Midroll breaks feedback system

1 . A computer-implemented method comprising:

accessing, by a processor of a content server, a media item comprising visible content;

identifying, by the processor using a machine learning algorithm, a plurality of candidate break points in the media item, wherein the machine learning algorithm produces a plurality of confidence values respectively associated with the plurality of candidate break points, and wherein each confidence value indicates a likelihood that the corresponding candidate break point is an appropriate location for inclusion of a content item;

selecting, by the processor from the plurality of candidate break points, a break point in the media item, the break point being associated with a first point in time within the media item;

providing the media item to a plurality of devices, wherein each of the plurality of devices presents (i) the media item and (ii) the content item at the first point in time within the media item during playback of the media item;

after providing the media item to the plurality of devices, determining, by the processor based on data indicating how the media item and the content item are viewed by users when presented via the plurality of devices, to adjust the break point from the first point in time to a second point in time within the media item, wherein the second point in time is different from the first point in time;

adjusting, by the processor, a position of the break point from the first point in time to the second point in time; and

after adjusting the position of the break point, providing the media item to an additional device, wherein the additional device presents (i) the media item and (ii) the content item at the second point in time within the media item during playback of the media item.

2 . The computer-implemented method of claim 1 , wherein adjusting the position of the break point comprises:

selecting, by the processor from the plurality of candidate break points, a second break point that aligns with the second point in time.

3 . The computer-implemented method of claim 1 , wherein determining to adjust the break point in the media item comprises:

determining, by the processor based on the data indicating how the media item and the content item are viewed by users when presented via the plurality of devices and the plurality of confidence values respectively associated with the plurality of candidate break points, to adjust the break point from the first point in time to the second point in time within the media item, wherein the second point in time is different from the first point in time.

4 . The computer-implemented method of claim 1 , wherein identifying the break point in the media item comprises:

identifying, by the processor using the machine learning algorithm, a scene change in the media item.

5 . The computer-implemented method of claim 1 , wherein identifying the break point in the media item comprises:

identifying, by the processor using the machine learning algorithm, a break in dialogue in the media item.

6 . The computer-implemented method of claim 1 , wherein adjusting the position of the break point comprises:

after determining to adjust the break point, automatically adjusting, by the processor, the position of the break point.

7 . The computer-implemented method of claim 1 , wherein adjusting the position of the break point comprises:

presenting, via an electronic device of a user, an indication of an adjustment to the break point in the media item;

receiving, via the electronic device, an acceptance to adjust the break point; and

after receiving the acceptance to adjust the break point, adjusting the position of the break point.

8 . A system for managing break points in a media item, the system comprising:

a memory storing data associated with a machine learning algorithm; and

at least one processor interfacing with the memory and configured to:

access the media item comprising visible content,

identify, using the machine learning algorithm, a plurality of candidate break points in the media item, wherein the machine learning algorithm produces a plurality of confidence values respectively associated with the plurality of candidate break points, and wherein each confidence value indicates a likelihood that the corresponding candidate break point is an appropriate location for inclusion of a content item,

select, from the plurality of candidate break points, a break point in the media item, the break point being associated with a first point in time within the media item,

provide the media item to a plurality of devices, wherein each of the plurality of devices presents (i) the media item and (ii) a content item at the first point in time within the media item during a playback of the media item,

after providing the media item to the plurality of devices, determine, based on data indicating how the media item and the content item are viewed by users when presented via the plurality of devices, to adjust the break point from the first point in time to a second point in time within the media item, wherein the second point in time is different from the first point in time,

adjust a position of the break point from the first point in time to the second point in time, and

after adjusting the position of the break point, provide the media item to an additional device, wherein the additional device presents (i) the media item and (ii) the content item at the second point in time within the media item during playback of the media item.

9 . The system of claim 8 , wherein to adjust the position of the break point, the at least one processor is configured to:

select, from the plurality of candidate break points, a second break point that aligns with the second point in time.

10 . The system of claim 8 , wherein to determine to adjust the break point in the media item, the at least one processor is configured to:

determine, based on the data indicating how the media item and the content item are viewed by users when presented via the plurality of devices and the plurality of confidence values respectively associated with the plurality of candidate break points, to adjust the break point from the first point in time to the second point in time within the media item, wherein the second point in time is different from the first point in time.

11 . The system of claim 8 , wherein to identify the break point in the media item, the at least one processor is configured to:

identify, using the machine learning algorithm, a scene change in the media item.

12 . The system of claim 8 , wherein to identify the break point in the media item, the at least one processor is configured to:

identify, using the machine learning algorithm, a break in dialogue in the media item.

13 . The system of claim 8 , wherein to adjust the position of the break point, the at least one processor is configured to:

after determining to adjust the break point, automatically adjust the position of the break point.

14 . The system of claim 8 , wherein to adjust the position of the break point, the at least one processor is configured to:

present, via an electronic device of a user, an indication of an adjustment to the break point in the media item,

receive, via the electronic device, an acceptance to adjust the break point, and

after receiving the acceptance to adjust the break point, adjust the position of the break point.