Authors:
Chhavi Sharma
1
;
Viswanath Pulabaigari
1
and
Amitava Das
2
Affiliations:
1
Department of Computer Science Engineering, Indian Institute of Information Technology, Sri City, India
;
2
Wipro AI Labs, Bangalore, India
Keyword(s):
Meme, Multi-modality, Social Media.
Abstract:
Building on the foundation of consolidating humor with social relevance, internet memes have become an imperative communication tool of the modern era. Memes percolate through the dynamic ecosystem of the social network, influencing and changing the social order along the way. As a result, the status quo of the social balance changes significantly, and at times channelized in unwanted directions. Besides flagging harmful memes, detecting them amongst the disparate multi-modal online content is of crucial importance, which has remained understudied. As an effort to characterize internet memes, we attempt to classify meme vs non- meme, by leveraging techniques like Siamese network and canonical correlation analysis (CCA), towards capturing the feature association between the visual and textual components of a meme. The experiments are observed to yield impressive performance, and could further provide insights for applications like meme content moderation over social media.