Understanding User Preference -- Comparison between Linear and Directional Top-K Query results
Xiaolei Jiang
TL;DR
This work examines how users prefer Linear Top-$k$ and Directional Top-$k$ queries in multidimensional rankings, using two real-world topics—used cars and football players—to elicit preferences via scatter-plot visualizations. The methodology combines a structured questionnaire with two-attribute, equally weighted datasets and rigorous statistical tests (binomial, McNemar, logistic regression, chi-square) to test three hypotheses about differences in preferences, topic effects, and knowledge-driven differences. Key findings show a strong directional preference in the lifestyle-like used-cars topic, while football-related preferences are more balanced and influenced by knowledge level; this demonstrates substantial cross-topic differences in user preferences and the contextual nature of ranking judgments. The results have practical implications for designing user-centric ranking systems, suggesting that directional queries can better capture balanced trade-offs in everyday decision contexts, while domain expertise can steer preferences in specialized domains.
Abstract
This paper investigates user preferences for Linear Top-k Queries and Directional Top-k Queries, two methods for ranking results in multidimensional datasets. While Linear Queries prioritize weighted sums of attributes, Directional Queries aim to deliver more balanced results by incorporating the spatial relationship between data points and a user-defined preference line. The study explores how preferences for these methods vary across different contexts by focusing on two real-world topics: used cars (e-commerce domain) and football players (personal interest domain). A user survey involving 106 participants was conducted to evaluate preferences, with results visualized as scatter plots for comparison. The findings reveal a significant preference for directional queries in the used cars topic, where balanced results align better with user goals. In contrast, preferences in the football players topic were more evenly distributed, influenced by user expertise and familiarity with the domain. Additionally, the study demonstrates that the two specific topics selected for this research exhibit significant differences in their impact on user preferences. This research reveals authentic user preferences, highlighting the practical utility of Directional Queries for lifestyle-related applications and the subjective nature of preferences in specialized domains. These insights contribute to advancing personalized database technologies, guiding the development of more user-centric ranking systems.