Detecting Sarcasm in Multimodal Social Platforms

TL;DR

This paper investigates sarcasm detection in multimodal social media posts by analyzing textual and visual content, proposing two integrated computational frameworks, and demonstrating improved detection accuracy across platforms.

Contribution

It introduces two novel multimodal sarcasm detection methods combining visual and textual features and evaluates their effectiveness on social media data.

Findings

Combining visual and textual modalities improves sarcasm detection accuracy.

Visual semantics enhance the understanding of sarcastic content.

Multimodal approaches outperform unimodal methods across platforms.

Abstract

Sarcasm is a peculiar form of sentiment expression, where the surface sentiment differs from the implied sentiment. The detection of sarcasm in social media platforms has been applied in the past mainly to textual utterances where lexical indicators (such as interjections and intensifiers), linguistic markers, and contextual information (such as user profiles, or past conversations) were used to detect the sarcastic tone. However, modern social media platforms allow to create multimodal messages where audiovisual content is integrated with the text, making the analysis of a mode in isolation partial. In our work, we first study the relationship between the textual and visual aspects in multimodal posts from three major social media platforms, i.e., Instagram, Tumblr and Twitter, and we run a crowdsourcing task to quantify the extent to which images are perceived as necessary by human annotators. Moreover, we propose two different computational frameworks to detect sarcasm that integrate the textual and visual modalities. The first approach exploits visual semantics trained on an external dataset, and concatenates the semantics features with state-of-the-art textual features. The second method adapts a visual neural network initialized with parameters trained on ImageNet to multimodal sarcastic posts. Results show the positive effect of combining modalities for the detection of sarcasm across platforms and methods.