Answers are grounded in this paper and cite their sources.
Analysis of over 650k messages on Telegram reveals emoji reactions signal social approval, suggesting new implications for sentiment analysis.
Emoji reactions are a frequently used feature of messaging platforms. Prior work mainly interpreted emojis as indicators of emotional resonance or user sentiment. However, emoji reactions may instead reflect broader social dynamics. Here, we investigate the communicative function of emoji reactions on Telegram by analyzing the relationship between the emotional and rhetorical content of messages and the emoji reactions they receive. We collect and analyze over 650k Telegram messages that received at least one emoji reaction. We annotate each message with sentiment, emotion, persuasion strategy, and speech act labels, and infer the sentiment and emotion of emoji reactions using both lexicons and large languages. We find a systematic mismatch between message sentiment and reaction sentiment, with positive reactions dominating even when the message is neutral or negative. We show that this pattern remains consistent across rhetorical strategies and emotional tones, suggesting that emoji reactions may signal a degree of social approval rather than reflecting emotional resonance. Finally, we shed light on the communicative strategies that predict greater emoji engagement. These findings have methodological implications for sentiment analysis, as interpreting emoji reactions as direct proxies for emotional response may be misleading.
No takes yet. Share an insight, caveat, or question.
Tardelli et al. (2025) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: