Visual Sentiment Prediction with Deep Convolutional Neural Networks
This addresses the need for visual sentiment analysis in online social networks, but it is incremental as it applies existing CNN methods to a new domain.
The paper tackles the problem of predicting sentiment from images, which is understudied compared to text-based sentiment analysis, by proposing a framework using Deep Convolutional Neural Networks (CNN) with transfer learning from object recognition models, and demonstrates effectiveness on real-world datasets from Twitter and Tumblr.
Images have become one of the most popular types of media through which users convey their emotions within online social networks. Although vast amount of research is devoted to sentiment analysis of textual data, there has been very limited work that focuses on analyzing sentiment of image data. In this work, we propose a novel visual sentiment prediction framework that performs image understanding with Deep Convolutional Neural Networks (CNN). Specifically, the proposed sentiment prediction framework performs transfer learning from a CNN with millions of parameters, which is pre-trained on large-scale data for object recognition. Experiments conducted on two real-world datasets from Twitter and Tumblr demonstrate the effectiveness of the proposed visual sentiment analysis framework.