Quantum-Inspired Semantic Encoding and Temporal Transformer Fusion (QuST-TF) for Misinformation Detection

Misinformation propagates more rapidly than factual content on social media, presenting significant challenges for automated misinformation detection. Existing approaches often focus solely on textual features without incorporating temporal information, treat timing and propagation as separate factors, or apply quantum-inspired methods primarily to multimodal data rather than text-centric misinformation. This study introduces QuST-TF (Quantum-inspired Semantic encoding and Temporal Transformer Fusion), a unified model designed to detect misinformation in tweets and news articles. QuST-TF integrates quantum-inspired (classical approximation) amplitude encoding, time-aware Transformer fusion, and propagation graph attention based on engagement data, without reliance on images, audio, or quantum hardware. Performance gains are achieved through quantum-inspired (classical approximation) nonlinear angular modulation (cosine and sine rotations) implemented via classical computation, rather than genuine quantum computing. All computations utilize classical Dense layers, Rectified Linear Unit (ReLU) activations, and cosine/sine functions on CPUs or GPUs; quantum hardware is not required. The quantum-inspired (classical approximation) layer applies classical rotation-based transformations to enrich the semantic representation of BERT (Bidirectional Encoder Representations and Transformer) embeddings. Temporal information is captured by a dual-attention Transformer encoder, while propagation graph attention monitors the spread of claims. Evaluation on FakeNewsNet and PHEME datasets demonstrates 91.4% and 95.5% accuracy, respectively, with 34% fewer trainable parameters compared to standard Transformers. Ablation studies indicate that quantum encoding is the most influential component (+3.0% versus without quantum encoding), surpassing the contributions of graph attention (+2.6%) and temporal attention (+2.2%). The integration of all three components yields a 1.3% synergistic improvement, confirming effective inter-module collaboration. Attention visualization enhances interpretability, supporting the utility of QuST-TF for fact-checking applications.