Social media platforms have become central to modern communication, yet they also harbor offensive content that challenges platform safety and inclusivity. While prior research has primarily focused on textual indicators of offense, the role of emojis, ubiquitous visual elements in online discourse, remains underexplored. Emojis, despite being rarely offensive in isolation, can acquire harmful meanings through symbolic associations, sarcasm, and contextual misuse. In this work, we systematically examine emoji contributions to offensive Twitter messages, analyzing their distribution across offense categories and how users exploit emoji ambiguity. To address this, we propose an LLM-powered, multi-step moderation pipeline that selectively replaces harmful emojis while preserving the tweet’s semantic intent. Human evaluations demonstrate that our approach effectively reduces offensiveness while preserving semantic integrity. Our analysis also reveals heterogeneous effects across offense types, offering nuanced insights for online communication and emoji moderation.

The frequent introduction of new emojis in each Unicode release creates a dynamic shift in social media content, providing a unique opportunity to explore the evolution of digital language. Analyzing a large dataset of sampled English tweets, we examine how newly released emojis gain popularity and evolve in meaning. We find that the community size of early adopters and emoji semantics are positively correlated with their popularity. Certain emojis experienced notable shifts in the meanings and sentiment associations during the diffusion process. Additionally, we propose a novel framework utilizing language models to extract words and pre-existing emojis with semantically similar contexts, which enhances the interpretation of new emojis. The framework demonstrates its effectiveness in improving downstream text classification performance by substituting unknown new emojis with familiar ones. This study offers a new perspective in understanding how new language units are adopted, adapted, and integrated into the fabric of online communication.

Multimodal emotion recognition in conversation (MERC) refers to identifying and classifying human emotional states by combining data from multiple different modalities (e.g., audio, images, text, video, etc.). Specifically, human emotional expressions are often complex and diverse, and these complex emotional expressions can be captured and understood more comprehensively through the fusion of multimodal information. Most existing graph-based multimodal emotion recognition methods can only use shallow GCNs to extract emotion features and fail to capture the temporal dependencies caused by dynamic changes in emotions. To address the above problems, we propose a Dynamic Graph Neural Ordinary Differential Equation Network (DGODE) for multimodal emotion recognition in conversation, which combines the dynamic changes of emotions to capture the temporal dependency of speakers’ emotions. Technically, the key idea of DGODE is to use the graph ODE evolution network to characterize the continuous dynamics of node representations over time and capture temporal dependencies. Extensive experiments on two publicly available multimodal emotion recognition datasets demonstrate that the proposed DGODE model has superior performance compared to various baselines. Furthermore, the proposed DGODE can also alleviate the over-smoothing problem, thereby enabling the construction of a deep GCN network.