More than half of human genes exercise alternative polyadenylation (APA) and generate mRNA transcripts with varying 3' untranslated regions (UTR). However, current computational approaches for identifying C/PASs and quantifying 3'UTR length changes from bulk RNA-seq data fail to unravel actual tissue- and disease-specific APA dynamics. Here, we developed a next-generation bioinformatics algorithm and application, PolyAMiner-Bulk, that utilizes an attention-based machine learning architecture and an improved vector projection-based engine to assess differential APA dynamics accurately. When applied to earlier studies, PolyAMiner-Bulk accurately identified more than twice the number of APA changes in an RBM17 knockdown bulk RNA-seq benchmarking dataset compared to current generation tools. Moreover, on a separate dataset, PolyAMiner-Bulk revealed novel APA dynamics and pathways in scleroderma pathology and identified a novel APA gene that was independently identified as being involved in scleroderma pathogenesis in a separate study. Lastly, as a proof-of-principle, we used PolyAMiner-Bulk to analyze bulk RNA-seq data of post-mortem prefrontal cortexes from the ROSMAP data consortium and unraveled novel APA dynamics in Alzheimer's Disease. Our method, PolyAMiner-Bulk, creates a paradigm for future alternative polyadenylation analysis from bulk RNA-seq data.