AI-Driven Contextual Advertising: A Technology Report and Implication Analysis
It addresses the shift from personal data-based to context-based advertising, offering insights for stakeholders but is incremental as it builds on existing research.
The paper examines how AI can enhance contextual advertising by improving semantic understanding of media context and optimizing ad placement, while also analyzing potential risks like unfair ad delivery and manipulation.
Programmatic advertising consists in automated auctioning of digital ad space. Every time a user requests a web page, placeholders on the page are populated with ads from the highest-bidding advertisers. The bids are typically based on information about the user, and to an increasing extent, on information about the surrounding media context. The growing interest in contextual advertising is in part a counterreaction to the current dependency on personal data, which is problematic from legal and ethical standpoints. The transition is further accelerated by developments in Artificial Intelligence (AI), which allow for a deeper semantic understanding of context and, by extension, more effective ad placement. In this article, we begin by identifying context factors that have been shown in previous research to positively influence how ads are received. We then continue to discuss applications of AI in contextual advertising, where it adds value by, e.g., extracting high-level information about media context and optimising bidding strategies. However, left unchecked, these new practices can lead to unfair ad delivery and manipulative use of context. We summarize these and other concerns for consumers, publishers and advertisers in an implication analysis.