AI Blob! LLM-Driven Recontextualization of Italian Television Archives

2025-08-13

AI Summary

This study addresses the challenge of automating narrative construction and cultural analysis for television archives. We propose a dynamic semantic retrieval framework: leveraging ASR transcripts from 1,547 Italian TV programs, we perform sentence-level semantic segmentation and vectorization to build a searchable video-fragment embedding repository. Integrating large language models (LLMs) with retrieval-augmented generation (RAG), our method enables theme-driven, cross-temporal recombination of fragments, generating narrative montages that balance ironic juxtaposition with thematic coherence. Unlike conventional approaches reliant on static metadata, our framework is the first to deeply couple semantic cataloging, vector-based retrieval, and LLM-based generation within broadcast archive recontextualization. The project releases open-source datasets and code, offering a reusable methodological paradigm for media history, digital humanities, and AI-mediated cultural research.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Natural Language Processing: Summarization
• Computer Vision: Image and Video Retrieval

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data

Abstract

This paper introduces AI Blob!, an experimental system designed to explore the potential of semantic cataloging and Large Language Models (LLMs) for the retrieval and recontextualization of archival television footage. Drawing methodological inspiration from Italian television programs such as Blob (RAI Tre, 1989-), AI Blob! integrates automatic speech recognition (ASR), semantic embeddings, and retrieval-augmented generation (RAG) to organize and reinterpret archival content. The system processes a curated dataset of 1,547 Italian television videos by transcribing audio, segmenting it into sentence-level units, and embedding these segments into a vector database for semantic querying. Upon user input of a thematic prompt, the LLM generates a range of linguistically and conceptually related queries, guiding the retrieval and recombination of audiovisual fragments. These fragments are algorithmically selected and structured into narrative sequences producing montages that emulate editorial practices of ironic juxtaposition and thematic coherence. By foregrounding dynamic, content-aware retrieval over static metadata schemas, AI Blob! demonstrates how semantic technologies can facilitate new approaches to archival engagement, enabling novel forms of automated narrative construction and cultural analysis. The project contributes to ongoing debates in media historiography and AI-driven archival research, offering both a conceptual framework and a publicly available dataset to support further interdisciplinary experimentation.

Problem

• Semantic cataloging of Italian TV archives using LLMs
• Automated retrieval and recontextualization of audiovisual fragments
• AI-driven narrative construction for cultural analysis

Innovation

• Uses ASR, semantic embeddings, RAG for archives
• LLM generates queries for thematic content retrieval
• Algorithmically creates narrative montages from fragments