Auditing Algorithmic Content Curation on Search Engines Using Virtual Agents

Makhortykh, Mykola; Urman, Aleksandra; Ulloa, Roberto (27 May 2021). Auditing Algorithmic Content Curation on Search Engines Using Virtual Agents (Unpublished). In: 71st Annual ICA conference - "Engaging the Essential Work of Care: Communication, Connectedness, and Social Justice". Virtual. 27.05-31.05.2021.

Full text not available from this repository.

The use of virtual agents (i.e., software programmes emulating browsing behaviour) offers new possibilities for conducting auditing of systems for algorithmic content curation (e.g., web search engines). In our paper, we build on earlier approaches for algorithmic auditing to refine methodology for large-scale virtual agent-based auditing in the controlled environment. We then use this methodology to conduct a comparative study of algorithmic content curation on six search engines (e.g., Baidu, Google, and Yandex). Using a large set of queries in English, Russian, and Chinese that deal with three categories of topics - i.e., recent events, historical events, and abstract concepts - we investigate both cross- and intra-engine variations in information source ranking.

Item Type:

Conference or Workshop Item (Paper)

Division/Institute:

03 Faculty of Business, Economics and Social Sciences > Social Sciences > Institute of Communication and Media Studies (ICMB)

UniBE Contributor:

Makhortykh, Mykola, Urman, Aleksandra

Subjects:

000 Computer science, knowledge & systems
300 Social sciences, sociology & anthropology

Language:

English

Submitter:

Mykola Makhortykh

Date Deposited:

21 Jun 2021 15:20

Last Modified:

05 Dec 2022 15:51

Uncontrolled Keywords:

algorithmic audit, search engine, virtual agent, algorithms, information retrieval, experiment

URI:

https://boris.unibe.ch/id/eprint/156710

Actions (login required)

Edit item Edit item
Provide Feedback