Auditing Search Query Suggestion Bias Through Recursive Algorithm Interrogation

2022-06-26

Web Science Conference

AI Summary

This study addresses the challenge of identifying bias in search query suggestions, which is hindered by sparse contextual information and the limited number of suggestions provided per query round, resulting in an insufficient data foundation for robust analysis. To overcome these limitations, the authors propose a recursive algorithmic interrogation method that systematically constructs a query suggestion tree to uncover secondary and deeper-level suggestions, thereby moving beyond the conventional reliance on only top-tier recommendations. This approach substantially expands the dataset of suggestions associated with political figures and enables, for the first time, a thorough investigation into latent thematic group biases. Consequently, the method significantly enhances both the comprehensiveness and accuracy of bias detection in search suggestion systems.

Technology Category

• Search and Optimization: Algorithm Configuration
• Data Mining & Knowledge Management: Intelligent Query Processing
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs

Abstract

Despite their important role in online information search, search query suggestions have not been researched as much as most other aspects of search engines. Although reasons for this are multi-faceted, the sparseness of context and the limited data basis of up to ten suggestions per search query pose the most significant problem in identifying bias in search query suggestions. The most proven method to reduce sparseness and improve the validity of bias identification of search query suggestions so far is to consider suggestions from subsequent searches over time for the same query. This work presents a new, alternative approach to search query bias identification that includes less high-level suggestions to deepen the data basis of bias analyses. We employ recursive algorithm interrogation techniques and create suggestion trees that enable access to more subliminal search query suggestions. Based on these suggestions, we investigate topical group bias in person-related searches in the political domain.

Problem

• search query suggestions
• bias identification
• data sparsity
• algorithmic bias
• recursive interrogation

Innovation

• recursive algorithm interrogation
• search query suggestions
• bias auditing
• suggestion trees
• topical group bias