A Comprehensive Multimodal Framework for Optimizing Social Media Hashtag Recommendations

In the dynamic landscape of social media, the strategic use of hashtags has emerged as a crucial tool for enhancing content discoverability and engagement. This research introduces the neurosymbolic contrastive framework (NSCF), an innovative methodology designed to address the multifaceted challenges inherent in automated hashtag recommendation, such as the integration of multimodal data, the context sensitivity of content, and the dynamic nature of social media trends. By combining deep learning's representational strengths with the deductive prowess of symbolic artificial Intelligence (AI), NSCF crafts contextually relevant and logically coherent hashtag suggestions. Its dual-stream architecture meticulously processes and aligns textual and visual content through contrastive learning, ensuring a comprehensive understanding of multimodal social media data. The framework's neurosymbolic integration leverages structured knowledge and logical inference, significantly enhancing the relevance and coherence of its recommendations. Evaluated against a variety of datasets, including MM-INS, NUS-WIDE, and HARRISON, NSCF has demonstrated exceptional performance, outshining existing models and baseline methods across key metrics such as precision (0.721–0.701), recall (0.736–0.716), and F1 score (0.728–0.708). This research represents a major advancement in social media analytics as it not only demonstrates NSCF's novel approach but also sheds light on its potential to transform hashtag recommendation systems.