US 12,452,212 B1
Systems and methods for preventing social media harassment
Daniel Kats, Culver City, CA (US); Daniel Marino, Los Angeles, CA (US); Yun Shen, Bristol (GB); and Acar Tamersoy, Culver City, CA (US)
Assigned to Gen Digital Inc., Tempe, AZ (US)
Filed by GEN DIGITAL INC., Tempe, AZ (US)
Filed on Oct. 25, 2021, as Appl. No. 17/510,204.
Int. Cl. H04L 29/06 (2006.01); G06Q 50/00 (2012.01); H04L 9/40 (2022.01); H04L 51/212 (2022.01); H04L 51/52 (2022.01)
CPC H04L 63/0245 (2013.01) [G06Q 50/01 (2013.01); H04L 51/212 (2022.05); H04L 51/52 (2022.05)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for preventing social media harassment, at least a portion of the method being performed by a computing device comprising at least one processor, the method comprising:
identifying, based on an analysis of previous messages received by a user via a social media service and further based on the user marking a subset of the previous messages as harassing messages directed at the user, at least one harassment topic relevant to the user;
intercepting a message sent by a sender, via the social media service, to the user as a recipient of the message;
performing topic modeling on content of the message to identify one or more topics of the message, wherein the topic modeling is customized based on the at least one harassment topic relevant to the user and is further customized based at least in part on the user's preferences and the subset of the previous messages marked by the user;
calculating, based at least in part on the topic modeling, a probability that the message is harassment targeted at the user by weighting the identified one or more topics with respect to the at least one harassment topic; and
preventing the user from receiving the message in response to determining that the probability that the message is harassment meets a threshold for harassment probability.