Methods, systems, and media for presenting comments based on correlation with content

摘要

Methods, systems, and media for presenting comments based on correlation with content are provided. In some implementations, a method for presenting ranked comments is provided, the method comprising: receiving, using a hardware processor, content data related to an item of content; receiving, using the hardware processor, comment data related to a comment associated with the item of content; determining, using the hardware processor, a degree of correlation between at least a portion of the comment data and one or more portions of the content data; determining, using the hardware processor, a priority for the comment based on the degree of correlation; and presenting, using the hardware processor, the comment based on the priority.

主权项

1. A method for presenting ranked comments based on a correlation between a portion of a video and comments associated with the video, the method comprising:
receiving, using one or more hardware processors, first text data of words in a video being presented to a first user in a first instance of a user interface; receiving second text data that is part of a first user comment posted by the first user in association with the video, wherein the first user comment was posted using the first instance of the user interface; identifying a first string of characters from the second text data that is likely to include a quote of the first text data, wherein the first string of characters includes a plurality of words; in response to identifying the first string of characters, comparing the first string of characters to at least a second string of characters from the first text data; determining how different the first string of characters is from the second string of characters based on the comparison; determining a degree of correlation between the first string of characters and the first text data based at least in part on how different the second string of characters is from the first string of characters, wherein the degree of correlation is less than it would be if there were no differences between the two strings by an amount that is based on how different the two strings of characters are; generating a score for the first comment based at least in part on how closely the first string of characters quotes the second string of characters represented by the degree of correlation and based at least in part on a length of the first string of characters; determining a ranking of a plurality of comments associated with the video, including the first user comment and a plurality of previously posted comments, based at least in part on the score; causing at least two of the plurality of comments associated with the video to be presented to a second user in association with the video being presented in a second instance of the user interface in an order that is based at least in part on the ranking; and causing a link to a portion of the video that corresponds to the second string of characters to be associated with the first user comment based on the degree of correlation between the first string of characters and the second string of characters, wherein selection of the link causes the portion of the video to be presented in the second instance of the user interface.