Systems and methods for automatically identifying spam in social media comments based on context
Systems and methods are described herein for automatically identifying spam in social media comments based on comparison of the context or topic of the popular or trending post with the context or topic of each comment associated with the post. Content of a social media post is processed to identify a topic of the social media post. A plurality of comments associated with the social media post are accessed and the topic of each comment is compared to the topic of the social media post and, if the topics do not match, the comment is identified as spam. A notification is generated for display to an administrator of the social media platform on which the social media post resides identifying the comment as spam.
1 . A computer-implemented method comprising:
accessing, by a server, a comment to be posted in association with a social media post, wherein the comment is submitted by a first user, and the social media post is submitted by a second user;
determining, by the server, whether a topic of the comment matches a topic of the social media post;
based at least in part on determining that the topic of the comment does not match the topic of the social media post:
accessing, by the server, an exclusion list comprising one or more entries, wherein the one or more entries comprise one or more characters representing emotional responses;
determining, by the server, whether content of the comment matches an entry of the exclusion list by:
identifying a textual portion in the content of the comment;
comparing the textual portion and the one or more characters representing emotional responses; and
determining, based on the comparing, that the textual portion comprises a character of the one or more characters representing emotional responses; and
based at least in part on determining that the content of the comment matches the entry of the exclusion list:
identifying, by the server, the comment as related to the social media post; and
causing, by the server, the comment to be posted in association with the social media post.
2 . The method of claim 1 , wherein the comment is a first comment, the method further comprising:
determining whether content of a second comment matches an entry of the exclusion list; and
based at least in part on determining that the content of the second comment does not match any entry of the exclusion list:
identifying the second comment as unrelated to the social media post; and
transmitting a notification comprising an identifier of the second comment.
3 . The method of claim 2 , wherein the social media post is published via a social media platform, and wherein the notification is transmitted by the server to a device associated with an administrator of the social media platform.
4 . The method of claim 1 , wherein the one or more characters comprise at least one of alphanumeric characters, text strings, emojis, emoticons, or graphical icons.
5 . The method of claim 1 , wherein the one or more entries comprise repeated content across a plurality of comments.
6 . The method of claim 1 , wherein the exclusion list is indicative of acceptable content of comments.
7 . The method of claim 1 , wherein determining that the topic of the comment does not match the topic of the social media post comprises:
identifying one or more keywords of the comment; and
determining, based on the one or more keywords, that the comment comprises advertisement content.
8 . The method of claim 7 , wherein determining, based on the one or more keywords, that the comment comprises the advertisement content comprises determining that the one or more keywords are indicative of contact information.
9 . A system comprising:
memory for storing data associated with social media; and
control circuitry implemented on a server and configured to:
access, from the memory, a comment to be posted in association with a social media post, wherein the comment is submitted by a first user, and the social media post is submitted by a second user;
determine whether a topic of the comment matches a topic of the social media post;
based at least in part on determining that the topic of the comment does not match the topic of the social media post:
access an exclusion list comprising one or more entries, wherein the one or more entries comprise one or more characters representing emotional responses;
determine whether content of the comment matches an entry of the exclusion list by:
identifying a textual portion in the content of the comment;
comparing the textual portion and the one or more characters representing emotional responses; and
determining, based on the comparing, that the textual portion comprises a character of the one or more characters representing emotional responses; and
based at least in part on determining that the content of the comment matches the entry of the exclusion list:
identify the comment as related to the social media post; and
cause the comment to be posted in association with the social media post.
10 . The system of claim 9 , wherein the comment is a first comment, and wherein the control circuitry is further configured to:
determine whether content of a second comment matches an entry of the exclusion list; and
based at least in part on determining that the content of the second comment does not match any entry of the exclusion list:
identify the second comment as unrelated to the social media post; and
transmit a notification comprising an identifier of the second comment.
11 . The system of claim 10 , wherein the social media post is published via a social media platform, and wherein the control circuitry is configured to transmit the notification to a device associated with an administrator of the social media platform.
12 . The system of claim 9 , wherein the one or more characters comprise at least one of alphanumeric characters, text strings, emojis, emoticons, or graphical icons.
13 . The system of claim 9 , wherein the one or more entries comprise repeated content across a plurality of comments.
14 . The system of claim 9 , wherein the exclusion list is indicative of acceptable content of comments.
15 . The system of claim 9 , wherein the control circuitry, when determining that the topic of the comment does not match the topic of the social media post, is configured to:
identify one or more keywords of the comment; and
determine, based on the one or more keywords, that the comment comprises advertisement content.
16 . The system of claim 15 , wherein the control circuitry, when determining, based on the one or more keywords, that the comment comprises the advertisement content, is configured to determine that the one or more keywords are indicative of contact information.