“Blissfully Happy” or “Ready toFight”: Varying Interpretations of Emoji

Abstract

Emoji are commonly used in modern text communication. However, as graphics with nuanced details, emoji may be open to interpretation. Emoji also render differently on different viewing platforms (e.g., Apple’s iPhone vs. Google’s Nexus phone), potentially leading to communication errors. We explore whether emoji renderings or differences across platforms give rise to diverse interpretations of emoji. Through an online survey, we solicit people’s interpretations of a sample of the most popular emoji characters, each rendered for multiple platforms. Both in terms of sentiment and semantics, we analyze the variance in interpretation of the emoji, quantifying which emoji are most (and least) likely to be misinterpreted. In cases in which participants rated the same emoji rendering, they disagreed on whether the sentiment was positive, neutral, or negative 25% of the time. When considering renderings across platforms, these disagreements only increase. Overall, we find significant potential for miscommunication, both for individual emoji renderings and for different emoji renderings across platforms.

On the Context-Free Ambiguity of Emoji

“…Emojis: interpretation and meaning. Previous research has shown that emojis are often misunderstood (Miller et al 2016(Miller et al , 2017. Misunderstanding is sometimes related to how the emoji's design is interpreted in context or the way it is shown on the receiving side.…”

“…Our work studies the intrinsic ability of emojis to convey information, independent of the textual context they are used in. In contrast to Miller et al (2016Miller et al ( , 2017, who focused on small subsets of anthropomorphic emojis, we consider a far more exhaustive set of emojis (see Table 1). The aspiration of an emoji-based language.…”

“…Previous work on the ambiguity of emojis focused on differences between platforms (Shurick and Daniel 2020) and their usage in context (Miller et al 2017). Most closely related past studies focused on frequently used and anthropomorphic emojis (Shurick and Daniel 2020;Miller et al 2017Miller et al , 2016, discarding many available emojis. Whereas a lot is known about emoji sentiment and usage in context (Novak et al 2015), less is known about emoji semantics beyond sentiment and context-free emoji interpretation.…”

#Emoji: A Study on the Association between Emojis and Hashtags on Twitter

“…Users apply emojis to make a message more engaging to the recipient, or for relationship maintenance (Hu et al 2017). The differences in emoji usage are demonstrated across communities, such as, apps, platforms, languages, cultures and genders (Tauch and Kanjo 2016; Lu et al 2016;Chen et al 2018b;Barbieri et al 2016;Miller et al 2016). Besides the study of emoji usage in social media, researchers also develop models to incorporate emoji information in the downstream tasks.…”

“…Hashtags usually consist of abbreviated or concatenated concepts, making them hard to understand for outside observers. Emojis have also been associated with great ambiguity due to the rich information coded in the tiny pictures (Miller et al 2016). On the other hand, although some previous work assumes a hidden correlation between emojis and hashtags (Park, Xu, and Fung 2018), little research has explicitly examined the relationship between hashtags and emojis.…”