A Comprehensive Review on Hashtag Recommendation: From Traditional to Deep Learning and Beyond

2025-03-24

AI Summary

Social media tag recommendation faces core challenges including data sparsity, cold-start problems, and limited interpretability, while existing surveys suffer from platform-specific biases and outdated coverage. This paper presents a systematic literature review, introducing for the first time a cross-platform, full-lifecycle structured taxonomy that traces methodological evolution—from statistical approaches to multimodal Transformers—across problem formulation, filtering strategies, and evaluation paradigms. Methodologically, it innovatively integrates traditional NLP, graph neural networks, multimodal representation learning, and context-aware Transformers. The contribution includes a hybrid evaluation framework unifying quantitative metrics, qualitative analysis, and interpretability assessment. Results reveal a paradigm shift toward user-centric, adaptive recommendation, offering theoretical foundations and practical guidelines for downstream tasks such as tweet classification, sentiment analysis, and popularity prediction.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining
• Machine Learning: Multimodal Learning

Application Category

• User Modeling, Personalization and Recommendation: Social recommender systems and personalization for the social Web
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Social Networks and Social Media: Social mining and social search on the Web

Abstract

The exponential growth of user-generated content on social media platforms has precipitated significant challenges in information management, particularly in content organization, retrieval, and discovery. Hashtags, as a fundamental categorization mechanism, play a pivotal role in enhancing content visibility and user engagement. However, the development of accurate and robust hashtag recommendation systems remains a complex and evolving research challenge. Existing surveys in this domain are limited in scope and recency, focusing narrowly on specific platforms, methodologies, or timeframes. To address this gap, this review article conducts a systematic analysis of hashtag recommendation systems, comprehensively examining recent advancements across several dimensions. We investigate unimodal versus multimodal methodologies, diverse problem formulations, filtering strategies, methodological evolution from traditional frequency-based models to advanced deep learning architectures. Furthermore, we critically evaluate performance assessment paradigms, including quantitative metrics, qualitative analyses, and hybrid evaluation frameworks. Our analysis underscores a paradigm shift toward transformer-based deep learning models, which harness contextual and semantic features to achieve superior recommendation accuracy. Key challenges such as data sparsity, cold-start scenarios, polysemy, and model explainability are rigorously discussed, alongside practical applications in tweet classification, sentiment analysis, and content popularity prediction. By synthesizing insights from diverse methodological and platform-specific perspectives, this survey provides a structured taxonomy of current research, identifies unresolved gaps, and proposes future directions for developing adaptive, user-centric recommendation systems.

Problem

• Reviewing hashtag recommendation systems' evolution and methodologies.
• Addressing challenges like data sparsity and model explainability.
• Proposing future directions for adaptive recommendation systems.

Innovation

• Transformer-based deep learning models
• Multimodal methodologies for hashtag recommendation
• Hybrid evaluation frameworks for performance