Image Sentiment Analysis
This work proposes a model based on the mid-level features of the images that combines the techniques of SentiBank, RCNN (Regions with CNN) and SentiStrength, and shows that this approach achieves better sentiment classification accuracy.
Abstract
: It is true that a picture is worth a thousand words. The use of images to express views, opinions, feelings, emotions and sentiments has increased tremendously on social platforms like Flickr, Instagram, Twitter, Tumblr, etc. The analysis of sentiments in us er-generated images is of increasing importance for developing several applications. A lot of research work has been done for 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 model based on the mid-level features of the images that combines the techniques of SentiBank, RCNN (Regions with CNN) and SentiStrength. Results of experiments conducted on Flickr image dataset show that this approach achieves better sentiment classification accuracy.