Topic Analysis in News About AI: An Approach Based on LDA and Large Language Models

  • Jorge Galán-Mena
  • , Martín López-Nores
  • , Josué Galán
  • , Daniel Pulla-Sánchez
  • , Luis F. Guerrero-Vásquez
  • , Juan P. Salgado-Guerrero

    Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

    Abstract

    Topic analysis within broad and evolving fields poses great challenges when attempting to be addressed by traditional methods. In response, topic modeling seeks to automate the identification and analysis of underlying themes within several collections of documents in order to synthesize and facilitate the interpretation of their content. The present study applied multiple iterations of the Latent Dirichlet Allocation (LDA) model and the Best-K mechanism in the identification of topics within a volume of 250 news items labeled with “Artificial Intelligence” within a mainstream web portal. Additionally, a large language model (LLM) was implemented to improve interpretation and description for the labeling of found topics. As a result, 9 key topics were identified ranging from the main trends and challenges in AI.

    Original languageEnglish
    Title of host publicationEmerging Trends in Information Systems and Technologies - WorldCIST 2025 Volume 2
    EditorsAlvaro Rocha, Hojjat Adeli, Aneta Poniszewska-Maranda, Fernando Moreira, Isaias Bianchi
    PublisherSpringer Science and Business Media Deutschland GmbH
    Pages355-366
    Number of pages12
    ISBN (Print)9783032011299
    DOIs
    StatePublished - 2026
    Event13th World Conference on Information Systems and Technologies, WorldCIST 2025 - Florianopolis, Brazil
    Duration: Apr 15 2025Apr 17 2025

    Publication series

    NameLecture Notes in Networks and Systems
    Volume1582 LNNS
    ISSN (Print)2367-3370
    ISSN (Electronic)2367-3389

    Conference

    Conference13th World Conference on Information Systems and Technologies, WorldCIST 2025
    Country/TerritoryBrazil
    CityFlorianopolis
    Period04/15/2504/17/25

    Keywords

    • Automatic topic labeling
    • Large Language Models (LLM)
    • Latent Dirichlet Allocation
    • News media analysis
    • Topic modeling

    Fingerprint

    Dive into the research topics of 'Topic Analysis in News About AI: An Approach Based on LDA and Large Language Models'. Together they form a unique fingerprint.

    Cite this