We develop a novel visual model which can recognize protesters, describe their activities by visual attributes and estimate the level of perceived violence in an image. Studies of social media and protests use natural language processing to track how individuals use hashtags and links, often with a focus on those items' diffusion. These approaches, however, may not be effective in fully characterizing actual real-world protests (e.g., violent or peaceful) or estimating the demographics of participants (e.g., age, gender, and race) and their emotions. Our system characterizes protests along these dimensions. We have collected geotagged tweets and their images from 2013-2017 and analyzed multiple major protest events in that period. A multi-task convolutional neural network is employed in order to automatically classify the presence of protesters in an image and predict its visual attributes, perceived violence and exhibited emotions. We also release the UCLA Protest Image Dataset, our novel dataset of 40,764 images (11,659 protest images and hard negatives) with various annotations of visual attributes and sentiments. Using this dataset, we train our model and demonstrate its effectiveness. We also present experimental results from various analysis on geotagged image data in several prevalent protest events. Our dataset will be made accessible at
Clickbaits are routinely utilized by online publishers to attract the attention of people in competitive media markets. Clickbaits are increasingly used in visual-centric social media but remain a largely unexplored problem. Existing defense mechanisms rely on text-based features and are thus inapplicable to visual social media. By exploring the relationships between images and text, we develop a novel approach to characterize clickbaits on visual social media. Focusing on the topic of fashion, we first examined the prevalence of clickbaits on Instagram and surveyed their negative impacts on user experience through a focus group study (N=31). In a largescale analysis, we collected 450,000 Instagram posts and manually labeled 12,659 of these posts to determine what people consider to be clickbaits. By combining three different types of features (e.g., image, text, and meta features), our classifier was able detect clickbaits with an accuracy of 0.863. We performed an extensive feature analysis and showed that content-based features are much more important than meta features (e.g., number of followers) in clickbait classification. Our analysis indicates that approximately 11% of fashion-related Instagram posts are clickbait and that these posts are consistently accompanied by many hashtags, thus demonstrating that clickbait is prevalent in visual social media.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.