Identification and tracking of internet memes
In a method for identification of an Internet meme, a plurality of sources is monitored for digital visual content comprising a visual moment and a caption. It is determined whether instances of digital visual content include a same visual moment. Provided the instances of digital visual content include the same visual moment, the instances of digital visual content including the same visual moment are identified as similar digital visual content. Each instance of the similar digital visual content is tracked. Provided a total number of instances of the similar digital visual content exceeds an Internet meme threshold, the similar digital visual content is identified as an Internet meme, wherein the same visual moment is a root visual moment and each caption corresponds to a different iteration of the Internet meme.
1. A method for tracking of digital memes, the method comprising:
monitoring a plurality of sources of digital visual content comprising a visual moment and a caption;
comparing an instance of digital visual content to a digital meme;
provided the instance of digital visual content satisfies a similarity threshold, identifying the instance of digital visual content as an instance of the digital meme;
determining whether the instance of the digital meme is identical to an existing iteration of the digital meme based on a comparison between a caption of the existing iteration of the digital meme and a caption of the instance of the digital meme;
provided the instance of the digital meme is not identical to an existing iteration of the digital meme based on the instance of the digital meme including a different caption from the existing iteration of the digital meme, tracking the instance of the digital meme as a new iteration of the digital meme; and
provided the instance of the digital meme is identical to an existing iteration of the digital meme based on the instance of the digital meme including the same caption as the existing iteration of the digital meme, tracking the instance of the digital meme as another instance of the existing iteration of the digital meme.
2. The method of claim 1 , further comprising:
generating a perceptual hash for the instance of digital visual content;
comparing a perceptual hash for the digital visual content to a perceptual hash for the digital meme; and
provided a distance between two perceptual hashes satisfies the similarity threshold, identifying the instance of digital visual content as an instance of the digital meme.
3. The method of claim 2 , further comprising:
determining that the instance of the digital meme includes a same underlying visual moment as the digital meme;
determining that the instance of the digital meme includes a different caption from the digital meme; and
based on the instance of the digital meme including a different caption, tracking the instance of the digital meme as another instance of the existing iteration of the digital meme.
4. The method of claim 1 , wherein the digital visual content comprises one or more frames of a video.
5. The method of claim 1 wherein the instance of the digital meme is only tracked as another instance of the existing iteration of the digital meme if it is generated by a different social media account than existing iterations of the digital meme.
6. The method of claim 1 , further comprising:
tracking each instance of the digital meme at the plurality of sources;
tracking each iteration of the digital meme; and
determining a reach of each iteration of the digital meme, wherein the reach of each iteration of the digital meme corresponds to engagement with each iteration of the digital meme.
7. The method of claim 6 , further comprising:
calculating a viral score for each digital meme, the viral score comprising a first component associated with the reach of each iteration of the digital meme and a second component associated with a number of iterations of each digital meme.
8. The method of claim 6 , further comprising:
normalizing the reach of an existing iteration of the digital meme based on an average number of engagement measures for digital memes at a particular source of digital visual content.
9. A non-transitory computer readable storage medium having computer readable program code stored thereon for causing a computer system to perform a method for identification of a digital meme, the method comprising:
monitoring a plurality of sources for digital visual content comprising a visual moment and a caption;
comparing an instance of digital visual content to a digital meme;
provided the instance of digital visual content satisfies a similarity threshold, identifying the instance of digital visual content as an instance of the digital meme;
determining whether the instance of the digital meme is identical to an existing iteration of the digital meme based on a comparison between a caption of the existing iteration of the digital meme and a caption of the instance of the digital meme;
provided the instance of the digital meme is not identical to an existing iteration of the digital meme based on the instance of the digital meme including a different caption from the existing iteration of the digital meme, tracking the instance of the digital meme as a new iteration of the digital meme; and
provided the instance of the digital meme is identical to an existing iteration of the digital meme based on the instance of the digital meme including the same caption as the existing iteration of the digital meme, tracking the instance of the digital meme as another instance of the existing iteration of the digital meme.
