Improving Aggregated Search Coherence

Aggregated search is that task of blending results from different search services, or verticals, into the core web results. Aggregated search coherence is the extent to which results from different sources focus on similar senses of an ambiguous or underspecified query. Prior research studied the effect of aggregated search coherence on search behavior and found that the query-senses in the vertical results can affect user interaction with the web results. In this work, we develop and evaluate algorithms for vertical results selection—deciding which results from a particular vertical to display. Results from a large-scale user study suggest that algorithms that improve the level of coherence between the vertical and web results influence users to make more productive decisions with respect to the web results—to engage with the web results when at least one of them is relevant and, to a lesser extent, to avoid engaging with the web results otherwise.