam, and a pathway for spreading real news.

5. A system applied to a plurality of messages in a social media network, the system comprising:

a processor to execute software instructions;

a storage device in which to store the social media data;

software instructions that when executed by the processor cause the system to:

transmit the plurality of messages in the social media network;

receive essential characteristics of social media network users in the social media network, the essential characteristics representing both local proximity and community structures detected within the social media network including an average distance between nodes and community-wise similarity among the social media network users within the local proximity and community structures detected;

classify propagation pathways each comprising a sequence of users via which the plurality of messages are transmitted through the social media network;

determine a spreader of the plurality of messages spread on the social media network and classify the plurality of messages based on (i) which social media network user spread the plurality of messages and (ii) when the social media network user spread the plurality of messages; and

take an action on one or more of the plurality of messages that are transmitted through the social media network based on the classification of the propagation pathways via which the plurality of messages are transmitted through the social media network and the received essential characteristics of the social media network users including the social media network user determined to be the spreader of the plurality of messages; and

wherein taking the action on the one or more of the plurality of messages that are transmitted through the social media network based on the classification of the propagation pathways, comprises filtering out the one or more of the plurality of messages that are transmitted in the social media network over a propagation pathway that is classified as a fake news propagation pathway.

6. The system of claim 5 , wherein the software instructions that when executed by the processor cause the system to receive essential characteristics of social media network users in the social media network comprise software instructions that when executed by the processor cause the system to receive essential characteristics of social media network users using Large-Scale Information Network Embedding (LINE) and incorporating community information.

7. The system of claim 5 , wherein the software instructions that when executed by the processor cause the system to classify propagation pathways each comprising a sequence of users via which the plurality of messages are transmitted through the social media network comprises software instructions that when executed by the processor cause the system to classify the propagation pathways utilizing a Long Short-Term Memory Recurrent Neural Network (LSTM-RNN).

8. The system of claim 5 , wherein the software instructions that when executed by the processor cause the system to classify propagation pathways each comprising a sequence of users via which the plurality of messages are transmitted through the social media network comprises software instructions that when executed by the processor cause the system to classify the propagation pathways as one of: a pathway for spreading fake news or spam, and a pathway for spreading real news.

9. Non-transitory computer-readable storage media having instructions stored thereupon that, when executed a system having at least a processor and a memory therein, the instructions cause the system to perform operations comprising:

transmitting the plurality of messages in the social media network;

receiving essential characteristics of social media network users in the social media network, the essential characteristics representing both local proximity and community structures detected within the social media network including an average distance between nodes and community-wise similarity among the social media network users within the local proximity and community structures detected;

classifying propagation pathways each comprising a sequence of users via which the plurality of messages are transmitted through the social media network;

determining a spreader of the plurality of messages spread on the social media network and classifying the plurality of messages based on (i) which social media network user spread the plurality of messages and (ii) when the social media network user spread the plurality of messages; and

taking an action on one or more of the plurality of messages that are transmitted through the social media network based on the classification of the propagation pathways via which the plurality of messages are transmitted through the social media network and the received essential characteristics of the social media network users including the social media network user determined to be the spreader of the plurality of messages; and

wherein taking the action on the one or more of the plurality of messages that are transmitted through the social media network based on the classification of the propagation pathways, comprises filtering out the one or more of the plurality of messages that are transmitted in the social media network over a propagation pathway that is classified as a fake news propagation pathway.

10. The non-transitory computer-readable storage media of claim 9 , wherein receiving essential characteristics of social media network users in the social media network comprises receiving essential characteristics of social media network users using Large-Scale Information Network Embedding (LINE) and incorporating community information.

11. The non-transitory computer-readable storage media of claim 9 , wherein classifying propagation pathways each comprising a sequence of users via which the plurality of messages are transmitted through the social media network comprises classifying the propagation pathways utilizing a Long Short-Term Memory Recurrent Neural Network (LSTM-RNN).

12. The non-transitory computer-readable storage media of claim 9 , wherein classifying propagation pathways each comprising a sequence of users via which the plurality of messages are transmitted through the social media network comprises classifying the propagation pathways as one of: a pathway for spreading fake news or spam, and a pathway for spreading real news.