Akademik Veri Yönetim Sistemi
37th IEEE International Conference on Tools with Artificial Intelligence (ICTAI), Athens, Yunanistan, 3 - 05 Kasım 2025, ss.10-18, (Tam Metin Bildiri)
In politically charged environments, understanding how ideological narratives emerge, spread, and shape user behav- ior on social media is critical for applications ranging from misin- formation detection to enriching public discourse with verifiable truth. In this study, we present NARRA-SCALE, a framework that brings together network analysis, narrative detection, stance classification, and bipartite scaling to place users, communities, and messages along a single ideological dimension. As a case study, we apply NARRA-SCALE to a U.S. race relations related dataset chiefly polarized between “Black Lives Matter” and “All Lives Matter” supporters. We extract topic coded key phrases and named entities using frequency-based heuristics. Using key phrase co-occurrence relationships and latent representations of matching messages, we mine grouped (entities, issues/aspects, values) triplets characterizing key recurring narratives within the corpus. We use an LLM to summarize messages matching each triplet. Subsequently, a panel of experts label the stance information of the narratives on their key phrases, enabling weak supervision for training a high-accuracy stance detection model which achieves an 81% accuracy on a held-out gold standard. Next, we construct a signed bipartite graph with colored edges (i.e., representing support versus opposition) between users and key terms mentioned in their messaging corresponding to debated core values, issues, and actors to co-scale their positions on a [-1,+1] range. Our method reaches 91% agreement with user groups identified through community structure as well as with the “ideal points” of political elites and the general public on Twitter in the U.S. and five European countries