Skip to main navigation Skip to search Skip to main content

Geo-Personalization Bias in News Search: Analyzing Filter Bubbles in Search Engine Results with Multi-Perspective LLM Annotation

  • Seoul National University of Science and Technology (SNUST)
  • Georgia Institute of Technology
  • Louisiana State University

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

Abstract

This study systematically examines the formation patterns of filter bubbles in search engine results from an end-user perspective, analyzing them across diverse perspectives. Specifically, we investigate filter bubble formation patterns in search results obtained from two globally dominant search engines over a period of two months on six representative controversial topics. We analyze filter bubble formation in search engine results by varying geo-location while controlling other influencing factors. To ensure objective and scalable analysis, we utilize annotations generated by large language models (LLMs) that represent multiple distinct perspectives. We provide evidence demonstrating how filter bubbles are formed by addressing the following four research questions (RQs): search engine-specific personalization algorithms (RQ1) differently contribute to filter bubble formation; 2) user geo-location differences (RQ2) generate distinct filter bubbles reflecting regional characteristics; 3) these filter bubbles evolve in response to regional social events over time (RQ3); and 4) topic characteristics (RQ4) result in varying patterns of filter bubble formation. Our source code and scripts are publicly available at: https://anonymous.4open.science/r/Filter_Bubble-183C.

Original languageEnglish
Title of host publicationWSDM 2026 - Proceedings of the 19th ACM International Conference on Web Search and Data Mining
PublisherAssociation for Computing Machinery, Inc
Pages850-859
Number of pages10
ISBN (Electronic)9798400722929
DOIs
StatePublished - 21 Feb 2026
Event19th ACM International Conference on Web Search and Data Mining, WSDM 2026 - Boise, United States
Duration: 22 Feb 202626 Feb 2026

Publication series

NameWSDM 2026 - Proceedings of the 19th ACM International Conference on Web Search and Data Mining

Conference

Conference19th ACM International Conference on Web Search and Data Mining, WSDM 2026
Country/TerritoryUnited States
CityBoise
Period22/02/2626/02/26

Keywords

  • filter bubble detection
  • geo-location personalization
  • multi-perspective llm annotation
  • multi-region data collection
  • search engine personalization
  • statistical significance testing

Fingerprint

Dive into the research topics of 'Geo-Personalization Bias in News Search: Analyzing Filter Bubbles in Search Engine Results with Multi-Perspective LLM Annotation'. Together they form a unique fingerprint.

Cite this