Perils of Uncertainty? The Impact of Contextual Ambiguity on Search Advertising Keyword Performance

In this paper, we explore how the contextual ambiguity of a search can affect a keyword's performance. We propose an automatic way of categorizing keywords and examining keyword contextual ambiguity based on topic models from machine learning and computational linguistics. We quantify the effect of contextual ambiguity on keyword click-through performance using a hierarchical Bayesian model, and validate our study using a novel dataset from a major search engine containing information on click activities for 12,790 keywords across multiple categories from over 4.6 million impressions. We find that consumer click behaviors vary significantly across keywords, and keyword category and contextual ambiguity significantly affect such variation. Specifically, higher contextual ambiguity can lead to higher click-through rate (CTR) on top-positioned ads, but the CTR tends to decay faster with position. Our study has the potential to help advertisers design keyword portfolios, and help search engines improve the quality of sponsored ads.