Semantic Search of Memes on Twitter

TL;DR

This paper explores automatic classification and retrieval of memes on Twitter, proposing and evaluating several methods to improve meme identification and search in large datasets, with experiments on Chilean Twitter memes.

Contribution

It introduces and compares multiple methods for classifying memes and presents a system for meme retrieval using textual queries, evaluated on a large, annotated Twitter meme dataset.

Findings

Some methods are effective but room for improvement exists

Large dataset of Twitter memes was used for evaluation

System enables meme retrieval with textual queries

Abstract

Memes are becoming a useful source of data for analyzing behavior on social media. However, a problem to tackle is how to correctly identify a meme. As the number of memes published every day on social media is huge, there is a need for automatic methods for classifying and searching in large meme datasets. This paper proposes and compares several methods for automatically classifying images as memes. Also, we propose a method that allows us to implement a system for retrieving memes from a dataset using a textual query. We experimentally evaluate the methods using a large dataset of memes collected from Twitter users in Chile, which was annotated by a group of experts. Though some of the evaluated methods are effective, there is still room for improvement.