Emoji use reveals varied emotions on Twitter beyond simple sentiments
Emoji-Emotion Ranking System Using Twitter Data
Computation and LanguageSocial and Information Networks
Summary
Many people use emojis instead of words when talking online, but computers often guess their feelings too simply. The authors studied 100,000 Twitter replies with emojis and analyzed which emotions appeared alongside each emoji. They found that emojis don’t always show just one feeling but a mix of different emotions depending on the context. Their method ranks emojis by how strongly they relate to five basic feelings and maps them into a space that helps understand their emotional tone more smoothly.
What this means in practice
- •For social media analysts: Improve emotion detection tools by accounting for emojis’ varied emotional profiles rather than fixed sentiment labels.
- •For chatbot developers: Design chatbots that respond more appropriately to user emotions by interpreting emojis’ probabilistic emotional meanings.$Commercial implications: Enables commercial conversational agents to better understand user moods and improve interaction quality using richer emoji emotion cues.
Tested on one dataset.
Authors
Danila Khlebokazov, Nurkhan Tashimov, Pakizar Shamoi
Abstract
Nowadays, emojis are often replacing words. Yet computational systems still oversimplify them. Most existing approaches treat emojis as static sentiment indicators and overlook their emotional distributions. In this study, we propose an emoji-aware emotion analysis framework based on a Twitter (X) dataset of 100,000 emoji-containing replies collected between 2020-2025. After preprocessing and text cleaning, we applied text-to-emotion classification to detect five primary emotions (Happy, Angry, Sad, Fear, and Surprise) for each message. By aggregating emotion scores across contexts in which each emoji appears, we estimate emoji-emotion association distributions and construct an emoji-emotion ranking system reflecting relative emotional dominance. Furthermore, we project emojis into the Russell valence-arousal space to enable continuous affective interpretation. Our results demonstrate that emojis exhibit probabilistic, context-sensitive emotional profiles rather than fixed sentiment polarities.