Deriving Emotions and Sentiments from Visual Content: A Disaster Analysis Use Case

TL;DR

This paper explores visual sentiment analysis, especially for disaster images, proposing a deep learning approach and establishing a baseline for future research in analyzing emotions from visual content.

Contribution

It introduces a deep visual sentiment analyzer for disaster images, covering data collection, annotation, model selection, and evaluation, filling a gap in visual sentiment analysis research.

Findings

Developed a deep visual sentiment analysis model for disaster images

Provided a comprehensive methodology for data annotation and model evaluation

Established a baseline for future visual sentiment analysis research

Abstract

Sentiment analysis aims to extract and express a person's perception, opinions and emotions towards an entity, object, product and a service, enabling businesses to obtain feedback from the consumers. The increasing popularity of the social networks and users' tendency towards sharing their feelings, expressions and opinions in text, visual and audio content has opened new opportunities and challenges in sentiment analysis. While sentiment analysis of text streams has been widely explored in the literature, sentiment analysis of images and videos is relatively new. This article introduces visual sentiment analysis and contrasts it with textual sentiment analysis with emphasis on the opportunities and challenges in this nascent research area. We also propose a deep visual sentiment analyzer for disaster-related images as a use-case, covering different aspects of visual sentiment analysis starting from data collection, annotation, model selection, implementation and evaluations. We believe such rigorous analysis will provide a baseline for future research in the domain.