Cultural distance prediction system for media asset

1 . A system for dynamic advertisement placement comprising:

a memory storing instructions; and

one or more hardware processors communicatively coupled to the memory and configured by the instructions to perform operations comprising:

accessing content data for a media asset;

generating a scene graph for the media asset that provides details on one or more emotional highs or emotional lows in the content data, each scene comprising one or more events, and each event being determined by analyzing at least one of an audio content element, a visual content element, or a textual content element within the content data;

analyzing the scene graph to identify a set of peak emotional events within the content data;

creating a set of time-based markers that correspond to time-code ranges of the set of peak emotional events; and

providing the set of time-based markers and other deep metadata to a video streaming platform, the video streaming platform determining a set of advertisement placement positions within the media asset at moments that would incur greatest impact based on the one or more emotional highs or emotional lows in the content data,

wherein the media asset corresponds to a culture of origin and a culture of destination, and wherein the operations comprise:

determining an event of the set of peak emotional events at a timestamp within the content data of the media asset, the event of the set of peak emotional events being relevant to a cultural attribute category and corresponding to one of the one or more emotional highs or emotional lows in the content data;

identifying a first geographical region corresponding to the culture of origin and a second geographical region corresponding to the culture of destination;

accessing a first weight value of the cultural attribute category associated with the first geographical region;

accessing a second weight value of the cultural attribute category associated with the second geographical region;

using machine learning algorithm to generate a cultural distance score of the event of the set of peak emotional events based on the first weight value, the second weight value, and context data of the event of the set of peak emotional events; and

causing display of the cultural distance score of the media asset on a user interface of a client device.

2 . The system of claim 1 , wherein the other deep metadata comprises at least one of mood information, theme information, time period information, location information, event information, objectionable content information, or character information associated with the media asset.

3 . The system of claim 1 , wherein the audio content element comprises at least one a speech, music, or a background noise.

4 . The system of claim 1 , wherein the textual content element comprises at least one subtitles.

5 . The system of claim 1 , wherein the using of the machine learning algorithm to generate the cultural distance score of the event of the set of peak emotional events comprises:

identifying a third weight value based on the context data of the event of the set of peak emotional events, the context data describing content of the event of the set of peak emotional events the third weight value being associated with the second geographical region; and

applying the first weight value and the second weight value to the third weight value to generate the cultural distance score.

6 . The system of claim 1 , wherein the first geographical region is a region where the media asset is generated, and wherein the second geographical region is a region where the media asset is targeted for release.

7 . A method for dynamic advertisement placement comprising:

accessing, by a hardware processor, content data for a media asset;

generating, by the hardware processor, a scene graph for the media asset that provides details on one or more emotional highs or emotional lows in the content data, each scene comprising one or more events, and each event being determined by analyzing at least one of an audio content element, a visual content element, or a textual content element within the content data;

analyzing, by the hardware processor, the scene graph to identify a set of peak emotional events within the content data;

creating, by the hardware processor, a set of time-based markers that correspond to time-code ranges of the set of peak emotional events; and

providing, by the hardware processor, the set of time-based markers and other deep metadata to a video streaming platform, the video streaming platform determining a set of advertisement placement positions within the media asset at moments that would incur greatest impact based on the one or more emotional highs or emotional lows in the content data,

wherein the media asset corresponds to a culture of origin and a culture of destination, and wherein the method comprises:

determining an event of the set of peak emotional events at a timestamp within the content data of the media asset, the event of the set of peak emotional events being relevant to a cultural attribute category and corresponding to one of the one or more emotional highs or emotional lows in the content data;

identifying a first geographical region corresponding to the culture of origin and a second geographical region corresponding to the culture of destination;

accessing a first weight value of the cultural attribute category associated with the first geographical region;

accessing a second weight value of the cultural attribute category associated with the second geographical region;

using machine learning algorithm to generate a cultural distance score of the event of the set of peak emotional events based on the first weight value, the second weight value, and context data of the event of the set of peak emotional events; and

causing display of the cultural distance score of the media asset on a user interface of a client device.

8 . The method of claim 7 , wherein the other deep metadata comprises at least one of mood information, theme information, time period information, location information, event information, objectionable content information, or character information associated with the media asset.

9 . The method of claim 7 , wherein the audio content element comprises at least one a speech, music, or a background noise.

10 . The method of claim 7 , wherein the textual content element comprises at least one subtitles.

11 . The method of claim 7 , wherein the using of the machine learning algorithm to generate the cultural distance score of the event of the set of peak emotional events comprises:

identifying a third weight value based on the context data of the event of the set of peak emotional events, the context data describing content of the event of the set of peak emotional events the third weight value being associated with the second geographical region; and

applying the first weight value and the second weight value to the third weight value to generate the cultural distance score.

12 . The method of claim 7 , wherein the first geographical region is a region where the media asset is generated, and wherein the second geographical region is a region where the media asset is targeted for release.

13 . A non-transitory computer-readable medium comprising instructions that, when executed by a hardware processor of a device, cause the device to perform operations comprising:

accessing content data for a media asset;

generating a scene graph for the media asset that provides details on one or more emotional highs or emotional lows in the content data, each scene comprising one or more events, and each event being determined by analyzing at least one of an audio content element, a visual content element, or a textual content element within the content data;

analyzing the scene graph to identify a set of peak emotional events within the content data;

creating a set of time-based markers that correspond to time-code ranges of the set of peak emotional events; and

providing the set of time-based markers and other deep metadata to a video streaming platform, the video streaming platform determining a set of advertisement placement positions within the media asset at moments that would incur greatest impact based on the one or more emotional highs or emotional lows in the content data,

wherein the media asset corresponds to a culture of origin and a culture of destination, and wherein the operations comprise:

determining an event of the set of peak emotional events at a timestamp within the content data of the media asset, the event of the set of peak emotional events being relevant to a cultural attribute category and corresponding to one of the one or more emotional highs or emotional lows in the content data;

identifying a first geographical region corresponding to the culture of origin and a second geographical region corresponding to the culture of destination;

accessing a first weight value of the cultural attribute category associated with the first geographical region;

accessing a second weight value of the cultural attribute category associated with the second geographical region;

using machine learning algorithm to generate a cultural distance score of the event of the set of peak emotional events based on the first weight value, the second weight value, and context data of the event of the set of peak emotional events; and

causing display of the cultural distance score of the media asset on a user interface of a client device.

14 . The non-transitory computer-readable medium of claim 13 , wherein the other deep metadata comprises at least one of mood information, theme information, time period information, location information, event information, objectionable content information, or character information associated with the media asset.

15 . The non-transitory computer-readable medium of claim 13 , wherein the audio content element comprises at least one a speech, music, or a background noise.

16 . The non-transitory computer-readable medium of claim 13 , wherein the textual content element comprises at least one subtitles.

17 . The non-transitory computer-readable medium of claim 13 , wherein the using of the machine learning algorithm to generate the cultural distance score of the event of the set of peak emotional events comprises:

identifying a third weight value based on the context data of the event of the set of peak emotional events, the context data describing content of the event of the set of peak emotional events the third weight value being associated with the second geographical region; and

applying the first weight value and the second weight value to the third weight value to generate the cultural distance score.