Problem
Research questions and friction points this paper is trying to address.
Confirmation Bias
Academic Search Engines
Information Objectivity
Examining bias perpetuation in academic search engines: an algorithm audit of Google and Semantic Scholar
🤖 AI Summary
This study identifies systematic result bias in academic search engines—Google Scholar and Semantic Scholar—when responding to confirmation-biased queries (e.g., emphasizing “benefits” or “risks”), particularly on technological topics, thereby compromising objective information access. We constructed a structured query set capturing confirmation bias, manually annotated result stance and diversity, and conducted cross-engine statistical analysis of result distribution alongside effect-size estimation to comparatively characterize bias propagation mechanisms for the first time. Results show Semantic Scholar exhibits significantly lower overall bias than Google Scholar (37% lower on average); technical topics elicit stronger bias than health-related ones; and issue polarization does not consistently correlate with bias magnitude—challenging prevailing assumptions. Our work introduces a novel methodology and empirical benchmark for evaluating fairness and epistemic neutrality in academic search systems.
📝 Abstract
Researchers rely on academic Web search engines to find scientific sources, but search engine mechanisms may selectively present content that aligns with biases embedded in queries. This study examines whether confirmation biased queries prompted into Google Scholar and Semantic Scholar will yield results aligned with a query’s bias. Six queries (topics across health and technology domains such as ‘vaccines’, ‘Internet use’) were analyzed for disparities in search results. We confirm that biased queries (targeting ‘benefits’ or ‘risks’) affect search results in line with bias, with technology-related queries displaying more significant disparities. Overall, Semantic Scholar exhibited fewer disparities than Google Scholar. Topics rated as more polarizing did not consistently show more disparate results. Academic search results that perpetuate confirmation bias have strong implications for both researchers and citizens searching for evidence. More research is needed to explore how scientific inquiry and academic search engines interact.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Academic Search Engines
Confirmation Bias
Semantic Scholar Optimization
🔎 Similar Papers
No similar papers found.
