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 method for detecting spam on a social media platform, the method comprising:
identifying, by a server of the social media platform, a topic of a social media post;
accessing, by the server, a plurality of comments associated with the social media post;
determining, by the server, a topic of each respective comment;
determining, by the server, based on the topic of each respective comment, a respective plurality of synonymous topics;
determining, by the server, whether the topic of each respective comment of the plurality of comments matches the topic of the social media post based on the respective plurality of synonymous topics; and
in response to determining, by the server, that the topic of a respective comment of the plurality of comments does not match the topic of the social media post:
identifying, by the server, the respective comment as spam; and
generating for display, by the server, to an administrator of the social media platform, a notification comprising an identifier of the respective comment.
2. The method of claim 1 , the method further comprising:
identifying a textual portion of the social media post; and
performing natural language processing on the textual portion of the social media post.
3. The method of claim 2 , wherein:
identifying a topic of the social media post comprises retrieving a result of the natural language processing; and
wherein the natural language processing comprises automatic summarization of the textual portion of the social media post.
4. The method of claim 1 , wherein accessing a plurality of comments associated with the social media post comprises:
retrieving an identifier of the social media post;
transmitting a query to a database of comments associated with a plurality of social media posts, the query comprising the identifier of the social media post; and
receiving, in response to the query, the plurality of comments associated with the social media post.
5. The method of claim 1 , wherein determining a topic of each respective comment comprises:
identifying a textual portion of the respective comment of the plurality of comments; and
performing natural language processing on the textual portion of the respective comment of the plurality of comments;
wherein the natural language processing comprises automatic summarization of the textual portion of the respective comment of the plurality of comments.
6. The method of claim 1 , wherein
determining, based on the topic of each respective comment, a respective plurality of synonymous topics comprises generating, from the topic of the respective comment, a plurality of synonymous topics; and
determining whether the topic of each respective comment of the plurality of comments matches the topic of the social media post comprises:
comparing the topic of the social media post with the plurality of synonymous topics; and
determining, based on the comparing, that the topic of the social media post matches one of the plurality of synonymous topics.
7. The method of claim 1 , further comprising, further in response to determining that the topic of a respective comment of the plurality of comments does not match the topic of the social media post:
comparing the content of the respective comment to an exclusion list having a plurality of entries identifying excluded content;
determining, based on the comparing, whether the content of the respective comment matches at least one entry of the plurality of entries; and
in response to determining that the content of the respective comment matches at least one entry of the plurality of entries, identifying the first comment as not spam;
wherein identifying the respective comment as spam is in response to determining that the content of the respective comment does not match any entry of the plurality of entries.
8. The method of claim 7 , wherein the plurality of entries identifying excluded content comprises characters representing emotional responses.
9. The method of claim 8 , wherein the characters representing emotional responses are alphanumeric characters.
10. The method of claim 8 , wherein the characters representing emotional responses are graphical icons.
11. A system for detecting spam on a social media platform, the system comprising:
transceiver circuitry; and
control circuitry implemented on a server of the social media platform and configured to:
identify a topic of a social media post;
access, using the transceiver circuitry, a plurality of comments associated with the social media post;
determine a topic of each respective comment;
determine, based on the topic of each respective comment, a respective plurality of synonymous topics;
determine whether the topic of each respective comment of the plurality of comments matches the topic of the social media post based on the respective plurality of synonymous topics; and
in response to determining that the topic of a respective comment of the plurality of comments does not match the topic of the social media post:
identify the respective comment as spam; and
generate for display, to an administrator of the social media platform, a notification comprising an identifier of the respective comment.
12. The system of claim 11 , wherein the control circuitry is further configured to:
identify a textual portion of the social media post; and
perform natural language processing on the textual portion of the social media post.
13. The system of claim 12 , wherein:
the control circuitry configured to identify a topic of the social media post is configured to retrieving a result of the natural language processing; and
wherein the natural language processing comprises automatic summarization of the textual portion of the social media post.
14. The system of claim 11 , wherein the control circuitry configured to access a plurality of comments associated with the social media post is configured to:
retrieve an identifier of the social media post;
transmit a query to a database of comments associated with a plurality of social media posts, the query comprising the identifier of the social media post; and
receive, in response to the query, the plurality of comments associated with the social media post.
15. The system of claim 11 , wherein the control circuitry configured to determine a topic of each respective comment is configured to:
identify a textual portion of the respective comment of the plurality of comments; and
perform natural language processing on the textual portion of the respective comment of the plurality of comments;
wherein the natural language processing comprises automatic summarization of the textual portion of the respective comment of the plurality of comments.
16. The system of claim 11 , wherein
the control circuitry configured to determine, based on the topic of each respective comment, a respective plurality of synonymous topics is configured to generate, from the topic of the respective comment, a plurality of synonymous topics; and
the control circuitry configured to determine whether the topic of each respective comment of the plurality of comments matches the topic of the social media post is configured to:
compare the topic of the social media post with the plurality of synonymous topics; and
determine, based on the comparing, that the topic of the social media post matches one of the plurality of synonymous topics.
17. The system of claim 11 , wherein the control circuitry is further configured, further in response to determining that the topic of a respective comment of the plurality of comments does not match the topic of the social media post, to:
compare the content of the respective comment to an exclusion list having a plurality of entries identifying excluded content;
determine, based on the comparing, whether the content of the respective comment matches at least one entry of the plurality of entries; and
in response to determining that the content of the respective comment matches at least one entry of the plurality of entries, identify the respective comment as not spam;
wherein the control circuitry is further configured to identify the respective comment as spam is in response to determining that the content of the respective comment does not match any entry of the plurality of entries.
18. The system of claim 17 , wherein the plurality of entries identifying excluded content comprises characters representing emotional responses.
19. The system of claim 18 , wherein the characters representing emotional responses are alphanumeric characters.
20. The system of claim 18 , wherein the characters representing emotional responses are graphical icons.