Emoji–Emotion Ranking System Using Twitter Data

2026-05-13

2026 IEEE 6th International Conference on Smart Information Systems and Technologies (SIST)

AI Summary

This study addresses the limitation of existing sentiment analysis systems that treat emojis as static indicators, overlooking the context-dependence of their affective distributions. To this end, it proposes an emoji-aware sentiment analysis framework built upon Twitter data. Through text preprocessing, sentiment classification, and statistical aggregation, the approach estimates the association distributions between emojis and five basic emotions. Furthermore, Russell’s valence-arousal space is incorporated to enable continuous affective projection and interpretation. By challenging the conventional assumption of fixed sentiment polarity, this work demonstrates that emojis exhibit probabilistic and context-dependent affective characteristics. Ultimately, it establishes a novel paradigm for understanding the dynamic affective semantics of non-textual symbols in computational linguistics.

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 emojiaware emotion analysis framework based on a Twitter (X) dataset of 100,000 emoji-containing replies collected between 2020 and 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.

Problem

• emoji
• emotion analysis
• sentiment
• Twitter data
• affective computing

Innovation

• Emoji-Emotion Ranking
• Context-sensitive Emotion Analysis
• Valence-Arousal Space
• Probabilistic Emotional Profiles
• Twitter Data