Diving Deep into Sentiment: Understanding Fine-tuned CNNs for Visual Sentiment Prediction

TL;DR

This paper investigates how to adapt and optimize CNNs for visual sentiment analysis, providing insights into effective design patterns and performance enhancement techniques for this emerging task.

Contribution

It offers a comprehensive analysis of fine-tuning CNNs for visual sentiment prediction and explores methods to improve their effectiveness.

Findings

Fine-tuning CNNs improves sentiment prediction accuracy.

Performance boosting techniques enhance model effectiveness.

Deep analysis reveals design patterns for CNNs in sentiment tasks.

Abstract

Visual media are powerful means of expressing emotions and sentiments. The constant generation of new content in social networks highlights the need of automated visual sentiment analysis tools. While Convolutional Neural Networks (CNNs) have established a new state-of-the-art in several vision problems, their application to the task of sentiment analysis is mostly unexplored and there are few studies regarding how to design CNNs for this purpose. In this work, we study the suitability of fine-tuning a CNN for visual sentiment prediction as well as explore performance boosting techniques within this deep learning setting. Finally, we provide a deep-dive analysis into a benchmark, state-of-the-art network architecture to gain insight about how to design patterns for CNNs on the task of visual sentiment prediction.