Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

An investigation of biases in web search engine query suggestions

An investigation of biases in web search engine query suggestions Survey-based studies suggest that search engines are trusted more than social media or even traditional news, although cases of false information or defamation are known. The purpose of this paper is to analyze query suggestion features of three search engines to see if these features introduce some bias into the query and search process that might compromise this trust. The authors test the approach on person-related search suggestions by querying the names of politicians from the German Bundestag before the German federal election of 2017.Design/methodology/approachThis study introduces a framework to systematically examine and automatically analyze the varieties in different query suggestions for person names offered by major search engines. To test the framework, the authors collected data from the Google, Bing and DuckDuckGo query suggestion APIs over a period of four months for 629 different names of German politicians. The suggestions were clustered and statistically analyzed with regards to different biases, like gender, party or age and with regards to the stability of the suggestions over time.FindingsBy using the framework, the authors located three semantic clusters within the data set: suggestions related to politics and economics, location information and personal and other miscellaneous topics. Among other effects, the results of the analysis show a small bias in the form that male politicians receive slightly fewer suggestions on “personal and misc” topics. The stability analysis of the suggested terms over time shows that some suggestions are prevalent most of the time, while other suggestions fluctuate more often.Originality/valueThis study proposes a novel framework to automatically identify biases in web search engine query suggestions for person-related searches. Applying this framework on a set of person-related query suggestions shows first insights into the influence search engines can have on the query process of users that seek out information on politicians. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Online Information Review Emerald Publishing

An investigation of biases in web search engine query suggestions

Download PDF
17 pages

Loading next page...
 
/lp/emerald-publishing/an-investigation-of-biases-in-web-search-engine-query-suggestions-gBAjcam4Vg
Publisher
Emerald Publishing
Copyright
© Emerald Publishing Limited
ISSN
1468-4527
DOI
10.1108/oir-11-2018-0341
Publisher site
See Article on Publisher Site

Abstract

Survey-based studies suggest that search engines are trusted more than social media or even traditional news, although cases of false information or defamation are known. The purpose of this paper is to analyze query suggestion features of three search engines to see if these features introduce some bias into the query and search process that might compromise this trust. The authors test the approach on person-related search suggestions by querying the names of politicians from the German Bundestag before the German federal election of 2017.Design/methodology/approachThis study introduces a framework to systematically examine and automatically analyze the varieties in different query suggestions for person names offered by major search engines. To test the framework, the authors collected data from the Google, Bing and DuckDuckGo query suggestion APIs over a period of four months for 629 different names of German politicians. The suggestions were clustered and statistically analyzed with regards to different biases, like gender, party or age and with regards to the stability of the suggestions over time.FindingsBy using the framework, the authors located three semantic clusters within the data set: suggestions related to politics and economics, location information and personal and other miscellaneous topics. Among other effects, the results of the analysis show a small bias in the form that male politicians receive slightly fewer suggestions on “personal and misc” topics. The stability analysis of the suggested terms over time shows that some suggestions are prevalent most of the time, while other suggestions fluctuate more often.Originality/valueThis study proposes a novel framework to automatically identify biases in web search engine query suggestions for person-related searches. Applying this framework on a set of person-related query suggestions shows first insights into the influence search engines can have on the query process of users that seek out information on politicians.

Journal

Online Information Review – Emerald Publishing

Published: Jun 9, 2020

Keywords: Text mining; Politics; Bias; Regression analysis; Query suggestions; Web search engines

