Video playlists and recommendations based on electronic messaging communications

1. A method comprising:

receiving, by a first user device executing a messaging application, a first message from a second user device;

determining, by the first user device that is associated with a user, whether the first message includes a first reference to a first media item;

responsive to determining that the first message includes the first reference to the first media item, generating, by the first user device, media playlist information identifying the first media item; and

sending, by the first user device, the media playlist information identifying the first media item to a content sharing platform hosting a plurality of media items that comprise the first media item, the first media item to be added to a media playlist that groups different media items for playback and that is maintained by the content sharing platform, wherein the media playlist information comprises information to identify, among a plurality of media playlists maintained by the content sharing platform, the media playlist to which the first media is to be added.

2. The method of claim 1 , wherein the first media item is a video item.

3. The method of claim 1 , wherein the first media item identified in the media playlist information sent to the content sharing platform is to be recommended to the user associated with the first user device by the content sharing platform.

4. The method of claim 1 , further comprising:

receiving, from a third user device executing a third instance of the messaging application, a second message;

determining whether the second message includes a second reference to a second media item; and

responsive to determining that the second message includes the second reference to the second media item, updating the media playlist information to identify the second media item.

5. The method of claim 1 , wherein determining whether the first message includes the first reference to the first media item comprises:

parsing the first message to identify a link;

identifying a uniform resource locator (URL) associated with the link; and

determining that the URL is associated with the content sharing platform hosting the first media item.

6. The method of claim 1 , wherein generating the media playlist information identifying the first media item comprises:

determining whether the user has not interacted with the first reference to the first media item within a threshold amount of time; and

responsive to determining that the first message includes the first reference to the first media item and the user has not interacted with the first reference to the first media item within the threshold amount of time, generating the media playlist information identifying the first media item.

7. The method of claim 1 , wherein generating the media playlist information identifying the first media item comprises:

responsive to determining that the first message includes the first reference to the first media item, identifying a user preference indicating conditions for generating the media playlist information;

determining whether the conditions indicated by the user preference have been satisfied; and

responsive to determining the conditions indicated by the user preference have been satisfied, generating the media playlist information identifying the first media item.

8. The method of claim 1 , wherein generating the media playlist information identifying the first media item comprises:

analyzing a conversation comprising the first message using a machine-learning language classifier;

determining a sentiment of the conversation based on the machine-learning language classifier;

responsive to determining the conversation is associated with a positive user sentiment, generating the media playlist information identifying the positive user sentiment; and

responsive to determining the conversation is associated with a negative user sentiment, refraining from generating the media playlist information for the first media item.

9. The method of claim 1 , wherein generating the media playlist information identifying the first media item comprises:

analyzing a conversation comprising the first message using a machine-learning language classifier;

determining a topic of the conversation based on the machine-learning language classifier; and

generating the media playlist information identifying the topic of the conversation.

10. The method of claim 1 , wherein generating the media playlist information identifying the first media item comprises:

determining a sending user associated with a conversation comprising the first message; and

generating the media playlist information identifying the sending user.

11. An apparatus comprising:

a memory device; and

a processing device, coupled to the memory device, to:

receive, by a first user device executing a messaging application using the processing device, a first message from a second user device;

determine, by the first user device associated with a user, whether the first message includes a first reference to a first media item;

responsive to determining that the first message includes the first reference to the first media item, generate, by the first user device, media playlist information identifying the first media item; and

send, by the first user device, the media playlist information identifying the first media item to a content sharing platform hosting a plurality of media items that comprise the first media item, the first media item to be added to a media playlist that groups different media items for playback and that is maintained by the content sharing platform, wherein the media playlist information comprises information to identify, among a plurality of media playlists maintained by the content sharing platform, the media playlist to which the first media is to be added.

12. The apparatus of claim 11 , wherein sending the first media item identified in the media playlist information sent to the content sharing platform is to be recommended to the user associated with the first user device by the content sharing platform.

13. The apparatus of claim 11 , wherein to generate the media playlist information identifying the first media item, the processing device further to:

determine whether the user has not interacted with the first reference to the first media item within a threshold amount of time; and

responsive to determining that the first message includes the first reference to the first media item and the user has not interacted with the first reference to the first media item within the threshold amount of time, generate the media playlist information identifying the first media item.

14. The apparatus of claim 11 , wherein to generate the media playlist information identifying the first media item, the processing device further to:

responsive to determining that the first message includes the first reference to the first media item, identify a user preference indicating conditions for generating the media playlist information;

determine whether the conditions indicated by the user preference have been satisfied; and

responsive to determining the conditions indicated by the user preference have been satisfied, generate the media playlist information identifying the first media item.

15. The apparatus of claim 11 , wherein to generate the media playlist information identifying the first media item, the processing device further to:

analyze a conversation comprising the first message using a machine-learning language classifier;

determine a sentiment of the conversation based on the machine-learning language classifier;

responsive to determining the conversation is associated with a positive user sentiment, generate the media playlist information identifying the positive user sentiment; and

responsive to determining the conversation is associated with a negative user sentiment, refrain from generating the media playlist information for the first media item.

16. The apparatus of claim 11 , wherein to generate the media playlist information identifying the first media item, the processing device further to:

analyze a conversation comprising the first message using a machine-learning language classifier;

determine a topic of the conversation based on the machine-learning language classifier; and

generate the media playlist information identifying the topic of the conversation.

17. A non-transitory computer-readable medium comprising instructions that, responsive to execution by a processing device, cause the processing device to perform operations comprising:

receiving, by a first user device executing a messaging application using the processing device, a first message from a second user device;

determining, by the first user device that is associated with a user, whether the first message includes a first reference to a first media item;

responsive to determining that the first message includes the first reference to the first media item, generating, by the first user device, media playlist information identifying the first media item; and

sending, by the first user device, the media playlist information identifying the first media item to a content sharing platform hosting a plurality of media items that comprise the first media item, the first media item to be added to a media playlist that groups different media items for playback and that is maintained by the content sharing platform, wherein the media playlist information comprises information to identify, among a plurality of media playlists maintained by the content sharing platform, the media playlist to which the first media is to be added.

18. The non-transitory computer-readable medium of claim 17 , wherein

sending the first media item identified in the media playlist information sent to the content sharing platform is to be recommended to the user associated with the first user device by the content sharing platform.

19. The non-transitory computer-readable medium of claim 17 , wherein determining whether the first message includes the first reference to the first media item comprises:

parsing the first message to identify a link;

identifying a uniform resource locator (URL) associated with the link; and

determining that the URL is associated with the content sharing platform hosting the first media item.

20. The non-transitory computer-readable medium of claim 17 , wherein generating the media playlist information identifying the first media item comprises:

determining whether the user has not interacted with the first reference to the first media item within a threshold amount of time; and

responsive to determining that the first message includes the first reference to the first media item and the user has not interacted with the first reference to the first media item within the threshold amount of time, generating the media playlist information identifying the first media item.