Emojis have evolved as complementary sources for expressing emotion in social-media platforms where posts are mostly composed of texts and images. In order to increase the expressiveness of the social media posts, users associate relevant emojis with their posts. Incorporating domain knowledge has improved machine understanding of text. In this paper, we investigate whether domain knowledge for emoji can improve the accuracy of emoji recommendation task in case of multimedia posts composed of image and text. Our emoji recommendation can suggest accurate emojis by exploiting both visual and textual content from social media posts as well as domain knowledge from Emojinet. Experimental results using pre-trained image classifiers and pre-trained word embedding models on Twitter dataset show that our results outperform the current state-ofthe-art by 9.6%. We also present a user study evaluation of our recommendation system on a set of images chosen from MSCOCO dataset.
Usage of emoji in social media platforms has seen a rapid increase over the last few years. Majority of the social media posts are laden with emoji and users often use more than one emoji in a single social media post to express their emotions and to emphasize certain words in a message. Utilizing the emoji cooccurrence can be helpful to understand how emoji are used in social media posts and their meanings in the context of social media posts. In this paper, we investigate whether emoji cooccurrences can be used as a feature to learn emoji embeddings which can be used in many downstream applications such sentiment analysis and emotion identification in social media text. We utilize 147 million tweets which have emojis in them and build an emoji cooccurrence network. Then, we train a network embedding model to embed emojis into a low dimensional vector space. We evaluate our embeddings using sentiment analysis and emoji similarity experiments, and experimental results show that our embeddings outperform the current state-of-the-art results for sentiment analysis tasks.
No abstract
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
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2025 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.