Proceedings of the Fifth International Workshop on Emoji Understanding and Applications in Social Media
We study the extent to which emoji can be used to add interpretability to embeddings of text and emoji. To do so, we extend the POLAR-framework that transforms word embeddings to interpretable counterparts and apply it to word-emoji embeddings trained on four years of messaging data from the Jodel social network. We devise a crowdsourced human judgement experiment to study six usecases, evaluating against words only, what role emoji can play in adding interpretability to word embeddings. That is, we use a revised POLAR approach interpreting words and emoji with words, emoji or both according to human judgement. We find statistically significant trends demonstrating that emoji can be used to interpret other emoji very well.
This paper presents a new iconic language, the IKON language, and its philosophical, linguistic, and graphical principles. We examine some case studies to highlight the semantic complexity of the visual representation of meanings. We also introduce the Iconometer test to validate our icons and their application to the medical domain, through the creation of iconic sentences.
This paper presents the results of two experiments investigating the directness of emoji in constituting speaker meaning. This relationship is examined in two ways, with Experiment 1 testing whether speakers are committed to meanings they communicate via a single emoji and Experiment 2 testing whether that speaker is taken to have lied if that meaning is false and intended to deceive. Results indicate that emoji with high meaning agreement in general (i.e., pictorial representations of concrete objects or foods) reliably commit the speaker to that meaning and can constitute lying. Expressive emoji representing facial expressions and emotional states demonstrate a range of commitment and lie ratings: those with high meaning agreement constitute more commitment and more of a lie than those with less meaning agreement in the first place. Emoji can constitute speaker commitment and they can be lies, but this result does not apply uniformly to all emoji and is instead tied to agreement, conventionality, and lexicalization.
Identifying sarcasm is a challenging research problem owing to its highly contextual nature. Several researchers have attempted numerous mechanisms to incorporate context, linguistic aspects, and supervised and semi-supervised techniques to determine sarcasm. It has also been noted that emojis in a text may also hold key indicators of sarcasm. However, the availability of sarcasm datasets with emojis is scarce. This makes it challenging to effectively study the sarcastic nature of emojis. In this work, we present SarcOji which has been compiled from five publicly available sarcasm datasets. SarcOji contains labeled English texts which all have emojis. We also analyze SarcOji to determine if there is an incongruence in the polarity of text and emojis used therein. Further, emojis’ usage, occurrences, and positions in the context of sarcasm are also studied in this compiled dataset. With SarcOji we have been able to demonstrate that frequency of occurrence of an emoji and its position are strong indicators of sarcasm. SarcOji dataset is now publicly available with several derived features like sentiment scores of text and emojis, most frequent emoji, and its position in the text. Compilation of the SarcOji dataset is an initial step to enable the study of the role of emojis in communicating sarcasm. SarcOji dataset can also serve as a go-to dataset for various emoji-based sarcasm detection techniques.
A cross-linguistic study of COVID-19 memes should allow scholars and professionals to gain insight into how people engage in socially and politically important issues and how culture has influenced societal responses to the global pandemic. This preliminary study employs framing analysis to examine and compare issues, actors and stances conveyed by both English and Chinese memes. The overall findings point to divergence in the way individuals communicate pandemic-related issues in English-speaking countries versus China, although a few similarities were also identified. ‘Regulation’ is the most common issue addressed by both English and Chinese memes, though the latter does so at a comparatively higher rate. The ‘ordinary people’ image within these memes accounts for the largest percentage in both data sets. Although both Chinese and English memes primarily express negative emotions, the former often occurs on an interpersonal level, whereas the latter aims at criticizing society and certain group of people in general. Lastly, this study proposes explanations for these findings in terms of culture and political environment.
Emojis are an integral part of Internet communication nowadays. Even though, they are supposed to make the text clearer and less dubious, some emojis are ambiguous and can be interpreted in different ways. One of the factors that determine the perception of emojis is the user’s personality. In this work, I conducted an experimental study and investigated how personality traits, measured with a Big Five Inventory (BFI) questionnaire, affect reaction time when interpreting emoji. For a set of emoji, for which there are several possible interpretations, participants had to determine whether the emoji fits the presented context or not. Using regression analysis, I found that conscientiousness and neuroticism significantly predict the reaction time the person needs to decide about the emoji. More conscientious people take longer to resolve ambiguity, while more neurotic people make decisions about ambiguous emoji faster. The knowledge of the relationship between personality and emoji interpretation can lead to effective use of knowledge of people’s characters in personalizing interactive computer systems.
Emojis can assume different relations with the sentence context in which they occur. While affective elaboration and emoji-word redundancy are frequently investigated in laboratory experiments, the role of emojis in inferential processes has received much less attention. Here, we used an online ratings task and a recognition memory task to investigate whether differences in emoji function within a sentence affect judgments of emoji-text coherence and subsequent recognition accuracy. Emojis that function as synonyms of a target word from the passages were rated as better fitting with the passage (more coherent) than emojis consistent with an inference from the passage, and both types of emojis were rated as more coherent than incongruent (unrelated) emojis. In a recognition test, emojis consistent with the semantic content of passages (synonym and inference emojis) were better recognized than incongruent emojis. Findings of the present study provide corroborating evidence that readers extract semantic information from emojis and then integrate it with surrounding passage content.
This paper proposes EmojiCloud, an open-source Python-based emoji cloud visualization tool, to generate a quick and straightforward understanding of emojis from the perspective of frequency and importance. EmojiCloud is flexible enough to support diverse drawing shapes, such as rectangles, ellipses, and image masked canvases. We also follow inclusive and personalized design principles to cover the unique emoji designs from seven emoji vendors (e.g., Twitter, Apple, and Windows) and allow users to customize plotted emojis and background colors. We hope EmojiCloud can benefit the whole emoji community due to its flexibility, inclusiveness, and customizability.
This study examines the evolutionary trajectory of graphicons in a 13-year corpus of comments from BiliBili, a popular Chinese video-sharing platform. Findings show that emoticons (kaomoji) rose and fell in frequency, while emojis and stickers are both presently on the rise. Graphicon distributions differ in comments and replies to comments. There is also a strong correlation between the types of graphicons used in comments and their corresponding replies, suggesting a priming effect. Finally, qualitative analysis of the 10 most-frequent kaomojis, emojis, and stickers reveals a trend for each successive graphicon type to become less about emotion expression and more integrated with platform-specific culture and the Chinese language. These findings lend partial support to claims in the literature about graphicon evolution.