Robust Image Sentiment Analysis Using Progressively Trained and Domain Transferred Deep Networks

TL;DR

This paper introduces a CNN-based approach for image sentiment analysis that leverages large-scale noisy data and domain transfer techniques to improve accuracy on social media images.

Contribution

It presents a novel progressive training strategy and domain transfer method to enhance CNN performance on noisy, large-scale visual sentiment datasets.

Findings

CNN outperforms competing algorithms on Twitter images

Progressive fine-tuning improves sentiment prediction accuracy

Domain transfer with small labeled data boosts performance

Abstract

Sentiment analysis of online user generated content is important for many social media analytics tasks. Researchers have largely relied on textual sentiment analysis to develop systems to predict political elections, measure economic indicators, and so on. Recently, social media users are increasingly using images and videos to express their opinions and share their experiences. Sentiment analysis of such large scale visual content can help better extract user sentiments toward events or topics, such as those in image tweets, so that prediction of sentiment from visual content is complementary to textual sentiment analysis. Motivated by the needs in leveraging large scale yet noisy training data to solve the extremely challenging problem of image sentiment analysis, we employ Convolutional Neural Networks (CNN). We first design a suitable CNN architecture for image sentiment analysis. We obtain half a million training samples by using a baseline sentiment algorithm to label Flickr images. To make use of such noisy machine labeled data, we employ a progressive strategy to fine-tune the deep network. Furthermore, we improve the performance on Twitter images by inducing domain transfer with a small number of manually labeled Twitter images. We have conducted extensive experiments on manually labeled Twitter images. The results show that the proposed CNN can achieve better performance in image sentiment analysis than competing algorithms.