New Emoji Requests from Twitter Users

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.

[1]  Isabelle Augenstein,et al.  emoji2vec: Learning Emoji Representations from their Description , 2016, SocialNLP@EMNLP.

[2]  S. Jaeger,et al.  Measurement of product emotions using emoji surveys: Case studies with tasted foods and beverages , 2017 .

[3]  Chi-Hong Leung,et al.  Using emoji effectively in marketing: An empirical study , 2017 .

[4]  José Camacho-Collados,et al.  How Gender and Skin Tone Modifiers Affect Emoji Semantics in Twitter , 2018, *SEMEVAL.

[5]  Owen Rambow,et al.  Sentiment Analysis of Twitter Data , 2011 .

[6]  Amit P. Sheth,et al.  EmojiNet: An Open Service and API for Emoji Sense Discovery , 2017, ICWSM.

[7]  K. Crawford,et al.  The Conservatism of Emoji: Work, Affect, and Communication , 2015 .

[8]  R. Wegerif,et al.  The Semiotics of Emoji: The Rise of Visual Language in the Age of the Internet , 2017 .

[9]  M. Jeanmougin.  SOLEIL ET PEAU , 1992 .

[10]  Loren G. Terveen,et al.  "Blissfully Happy" or "Ready toFight": Varying Interpretations of Emoji , 2016, ICWSM.

[11]  Susan C. Herring,et al.  Communicative functions of emoji sequences on Sina Weibo , 2018, First Monday.

[12]  Ning Wang,et al.  Untangling Emoji Popularity Through Semantic Embeddings , 2017, ICWSM.

[13]  S. Jaeger,et al.  Can emoji be used as a direct method to measure emotional associations to food names? Preliminary investigations with consumers in USA and China , 2017 .

[14]  Saif Mohammad,et al.  NRC-Canada: Building the State-of-the-Art in Sentiment Analysis of Tweets , 2013, *SEMEVAL.

[15]  Horacio Saggion,et al.  How Cosmopolitan Are Emojis?: Exploring Emojis Usage and Meaning over Different Languages with Distributional Semantics , 2016, ACM Multimedia.

[16]  Horacio Saggion,et al.  What does this Emoji Mean? A Vector Space Skip-Gram Model for Twitter Emojis , 2016, LREC.

[17]  Lun-Wei Ku,et al.  UHop: An Unrestricted-Hop Relation Extraction Framework for Knowledge-Based Question Answering , 2019, NAACL.

[18]  Sandy J. J. Gould,et al.  Repurposing Emoji for Personalised Communication: Why pizza slice emoji means “I love you” , 2018 .

[19]  D. Skiba,et al.  Face with Tears of Joy Is Word of the Year: Are Emoji a Sign of Things to Come in Health Care? , 2016, Nursing education perspectives.

[20]  Darja Fiser,et al.  A Global Analysis of Emoji Usage , 2016, WAC@ACL.

[21]  Xuanzhe Liu,et al.  Emoji-Powered Representation Learning for Cross-Lingual Sentiment Classification , 2018, WWW.

[22]  Ning Wang,et al.  Learning from the ubiquitous language: an empirical analysis of emoji usage of smartphone users , 2016, UbiComp.

[23]  S. Jaeger,et al.  Dominant meanings of facial emoji: insights from Chinese consumers and comparison with meanings from internet resources , 2017 .

[24]  Crystal Abidin,et al.  Between art and application: Special issue on emoji epistemology , 2018, First Monday.

[25]  Delores H. Chambers,et al.  A focus group approach to understanding food-related emotions with children using words and emojis , 2017 .

[26]  Ruth Page,et al.  Saying ‘sorry’ : Corporate apologies posted on Twitter , 2014 .

[27]  Amit P. Sheth,et al.  A semantics-based measure of emoji similarity , 2017, WI.

[28]  George A. Miller,et al.  WordNet: A Lexical Database for English , 1995, HLT.

[29]  Ryan Kelly,et al.  Characterising the inventive appropriation of emoji as relationally meaningful in mediated close personal relationships , 2015 .

[30]  Henriette Cramer,et al.  Sender-intended functions of emojis in US messaging , 2016, MobileHCI.

[31]  Wenjun Zhou,et al.  The World Wants Mangoes and Kangaroos: A Study of New Emoji Requests Based on Thirty Million Tweets , 2019, WWW.

[32]  Jiebo Luo,et al.  Spice Up Your Chat: The Intentions and Sentiment Effects of Using Emojis , 2017, ICWSM.

[33]  Petra Kralj Novak,et al.  Sentiment of Emojis , 2015, PloS one.

[34]  Channary Tauch,et al.  The roles of emojis in mobile phone notifications , 2016, UbiComp Adjunct.

[35]  William Brendel,et al.  Exploring Emoji Usage and Prediction Through a Temporal Variation Lens , 2018, ArXiv.

[36]  Neha Kumar,et al.  Goodbye Text, Hello Emoji: Mobile Communication on WeChat in China , 2017, CHI.

[37]  David R. Flatla,et al.  Oh that's what you meant!: reducing emoji misunderstanding , 2016, MobileHCI Adjunct.

[38]  Kenji Araki,et al.  Text Normalization in Social Media: Progress, Problems and Applications for a Pre-Processing System of Casual English , 2011 .

[39]  D. Tanner,et al.  A strong wink between verbal and emoji-based irony: How the brain processes ironic emojis during language comprehension , 2018, PloS one.

[40]  Walid Magdy,et al.  Self-Representation on Twitter Using Emoji Skin Color Modifiers , 2018, ICWSM.

[41]  Uluslararası İktisat.  ISO 3166-2:IS , 2011 .

[42]  Iyad Rahwan,et al.  Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm , 2017, EMNLP.

[43]  S. Jaeger,et al.  Use of emoticon and emoji in tweets for food-related emotional expression , 2016 .

[44]  Orion Montoya,et al.  Varying Linguistic Purposes of Emoji in (Twitter) Context , 2017, ACL.

[45]  Amit P. Sheth,et al.  EmojiNet: Building a Machine Readable Sense Inventory for Emoji , 2016, SocInfo.

[46]  Patrizia Paggio,et al.  Investigating Redundancy in Emoji Use: Study on a Twitter Based Corpus , 2017, WASSA@EMNLP.

[47]  Barbara Poblete,et al.  Information credibility on twitter , 2011, WWW.

[48]  Filippo Menczer,et al.  The rise of social bots , 2014, Commun. ACM.

[49]  Thomas Gottron,et al.  Bad news travel fast: a content-based analysis of interestingness on Twitter , 2011, WebSci '11.

[50]  Vincent Larivière,et al.  Tweets as impact indicators: Examining the implications of automated “bot” accounts on Twitter , 2014, J. Assoc. Inf. Sci. Technol..

[51]  Loren G. Terveen,et al.  Understanding Emoji Ambiguity in Context: The Role of Text in Emoji-Related Miscommunication , 2017, ICWSM.

[52]  Jennifer Daniel.  When a Merperson is a Merman , 2019, WWW.