Matching video content to podcast episodes
A user input comprising a search term corresponding to a first media type is received. A first media item of the first media type is identified based on the search term. The first media item is associated with a first media item characteristic. A second media item of a second media type is identified. The second media item is associated with a second media item characteristic related to the first media item characteristic. A ranking of at least one of the second media item or the first media item reflects a correspondence between the second media item and the first media item based on a popularity indicator associated with the second media item and a popularity indicator associated with the first media item. The first media item and the second media item are provided to the user device based on the ranking.
1 . A method comprising:
receiving, from a user device, a user input comprising a search term corresponding to a first media type;
identifying, based on the search term, a first media item of the first media type, wherein the first media item is associated with a first media item characteristic;
identifying a second media item of a second media type, wherein the second media item is associated with a second media item characteristic related to the first media item characteristic, and wherein a ranking of at least one of the second media item or the first media item reflects a correspondence between the second media item and the first media item based on a popularity indicator associated with the second media item and a popularity indicator associated with the first media item; and
providing, to the user device, based on the ranking, the first media item of the first media type and the second media item of the second media type.
2 . The method of claim 1 , further comprising:
accessing a data store comprising a first plurality of first media items of the first media type, wherein the first plurality of first media items comprises the first media item.
3 . The method of claim 1 , wherein the first media item characteristic comprises at least one of: a first transcript of audio, a first audio content, a first title, a first description, a first duration, or a first publication date; and wherein the second media item characteristic comprises at least one of: a second transcript of audio, a second audio content, a second title, a second description, a second duration, or a second publication date.
4 . The method of claim 1 , wherein the second media item is received from a second user device.
5 . The method of claim 1 , wherein identifying the second media item comprises:
comparing the second media item characteristic to the first media item characteristic associated with each of a first plurality of first media items of the first media type;
determining, for each of the first plurality of first media items, a matching score based on the comparing; and
identifying the second media item that has a highest matching score, wherein the highest matching score satisfies a matching criterion.
6 . The method of claim 1 , wherein identifying the second media item comprises:
providing the first media item characteristic as input to a machine learning model trained to identify the second media item based on the second media item characteristic.
7 . The method of claim 1 , wherein the correspondence between the second media item and the first media item based on the popularity indicator associated with the second media item and the popularity indicator associated with the first media item reflects a combination of the popularity indicator associated with the second media item and the popularity indicator associated with the first media item.
8 . A system comprising:
a memory; and
a processing device communicably coupled to the memory, the processing device to:
receive, from a user device, a user input comprising a search term corresponding to a first media type;
identify, based on the search term, a first media item of the first media type, wherein the first media item is associated with a first media item characteristic;
identify a second media item of a second media type, wherein the second media item is associated with a second media item characteristic related to the first media item characteristic, and wherein a ranking of at least one of the second media item or the first media item reflects a correspondence between the second media item and the first media item based on a popularity indicator associated with the second media item and a popularity indicator associated with the first media item; and
provide, to the user device, based on the ranking, the first media item of the first media type and the second media item of the second media type.
9 . The system of claim 8 , wherein the processing device is further to:
access a data store comprising a first plurality of first media items of the first media type, wherein the first plurality of first media items comprises the first media item.
10 . The system of claim 8 , wherein the first media item characteristic comprises at least one of: a first transcript of audio, a first audio content, a first title, a first description, a first duration, or a first publication date; and wherein the second media item characteristic comprises at least one of: a second transcript of audio, a second audio content, a second title, a second description, a second duration, or a second publication date.
11 . The system of claim 8 , wherein the second media item is received from a second user device.
12 . The system of claim 8 , wherein to identify the second media item, the processing device is further to:
compare the second media item characteristic to the first media item characteristic associated with each of a first plurality of first media items of the first media type;
determine, for each of the first plurality of first media items, a matching score based on the comparing; and
identify the second media item that has a highest matching score, wherein the highest matching score satisfies a matching criterion.
13 . The system of claim 8 , wherein to identify the second media item, the processing device is further to:
provide the first media item characteristic as input to a machine learning model trained to identify the second media item based on the second media item characteristic.
14 . The system of claim 8 , wherein the correspondence between the second media item and the first media item based on the popularity indicator associated with the second media item and the popularity indicator associated with the first media item reflects a combination of the popularity indicator associated with the second media item and the popularity indicator associated with the first media item.
15 . A non-transitory machine-readable storage medium comprising instructions that cause a processing device to perform operations comprising:
receiving, from a user device, a user input comprising a search term corresponding to a first media type;
identifying, based on the search term, a first media item of the first media type, wherein the first media item is associated with a first media item characteristic;
identifying a second media item of a second media type, wherein the second media item is associated with a second media item characteristic related to the first media item characteristic, and wherein a ranking of at least one of the second media item or the first media item reflects a correspondence between the second media item and the first media item based on a popularity indicator associated with the second media item and a popularity indicator associated with the first media item; and
providing, to the user device, based on the ranking, the first media item of the first media type and the second media item of the second media type.
16 . The non-transitory machine-readable storage medium of claim 15 , wherein the operations further comprise:
accessing a data store comprising a first plurality of first media items of the first media type, wherein the first plurality of first media items comprises the first media item.
17 . The non-transitory machine-readable storage medium of claim 15 , wherein the first media item characteristic comprises at least one of: a first transcript of audio, a first audio content, a first title, a first description, a first duration, or a first publication date; and wherein the second media item characteristic comprises at least one of: a second transcript of audio, a second audio content, a second title, a second description, a second duration, or a second publication date.
18 . The non-transitory machine-readable storage medium of claim 15 , wherein identifying the second media item comprises:
comparing the second media item characteristic to the first media item characteristic associated with each of a first plurality of first media items of the first media type;
determining, for each of the first plurality of first media items, a matching score based on the comparing; and
identifying the second media item that has a highest matching score, wherein the highest matching score satisfies a matching criterion.
19 . The non-transitory machine-readable storage medium of claim 15 , wherein identifying the second media item comprises:
providing the first media item characteristic as input to a machine learning model trained to identify the second media item based on the second media item characteristic.
20 . The non-transitory machine-readable storage medium of claim 15 , wherein the correspondence between the second media item and the first media item based on the popularity indicator associated with the second media item and the popularity indicator associated with the first media item reflects a combination of the popularity indicator associated with the second media item and the popularity indicator associated with the first media item.