Organizing media content items utilizing detected scene types

A non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause a computing device to:

• identify a plurality of video files;
• identify a set of scene types;
• utilize a machine learning model to identify, based on video data from the plurality of video files and corresponding transcripts for the plurality of video files, mappings between a plurality of video segments, from the plurality of video files, to one or more scene types from the set of scene types;
• generate a plurality of collection objects corresponding to the set of scene types;
• and
• store video segments from the plurality of video segments in association with collection objects from the plurality of collection objects based on the mappings between the plurality of video segments and the one or more scene types from the set of scene types.

A system comprising:

• at least one processor;
• and
• at least one non-transitory computer-readable storage medium storing instructions that, when executed by the at least one processor, cause the system to:
• identify a video file;
• identify a set of scene types;
• utilize a machine learning model to identify, based on video data from the video file and a transcript for the video file, a mapping between a video segment, from the video file, to a scene type from the set of scene types;
• generate a collection object corresponding to the scene type;
• and
• provide, for display within a graphical user interface, the collection object to portray the video segment based on the mapping between the video segment and the scene type from the set of scene types.