References

  • The impact of search engine selection and sorting criteria on vaccination beliefs and attitudes: two experiments manipulating Google output
    Allam, A.; Schulz, P.J.; Nakamoto, K.
  • Bias on the web
    Baeza-Yates, R.
  • Ask for information retrieval: Part I. Background and theory
    Belkin, N.; Oddy, R.; Brooks, H.
  • Enriching word vectors with subword information
    Bojanowski, P.; Grave, E.; Joulin, A.; Mikolov, T.
  • A survey of query auto completion in information retrieval
    Cai, F.; de Rijke, M.
  • Term suggestion with similarity measure based on semantic analysis techniques in query logs
    Chen, L.
  • Beta regression in r
    Cribari-Neto, F.; Zeileis, A.
  • The search engine manipulation effect (seme) and its possible impact on the outcomes of elections
    Epstein, R.; Robertson, R.E.
  • Suppressing the search engine manipulation effect (SEME)
    Epstein, R.; Robertson, R.E.; Lazer, D.; Wilson, C.
  • Topical interests and the mitigation of search engine bias
    Fortunato, S.; Flammini, A.; Menczer, F.; Vespignani, A.
  • Bias in computer systems
    Friedman, B.; Nissenbaum, H.
  • Lemmatisation as a tagging task
    Gesmundo, A.; Samardžić, T.
  • 2017 Edelman Trust Barometer – global results
    Harary, A.; Bersoff, D.M.; Adkins, S.; Bruening, J.; Lvovich, S.; Bonifaz, G.; Heume, K.
  • Query autocompletions considered harmful
    Hiemstra, D.
  • Shaping the web: why the politics of search engines matters
    Introna, L.D.; Nissenbaum, H.
  • An efficient k-means clustering algorithm: analysis and implementation
    Kanungo, T.; Mount, D.M.; Netanyahu, N.S.; Piatko, C.D.; Silverman, R.; Wu, A.Y.; Member, S.; Member, S.
  • When do people use query suggestion? A query suggestion log analysis
    Kato, M.P.; Sakai, T.; Tanaka, K.
  • A comparison of query and term suggestion features for interactive searching
    Kelly, D.; Gyllstrom, K.; Bailey, E.W.
  • Search bias quantification: investigating political bias in social media and web search
    Kulshrestha, J.; Eslami, M.; Messias, J.; Zafar, M.B.; Ghosh, S.; Gummadi, K.P.; Karahalios, K.
  • The political impact of the internet on US Presidential Elections
    Larcinese, V.; Miner, L.
  • Living in a world of biased search engines
    Lewandowski, D.
  • 10 facts about the changing digital news landscape
    Matsa, K.E.; Lu, K.
  • Efficient estimation of word representations in vector space
    Mikolov, T.; Chen, K.; Corrado, G.; Dean, J.
  • Assessing bias in search engines
    Mowshowitz, A.; Kawaguchi, A.
  • Measuring search engine bias
    Mowshowitz, A.; Kawaguchi, A.
  • GermanWordEmbeddings
    Mueller, A.
  • Dynamic query suggestion
    Mysen, C.C.; Schwartz, S.E.
  • Investigating user perception of gender bias in image search: the role of sexism
    Otterbacher, J.; Checco, A.; Demartini, G.; Clough, P.
  • Click and elect: how fake news helped Donald Trump win a real election j Hannah Jane Parkinson
    Parkinson, H.J.
  • A picture of search
    Pass, G.; Chowdhury, A.; Torgeson, C.
  • X-means: extending k-means with efficient estimation of the number of clusters
    Pelleg, D.; Moore, A.
  • On measuring bias in online information
    Pitoura, E.; Tsaparas, P.; Flouris, G.; Fundulaki, I.; Papadakos, P.; Abiteboul, S.; Weikum, G.
  • Software framework for topic modelling with large corpora
    Řehůřek, R.; Sojka, P.
  • Auditing partisan audience bias within Google search
    Robertson, R.E.; Jiang, S.; Joseph, K.; Friedland, L.; Lazer, D.; Wilson, C.
  • Silhouettes: a graphical aid to the interpretation and validation of cluster analysis
    Rousseeuw, P.
  • Query autocompletions for German politicians of the 18th Bundestag
    Samokhina, A.; Bonart, M.; Schaer, P.; Heisenberg, G.
  • Auditing algorithms: research methods for detecting discrimination on internet platforms
    Sandvig, C.; Hamilton, K.; Karahalios, K.; Langbort, C.
  • The reason for the Obama victory: it’s the internet, stupid
    Schiffmann, B.
  • Adding manual constraints and lexical lookup to a brill-tagger for german
    Schneider, G.; Volk, M.
  • How google autocomplete works in search
    Sullivan, D.
  • Search engine coverage bias: evidence and possible causes
    Vaughan, L.; Thelwall, M.
  • A similarity measure for indefinite rankings
    Webber, W.; Moffat, A.; Zobel, J.
  • Algorithmic bias: do good systems make relevant documents more retrievable?
    Wilkie, C.; Azzopardi, L.
  • Estimating embedding vectors for queries
    Zamani, H.; Croft, W.B.
  • Watching the watchers: epstein and Robertson’s search engine manipulation effect
    Zweig, K.