10. The non-transitory computer readable storage medium of claim 9 , the method further comprising:
generating a perceptual hash for the instance of digital visual content;
comparing a perceptual hash for the digital visual content to a perceptual hash for the digital meme; and
provided a distance between two perceptual hashes satisfies the similarity threshold, identifying the instance of digital visual content as an instance of the digital meme.
11. The non-transitory computer readable storage medium of claim 10 , the method further comprising:
determining that the instance of the digital meme includes a same underlying visual moment as the digital meme;
determining that the instance of the digital meme includes a different caption from the digital meme; and
based on the instance of the digital meme including a different caption, tracking the instance of the digital meme as another instance of the existing iteration of the digital meme.
12. The non-transitory computer readable storage medium of claim 9 , wherein the instance of the digital meme is only tracked as another instance of the existing iteration of the digital meme if it is generated by a different social media account than existing iterations of the digital meme.
13. The non-transitory computer readable storage medium of claim 12 , the method further comprising:
tracking each instance of the digital meme at the plurality of sources;
tracking each iteration of the digital meme; and
determining a reach of each iteration of the digital meme, wherein the reach of each iteration of the digital meme corresponds to engagement with each iteration of the digital meme.
14. The non-transitory computer readable storage medium of claim 13 , the method further comprising:
calculating a viral score for each digital meme, the viral score comprising a first component associated with the reach of each iteration of the digital meme and a second component associated with a number of iterations of each digital meme.
15. A computer system comprising:
a data storage unit including processor-readable instructions; and
at least one processor coupled with the data storage unit, the at least one processor configured by the processor-readable instructions to perform operations comprising:
monitoring a plurality of sources for digital visual content comprising a visual moment and a caption;
comparing an instance of digital visual content to a digital meme;
provided the instance of digital visual content satisfies a similarity threshold, identifying the instance of digital visual content as an instance of the digital meme;
determining whether the instance of the digital meme is identical to an existing iteration of the digital meme based on a comparison between a caption of the existing iteration of the digital meme and a caption of the instance of the digital meme;
provided the instance of the digital meme is not identical to an existing iteration of the digital meme based on the instance of the digital meme including a different caption from the existing iteration of the digital meme, tracking the instance of the digital meme as a new iteration of the digital meme; and
provided the instance of the digital meme is identical to an existing iteration of the digital meme based on the instance of the digital meme including the same caption as the existing iteration of the digital meme, tracking the instance of the digital meme as another instance of the existing iteration of the digital meme.
16. The computer system of claim 15 , the operations further comprising:
generating a perceptual hash for the instance of digital visual content;
comparing a perceptual hash for the digital visual content to a perceptual hash for the digital meme; and
provided a distance between two perceptual hashes satisfies the similarity threshold, identifying the instance of digital visual content as an instance of the digital meme.
17. The computer system of claim 15 , the operations further comprising:
determining that the instance of the digital meme includes a same underlying visual moment as the digital meme;
determining that the instance of the digital meme includes a different caption from the digital meme; and
based on the instance of the digital meme including a different caption, tracking the instance of the digital meme as another instance of the existing iteration of the digital meme.
18. The computer system of claim 15 , wherein the instance of the digital meme is only tracked as another instance of the existing iteration of the digital meme if it is generated by a different social media account than existing iterations of the digital meme.
19. The computer system of claim 15 , the operations further comprising:
tracking each instance of the digital meme at the plurality of sources;
tracking each iteration of the digital meme; and
determining a reach of each iteration of the digital meme, wherein the reach of each iteration of the digital meme corresponds to engagement with each iteration of the digital meme.
20. The computer system of claim 15 , the operations further comprising:
calculating a viral score for each digital meme, the viral score comprising a first component associated with a reach of each iteration of the digital meme and a second component associated with a number of iterations of each digital meme.