New Emoji Requests from Twitter Users

Abstract

As emojis become prevalent in personal communications, people are always looking for new, interesting emojis to express emotions, show attitudes, or simply visualize texts. In this study, we collected more than 30 million tweets mentioning the word emoji in a 1-year period to study emoji requests on Twitter. First, we filtered out bot-generated tweets and extracted emoji requests from the raw tweets using a comprehensive list of linguistic patterns. To our surprise, some extant emojis, such as fire 🔥 and hijab 🧕, were still frequently requested by many users. A large number of non-existing emojis were also requested, which were classified into one of eight emoji categories by Unicode Standard. We then examined patterns of new emoji requests by exploring their time, location, and context. Eagerness and frustration of not having these emojis were evidenced by our sentiment analysis, and we summarize users’ advocacy channels. Focusing on typical patterns of co-mentioned emojis, we also identified expressions of equity, diversity, and fairness issues due to unreleased but expected emojis, and we summarized the significance of new emojis on society. Finally, time-continuity-sensitive strategies at multiple time granularity levels were proposed to rank petitioned emojis by the eagerness, and a real-time monitoring system to track new emoji requests was implemented. To the best of our knowledge, the proposed tracking system is the first to rank the new desired emojis on a large scale and in a real-time manner.