Deep Learning (DL) has attracted increasing attention on account of its significant processing power in tasks such as speech, image, or text processing. In order to the exponential development and widespread availability of digital Social Media (SM); analyzing these data using traditional tools and technologies is tough or even intractable. DL is found as an appropriate solution to this problem. In this article, we keenly discuss practiced DL architectures by presenting a taxonomy-oriented summary, following the major efforts made towards Social Media Analytics (SMA). Nevertheless, instead of the technical description, the article emphasis on describing the SMA-oriented problems with DL-based solutions. To this end, we also highlight the DL research challenges (such as scalability, heterogeneity, multimodality etc.) and future trends.

Graphs are a foundational way to represent scenarios where objects interact in pairs. Recently, Graph Neural Networks (GNNs) have become widely used for modeling simple graph structures, either in homogeneous or heterogeneous graphs, where edges represent pairwise relationships between nodes. However, many real-world situations involve more complex interactions where multiple nodes interact simultaneously, as observed in contexts such as social groups and gene-gene interactions. Traditional graph embeddings often fail to capture these multifaceted non-pairwise dynamics. A hypergraph, which generalizes a simple graph by connecting two or more nodes via a single hyperedge, offers a more efficient way to represent these interactions. While most existing research focuses on homogeneous and static hypergraph embeddings, many real-world networks are inherently heterogeneous and dynamic. To address this gap, we propose a GNN-based embedding for dynamic heterogeneous hypergraphs, specifically designed to capture non-pairwise interactions and their evolution over time. Unlike traditional embedding methods that rely on distance or meta-path- based strategies for node neighborhood aggregation, a k -hop neighborhood strategy is introduced to effectively encapsulate higher-order interactions in dynamic networks. Furthermore, the information aggregation process is enhanced by incorporating semantic hyperedges, further enriching hypergraph embeddings. Finally, embeddings learned from each timestamp are aggregated using a mean operation to derive the final node embeddings. Extensive experiments on five real-world datasets, along with comparisons against homogeneous, heterogeneous, and hypergraph-based baselines (both static and dynamic), demonstrate the robustness and superiority of our model.