Identifying Topics in Tweets Related to Citizen Security

  • Josselyn Jimenez
  • , Ruth Reátegui
  • , Janneth Chicaiza
  • , Henry N. Roa
  • , Daniel Pulla-Sánchez

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

    Abstract

    Crime and violence remain a significant challenge that impacts the economy and well-being. Citizens’ voices can be heard through social networks, especially when discussing security issues. Therefore, the objective of this research is to identify topics that are discussed in social network X concerning citizen security. Two algorithms were applied to identify the topic: LDA and BERTopic. Using the coherence score in LDA, the highest values were for 8 and 15 topics; the same number of topics were obtained with BERTopic. As a result, some of the topics discussed are related to narcotrafficking, traffic arms, racketeering, political corruption, emigration, and immigration problems.

    Original languageEnglish
    Title of host publicationEmerging Trends in Information Systems and Technologies - WorldCIST 2025. Volume 1
    EditorsAlvaro Rocha, Hojjat Adeli, Aneta Poniszewska-Maranda, Fernando Moreira, Isaias Bianchi
    PublisherSpringer Science and Business Media Deutschland GmbH
    Pages569-578
    Number of pages10
    ISBN (Print)9783031971181
    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
    Volume1514 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

    • BERTopic
    • Citizen security
    • LDA
    • Topic modeling

    Fingerprint

    Dive into the research topics of 'Identifying Topics in Tweets Related to Citizen Security'. Together they form a unique fingerprint.

    Cite this