Measuring Cross-Coverage Divergence for Threat-Intelligence Analysis
Paper — Maryam Fooladi, Federico Bottino, Alberto Trivero — NLPAICS 2026 — Alicante, Spain, 2026
Open-source intelligence relies heavily on source-level signals — domain provenance, amplification patterns, account coordination — which work against fabricated infrastructure but offer little leverage on content from established state media that is correctly attributed and passes source-level heuristics. We ask whether framing divergence across editorially-coherent outlet blocs is measurable as a content-level observable, and whether cross-bloc divergence exceeds the editorial polarization already present within a single domestic press tradition. Building on the event-state (ρ_e) density-matrix formalism of Bottino et al. (2026), we represent each bloc by a density matrix on a 15-dimensional framing-feature space and compute pairwise trace distances. On two contested events (Hormuz blockade 2026, n = 16, direct state-aligned coverage; Navalny death 2024, n = 14, state-aligned bloc reconstructed via quoted-proxy), the cross-bloc distance between state-aligned and mainstream-Western outlets exceeds the US-right/US-left distance by a factor of roughly 1.8 on both events. Top-eigenvector decomposition attributes the gap to interpretable framing axes — economic consequences and conflict framing on Hormuz, morality on Navalny. We position this as a measurement rather than a classifier; at two events the work characterizes the observable's behavior rather than calibrating thresholds.
—OSINT · Framing divergence · Threat intelligence
Source ↗ · Read more →
Why Organizational AI Needs Epistemic Infrastructure
Paper, preprint — Federico Bottino, Carlo Ferrero, Nicholas Dosio, Pierfrancesco Beneventano — arXiv preprint (cs.AI), 2026
Retrieval-Augmented Generation has become the default way of plugging an LLM into a company's documents. Inside real organizations, retrieval alone is not enough. An organization needs to know what it holds to be true, what is contested, what it is committed to, and — above all — what it doesn't know.
We present OIDA (Organizational Intelligence and Decision Architecture), a framework that represents organizational knowledge as typed objects with epistemic properties: commitment strength, contradiction status, provenance. The central piece is QUESTION-as-modeled-ignorance: a primitive that turns 'we don't know' into a first-class object the system can plan around, instead of filling the gap with a plausible-sounding sentence.
We also propose an Epistemic Quality Score (EQS) to evaluate not how fluent an answer sounds, but how honest it is about what it doesn't know. In our experiments OIDA reaches an EQS of 0.530 with 3,868 tokens, against 0.848 for a full-context baseline that uses 108,687 tokens — about 28× more. The QUESTION mechanism shows a statistically significant effect on outcome quality (Fisher exact, p = 0.0325).
—Epistemic infrastructure · Organizational AI · RAG
arXiv ↗ · PDF ↗ · Read more →
Why Traditional NLP Fails Political News — and How LLMs Can Bridge the Gap
Paper — Maryam Fooladi, Federico Bottino — 3rd Workshop on NLP for Political Sciences (PoliticalNLP 2026) at LREC 2026 — Palma de Mallorca, 2026
Classical sentiment analysis has been the default lens through which NLP looks at political news for over a decade. It is also the wrong lens. On politically substantive coverage, around 70% of articles get flattened into a single 'neutral' bin — exactly the cases where framing, ideology and rhetorical strategy are doing the work.
We systematically compare traditional sentiment pipelines (lexicon-based, fine-tuned transformers) with LLM-based approaches on a corpus of political news. The LLM family does not just score better. It answers a different, more honest question. Where the classical pipeline gives a 3-class verdict (positive / neutral / negative), an LLM-based reading recovers the dimensions political scientists actually use: framing, ideological positioning, rhetorical strategy, stance toward named actors.
We propose an evaluation protocol that focuses on the recovery of these dimensions instead of aggregate accuracy, and we publish the comparative results and the prompts used. The paper is a methodological argument as much as an empirical one: if the goal is to study political discourse, sentiment is not the right baseline anymore.
—Political NLP · LLM evaluation · Discourse analysis
Source ↗ · PDF ↗ · Read more →
Paper — Maryam Fooladi, Federico Bottino — Information Disorder Workshop (InDor) at LREC 2026 — Palma de Mallorca, 2026
Most AI systems aimed at the modern information landscape are built as a single monolithic pipeline: ingest, classify, output. That works on a benchmark. It falls apart the moment a real institutional analyst — a regulator, a media-literacy team, a strategic-foresight unit — has to use the result.
The paper proposes a four-layer architecture instead. (1) A strategic layer for narrative shifts, ideological framing, long-horizon signals. (2) An operational layer for source extraction, entity and event monitoring. (3) A compliance layer that carries the regulatory signal: provenance, audit trail, risk scoring. (4) A collaboration layer that models the analyst–AI interaction explicitly: review loops, handoffs, the fact that a person is accountable downstream.
The four layers are interconnected. Each one passes structured signal to the next, instead of competing for the same task. We argue that this separation is what makes the output trustable, auditable and actionable for an institutional analyst, and we explain why monolithic single-layer systems fail those three requirements at once. The paper is a position-and-design contribution: it names the layers, defines their interfaces, and grounds them in working analyst use cases.
—Information disorder · Multi-layer AI · Analyst tooling
Source ↗ · PDF ↗ · Read more →
Piccola guida all'uso consapevole del web
Book — Pietro Jarre, Federico Bottino — Golem Edizioni, 2018
A practical guide to a more conscious use of the web. Sloweb maps how the web actually works, where its threads run, and how to detect digital misbehaviour — written for readers who want to understand the medium rather than just consume it. Co-authored with Pietro Jarre.
—Digital ethics · Media sociology
Source ↗ · Read more →