• Advanced Contextual

Transparent Control & Safety Matter


Our mission at Advanced Contextual is simple. We believe individual privacy is important and doesn’t have to compromise good business. We provide publishers and brands with tools to better understand their audiences through content consumption and dynamic intent data. We do this in a way that preserves both scale and precision, not tied to any single identifier.

The two concepts of transparent control and safety have to be tied at the hip in advanced contextual technology, platforms and products. Never mind the greater industry debate around these topics. For advanced contextual to work, the publisher or brand has to be able to control with transparency to produce and target safe environments.

We think the most fundamental aspect of this is where the controls exist in the platform. First generation platforms tend to put controls at the “top of the stream”. For example, this means the engine makes decisions on what to block and it’s blocked system-wide from a few keywords.

Advanced contextual platforms have to provide these controls in a hierarchical fashion all the way down to the segment level. In some cases controls make sense to leverage at an aggregate level, but providing publishers and brands with segment-level controls that are easy to implement allows them to decide what should be included at the most granular level. This approach preserves relevant scale while allowing any blocking to be effective.

These controls need to be flexible. Brands and publishers need to exclude not only networks, sites, and keywords, but the ability to block topics and entities such as people, places and organizations. The controls need to work in concert with any targeting trigger that’s used to positively target.

Safety goes hand in hand with control. Advanced contextual platforms have to provide easy access to tools enabling brands and publishers to include/exclude networks, sites, keywords, topics and entities. Then, to augment the platform tools, advanced contextual systems must support the inclusion of external brand safety company tools. Providing home-grown tools that work with external brand-safety tools ensures a transparent level of control that results in safety.

We saw all of this come together last year when Covid became a dominant topic almost overnight. Over the course of a few days we saw our average impressions per second jump almost 150% and it was all virus-related. None of us in the industry knew what was going on, so we all worked to exclude Covid until we understood it. Most of the industry choked it off at the system level, but our platform excluded it at the segment level. We let our customers decide which segments would benefit from the increased scale of Covid, and which wouldn’t.


Since we did this at the segment level, “Covid” also wasn’t a monolithic term with one meaning. Advanced contextual systems must maintain a surrounding topical context in which to interpret individual keywords such as this. As we analyzed the Covid content, we were able to show our customers different insights that they could leverage if they chose to include it.

The combination of control and insights allowed our customers to determine what a safe Covid environment is and what it isn’t. It will be different to different publishers and brands. We think advanced contextual has to recognize this in both product and workflow.