Unsupervised sentiment analysis for social media images
Yilin Wang, Suhang Wang, Jiliang Tang, Huan Liu, Baoxin Li · 2015
Recently text-based sentiment prediction has been extensively studied, while image-centric sentiment analysis receives much less attention. In this pa-per, we study the problem of understanding human sentiments from large-scale social media images, considering both visual content and contextual in-formation, such as comments on the images, cap-tions, etc. The challenge of this problem lies in the “semantic gap ” between low-level visual fea-tures and higher-level image sentiments. Moreover, the lack of proper annotations/labels in the major-ity of social media images presents another chal-lenge. To address these two challenges, we propose a novel Unsupervised SEntiment Analysis (USEA) framework for social media images. Our approach exploits relations among visual content and rele-vant contextual information to bridge the “semantic gap ” in the prediction of image sentiments. With experiments on two large-scale datasets, we show that the proposed method is effective in addressing the two challenges. 1