Emoji meaning varies with topic and emotion on Twitter
Beyond a Single Sentiment Score: Topical and Affective Dimensions of Emoji Meaning on Twitter
Computation and LanguageArtificial IntelligenceSocial and Information Networks
Summary
Emoji are often thought to just show a simple feeling, like happy or sad. This paper shows that emoji meanings are more complex because they also depend on the topic they appear with. The authors analyzed many tweets and found that emoji used in specific topics tend to have stronger emotional meanings. They also checked how well emoji can help detect sarcasm and found that emoji cues are very strong but might make sarcasm prediction too easy in some datasets.
What this means in practice
- •For social media analysts: Improve sentiment and topic analysis tools by accounting for emoji meanings that vary with contextual topics and emotional intensity on Twitter.
- •For chatbot developers: Enhance chatbot understanding by integrating emoji usage patterns that reflect both topics and emotions, supporting more nuanced user interactions.
Authors
Rohan James, Ioannis Christofilogiannis, Yuuv Jauhari, Shreya Shah, Gauri Pethkar
Abstract
Emoji are widely treated as compact affective tokens whose meaning is summarised by a single sentiment score. We argue that this picture is incomplete. From a corpus of 16{,}575 English tweets and a per-emoji metric we call \emph{stability delta} (within-class minus between-class cosine similarity of sentence embeddings), we show that emojis used in tightly clustered topical contexts also exhibit \emph{more} polarised crowd-sourced sentiment, not less. Validated against the Kralj Novak et al.\ (2015) sentiment lexicon, the central correlation is Spearman $ρ= +0.361$ (Holm $p = 0.015$, 95\% bootstrap CI $[+0.10, +0.59]$); against the independent Ferré et al.\ (2025) Spanish 13-emotion ratings, $ρ= +0.509$ ($p = 0.0003$). The result survives permutation testing, BCa bootstrap, leave-one-out jackknife, partial correlation controlling for emoji frequency, and Holm correction across a four-test family. Topical coherence and affective dispersion are distinct dimensions of emoji meaning. As a downstream check we report leakage-free five-fold cross-validation results for sarcasm classification on the Emoji Sarcasm Dataset; all three baselines (a gated multimodal architecture, fine-tuned BERTweet features, and fine-tuned RoBERTa features) score above 0.97 macro F1, indicating the dataset has saturating emoji-label cues. We frame the classifier as supporting evidence rather than the contribution.