IAB Tech Lab’s Seller-Defined Audiences (SDA) is a privacy-compliant audience classification. However, to benefit from SDA, publishers should have a contextual classification that accurately defines their content and audiences. This is easier said than done because the IAB standard involves two taxonomies, one for content, and another for the audience.
The presence of two taxonomies means a publisher's writers and editors have to assign specific category tags to articles manually. This process is time-consuming and error-prone. It runs counter to the publisher’s need to define interest-based segments to match against SDA’s taxonomy quickly and easily for improved audience insights and monetization.
Machine-learning-based classifiers could help in overcoming the challenges involved in developing contextual classification. The classifiers automate the process by analyzing the content on a webpage to identify the subject matter and its sentiment. Besides, these systems constantly digest and process information and continuously learn and adjust their outputs accordingly.
This real-time optimization eliminates human error, and produces accurate page categorizations for improved audience definitions, and contextual targeting in line with the IAB Tech Lab’s content taxonomy. Significantly, machine-learning-based classifiers take the tedium out of the categorization and tagging process.
Click here to read the original article published by AdExchanger.
Please give your feedback on this article or share a similar story for publishing by clicking here.
