This episode was based on the article "Domain Analysis in SEO" from the Semantic Blog, which explores domain analysis as a fundamental tool in Information Science and its application in semantic SEO. I sought to detail how domain analysis helps understand, organize, and retrieve information in specific areas of knowledge, going beyond simple keyword research.

The discussion covers Birger Hjørland's eleven approaches to domain analysis, illustrating their relevance for creating robust taxonomies, ontologies, and workflows in SEO. The article also draws a parallel between domain analysis and domain modeling, highlighting their differences and the value of the former for developing effective digital solutions and promoting interdisciplinarity.

In this episode, we propose a new methodology for web content management, focusing on users' information needs diverging from Google's current search intent-based approach. You'll hear about criticisms of the search intent model for its simplicity and for ignoring users' subjective aspects, analyzing its historical Evolution, as well as Google's four intent classifications. In contrast, we present Carol Kuhlthau's Information Search Process (ISP), which considers the emotional, cognitive, and physical aspects of search and adapts three of its stages—Initiation, Exploration, and Collection—to formulate a new framework for creating content briefs. We advocate integrating concepts from library science and information science to improve SEO and content management, aiming to meet users' complex needs.

In today's episode, "Query Unfolding: A Data-Driven Approach to AI Search Visibility," we explore how Google's AI search breaks down an initial query into multiple contextual subqueries, a process called "query fan-out." We discuss how traditional SEO tools are inadequate for this new reality, proposing a new framework and a simulator in Google Colab to predict the likely follow-up questions AI might generate. This episode is based on my article of the same name, where I comment on Andrea Volpini's original text, adding insights into Ranganathan's concept of facets and delving deeper into the implications of "fan-out" for information retrieval with LLMs and knowledge graphs. In essence, the core text offers a 10-principle strategic guide to optimizing content for AI search, emphasizing semantic coverage, conversational adaptability, and understanding how AI fragments and interprets content to generate comprehensive answers.

company'sUltimately, the company's highlights promote a shared understanding. The source emphasizes the advantages of adopting ontologies, which include fostering a common sense, facilitating data integration, and lowering development costs. Additionally, the publication highlights the link between ontologies, structured data, and search engine optimization (SEO), arguing that effective content modeling and data structuring are essential for enhancing a company's online visibility. Concepts. It presents ontologies as "spiked information models" that are capable of structuring the logic of business concepts, helping to overcome challenges associated with imprecise domain models. The source highlights the benefits of adopting ontologies, including creating a common understanding, optimizing data integration, and reducing development costs. Finally, the publication establishes a connection between ontologies, structured data, and SEO, arguing that content modeling and data services are key to enhancing companies' online visibility.

In this episode, we introduce and explore the nature and theory of information, communication, and control, encompassing the fields of cybernetics and information science, in great detail. A set of excerpts, notably from Norbert Wiener, establishes cybernetics as a unified statistical theory of communication and control in machines and living organisms, discussing the role of feedback, the transition from Newtonian mechanics to statistics, and the development of computing machines and the nervous system. Another excerpt delves into Claude Shannon's mathematical theory of communication, which quantifies information using a logarithmic measure, introduces the concept of entropy, and discusses the capacity of discrete and continuous channels, even in the presence of noise. Finally, a third source, focusing on information science and Peter Ingwersen's cognitive models, examines the discipline's five core areas of study, drawing on the view that information is inherently linked to the user's state of uncertainty or need, and distinguishes human (cognitive) processing from machine processing of data.

This examines the enduring significance of the era. The episode explores the continuing relevance of the librarian's reference interview in the age of Artificial Intelligence (AI), arguing that traditional information retrieval principles remain essential for effective interactions with tools like Google Gemini. The author emphasizes the importance of structuring prompts intelligently, utilizing frameworks such as Kipling's six questions (What, Why, Who, How, When, and Where) to refine queries and achieve more precise results. Furthermore, the article analyzes the eight steps of Grogan's reference process, correlating each stage of the user's journey with the interaction with AI agents, from the initial perception of the problem to obtaining an informed solution. In essence, the source argues that excellence in information retrieval in the digital landscape is a collaboration between human and artificial intelligence, where librarianship skills guide the potential of AI.

The episode "AI: How do models get updated?" explores how artificial intelligence (AI) models and search engines obtain and process information, demystifying the idea that AIs scan the web in real-time for every answer. The author presents detailed responses from Gemini, ChatGPT, and Claude, which explain their respective training processes. The AIs reveal that they are trained on vast, pre-processed datasets (like Common Crawl or C4) offline and periodically, unlike traditional search crawlers (like Googlebot), which continuously index the web. For generative searches, a process like Retrieval-Augmented Generation (RAG) is used, where relevant information is retrieved from updated search indexes and then synthesized by the language model to generate a cohesive response, with sources cited. In short, there is a clear distinction between data collection for AI training and the algorithms used for traditional and generative searches, although all rely on the web's vast "library."

This episode explains the difference between tokens and embeddings, fundamental concepts in Artificial Intelligence (AI) and Large-Scale Language Models (LSMs) that impact SEO. Tokens are basic textual units, such as words, used in traditional keyword searching through sparse embeddings that consider only frequency. In contrast, dense embeddings are numerical representations that capture the semantic meaning and context of words, making them crucial for natural language understanding in modern AI systems. The article traces the evolution of Google search, highlighting how technologies like RankBrain, BERT, and MUM utilize embeddings to enhance the relevance of Search results. Finally, it presents hybrid search as a solution that combines the efficiency of semantic search with the accuracy of lexical (token-based) search, ensuring that AI systems can handle information both inside and outside their training domain.