Political slant in public broadcasting Author: Bart de Goede ...
Why?Automatically identify politicalslant in Dutch publicbroadcasting
Gentzkow & Shapiro (2010) Econometrical research: compare language use of news outlets to political language Conclusion: ‘...
OperationalizationFind characteristic words for Republicans andDemocrats in Congress Proceedings.Count relative frequencie...
Di erencesDutch versus EnglishTelevision instead of newspapersMore political partiesOther technique to derive characterist...
TelevisionSubtitles for the hearing impaired (http://tt888.nl)Data complete from January 2008 to February 2011Problem: Har...
Television Before After Broadcast with title 16.995 32.491 ...
Television Nova 362.844 words ...
Political groupsParliamentary period with greatest overlap on TV data set:Balkenende IVIdeology: goverment - opposition, n...
Political groupsGovernment (CDA, PvdA and ChristenUnie)Left wing opposition (GroenLinks, SP)Right wing opposition (PVV, VV...
Parsimonious languagemodels λ(t|D) et = tf (t, D) · (1 − λ)P ...
Parsimonious languagemodelsProbability distribution from word frequencies perdocumentCompare distribution with collection ...
Parsimonious languagemodelsFilter out corpus speci c stopwords (‘voorzitter’)Remove noise Hiemstra, D., Robertson, S., a...
Parsimonious languagemodels
Parsimonious languagemodels
Parsimonious languagemodels
ComparisonTwo methods: estimated probability and Kullback-Leiblerdivergence‘For each political group, estimate the probabi...
ResultsRight never winsCasual evaluation does not imply ‘strange’ right wing wordsGovernment and left results are closeCom...
ConclusionsLanguage in Dutch public broadcasting is notparticularly left (only a slight preference was found)Descriptive r...
Questions?
of 20

Political slant in public broadcasting

Presentation of my bachelor thesis Information Science. It provides an overview of my attempt to use parsimonious language models on parliamentary proceedings to derive characteristic words for left-wing and right-wing parties, and compare the occurences of these words in subtitles of programmes broadcasted by Dutch public broadcasting organizations.
Published on: Mar 4, 2016
Published in: News & Politics      
Source: www.slideshare.net


Transcripts - Political slant in public broadcasting

  • 1. Political slant in public broadcasting Author: Bart de Goede Supervisors: Dr. Maarten Marx Dr. Johan van Doornik June 23, 2011
  • 2. Why?Automatically identify politicalslant in Dutch publicbroadcasting
  • 3. Gentzkow & Shapiro (2010) Econometrical research: compare language use of news outlets to political language Conclusion: ‘An economically signi cant demand for news slanted towards one’s own political ideology exists.’ Gentzkow, M. and Shapiro, J. M. (2010). What drives media slant? Evi-dence from U.S. daily newspapers. Econometrica, 78(1):35–71.
  • 4. OperationalizationFind characteristic words for Republicans andDemocrats in Congress Proceedings.Count relative frequencies of these words in newspapersCompare occurrence of words between newspapers Gentzkow, M. and Shapiro, J. M. (2010). What drives media slant? Evi-dence from U.S. daily newspapers. Econometrica, 78(1):35–71.
  • 5. Di erencesDutch versus EnglishTelevision instead of newspapersMore political partiesOther technique to derive characteristic wordsOther comparison method(s)
  • 6. TelevisionSubtitles for the hearing impaired (http://tt888.nl)Data complete from January 2008 to February 2011Problem: Hardly any useful metadata
  • 7. Television Before After Broadcast with title 16.995 32.491 Unique titles 4.560 --> 2.702 2.238 Broadcast 1.104 1.064 frequency > 2 Solution: TV guide
  • 8. Television Nova 362.844 words Pauw & Witteman 895.935 words DWDD 1.626.929 words EenVandaag 1.556.642 words Nos Journaal 12.609.620 words Goedemorgen Nederland 760.658 words Netwerk 879.635 words NOS Jeugdjournaal 1.383.728 words Buitenhof DWDD EenVandaag Goedemorgen Nederland Het Elfde Uur Holland Doc Knevel en Van den Brink Netwerk Nieuwsuur NOS Jeugdjournaal Nos Journaal Nova Ochtendspits Pauw & Witteman PowNews SchoolTV Weekjournaal Sinterklaasjournaal Tegenlicht Uitgesproken Vragenuurtje Zembla
  • 9. Political groupsParliamentary period with greatest overlap on TV data set:Balkenende IVIdeology: goverment - opposition, not left - right (Hirst et al., 2010) Hirst, G., Riabinin, Y., Graham, J., and Boizot-Roche, M. Text to Ideologyor Text to Party Status?
  • 10. Political groupsGovernment (CDA, PvdA and ChristenUnie)Left wing opposition (GroenLinks, SP)Right wing opposition (PVV, VVD) Hirst, G., Riabinin, Y., Graham, J., and Boizot-Roche, M. Text to Ideologyor Text to Party Status?
  • 11. Parsimonious languagemodels λ(t|D) et = tf (t, D) · (1 − λ)P (t|C) + λP (t|D) et P (t|D) = t et Hiemstra, D., Robertson, S., and Zaragoza, H. (2004). Parsimonious lan-guage models for information retrieval. In Proceedings of the 27th Annual Inter-national ACM SIGIR Conference on Research and development in InformationRetrieval, SIGIR ’04, pages 178–185, New York, NY, USA. ACM.
  • 12. Parsimonious languagemodelsProbability distribution from word frequencies perdocumentCompare distribution with collection of documentsChoose terms that are substantially more frequent thanexpected Hiemstra, D., Robertson, S., and Zaragoza, H. (2004). Parsimonious lan-guage models for information retrieval. In Proceedings of the 27th Annual Inter-national ACM SIGIR Conference on Research and development in InformationRetrieval, SIGIR ’04, pages 178–185, New York, NY, USA. ACM.
  • 13. Parsimonious languagemodelsFilter out corpus speci c stopwords (‘voorzitter’)Remove noise Hiemstra, D., Robertson, S., and Zaragoza, H. (2004). Parsimonious lan-guage models for information retrieval. In Proceedings of the 27th Annual Inter-national ACM SIGIR Conference on Research and development in InformationRetrieval, SIGIR ’04, pages 178–185, New York, NY, USA. ACM.
  • 14. Parsimonious languagemodels
  • 15. Parsimonious languagemodels
  • 16. Parsimonious languagemodels
  • 17. ComparisonTwo methods: estimated probability and Kullback-Leiblerdivergence‘For each political group, estimate the probability that anarbitrary word in a tv-programme is one of theircharacteristic words’‘Calculate the risk of returning a document to the query’ tft,T V P (t|Mq ) ˆ P (q|T V ) = KL(Md Mq ) = P (t|Mq ) · log t∈q |T V | P (t|Md ) tV
  • 18. ResultsRight never winsCasual evaluation does not imply ‘strange’ right wing wordsGovernment and left results are closeComparison with regular Dutch does imply a littlepreference for left wing words
  • 19. ConclusionsLanguage in Dutch public broadcasting is notparticularly left (only a slight preference was found)Descriptive right wing words used lessMight be PVV-in uence; further investigation is needed
  • 20. Questions?

Related Documents