Abstract
AbstractThere has been near exponential increase in the use of images and video on various Social Media platforms in the last few years, in place of or in addition to the use of plain text. Automated sentiment analysis, at its core, is the capturing of human emotion by machine - the addition of image and video to social media output had made this already challenging task even greater. In this paper, we propose a multimodal, decision-level based approach to sentiment analysis (SA) of Twitter feeds. The solution proposed and outlined in this paper, combines the sentiment analysis scoring of not just text-based output but integrates SA scoring generated from analysis of image captions. For our experiments, we focused on politics and on two political topics (Trump/Brexit) that are generating a lot of discussion and debate on Twitter. We chose the political domain given the power that Social Media has on possibly influencing voters (https://www.theguardian.com/technology/2016/jul/31/trash-talk-how-twitter-is-shaping-the-new-politics) and the ‘strong’ opinions that are expressed in this area.KeywordsMultimodalitySentiment analysisImage captioningTweets
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
