Extraction of teletext subtitles from broadcast television for archival and analysis

David Laverty, John O'Raw

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Teletext subtitles are broadcast in some regions of the world, providing a potential resource of textual information corresponding to television current affairs, talk and magazine shows. Such programming offers an insight into sentiment, and will be useful in studies of national and global events. This paper discusses how textual information may be derived from digital television broadcasts featuring teletext subtitles, and shows some basic examples of their analysis for keywords related to the COVID-19 pandemic. The method has further possibilities, such as for the development of a searchable national archive of broadcast materials for education and research, and development of datasets for topics such as machine learning in sign language and sentiment analysis.

Original languageEnglish
Title of host publicationProceedings of the 33rd Irish Signals and Systems Conference, ISSC 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages6
ISBN (Electronic)9781665452274
DOIs
Publication statusPublished - 19 Jul 2022
Event33rd Irish Signals and Systems Conference, ISSC 2022 - Cork, Ireland
Duration: 09 Jun 202210 Jun 2022

Publication series

NameIrish Signals and Systems Conference: Proceedings
PublisherIEEE
ISSN (Print)2688-1446
ISSN (Electronic)2688-1454

Conference

Conference33rd Irish Signals and Systems Conference, ISSC 2022
Country/TerritoryIreland
CityCork
Period09/06/202210/06/2022

Keywords

  • Broadcasting
  • Sentiment
  • Subtitles
  • Television

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Information Systems
  • Signal Processing
  • Control and Optimization

Fingerprint

Dive into the research topics of 'Extraction of teletext subtitles from broadcast television for archival and analysis'. Together they form a unique fingerprint.

Cite this