Semantic targeting

Semantic targeting is a technique enabling the delivery of targeted advertising, a form of contextual advertising, for advertisements appearing on websites and is used by online publishers and advertisers to increase the effectiveness of their campaigns. The selection of advertisements are served by automated systems based on the content displayed to the user.

Origins

Semantic Targeting has originated from the developments arising from Semantic Web. The Semantic Web enables the representation of concepts expressed in human language to data in such a way that facilitates automatic processing, where software can programmatically understand and reason how different elements of data are related. The concept of semantic targeting utilises this capability to identify these concepts and the contexts in which they occur, enabling marketers to deliver highly targeted and specific ad campaigns to webpages.

The Evolution of Online Advertising

The targeting of advertising to specific micro segments is a fundamental requirement for an effective ad campaign. The two methods of targeting of recent times have been behavioral targeting and contextual targeting. It is now generally accepted that these forms have pitfalls for both advertiser and consumer.

Behavioral targeting aggregates data based upon a user's viewing of pages from a website. Generally this is facilitated by the placing of a cookie upon the user's PC. The cookie then reports the user's viewing behavior allowing for the identification of patterns of viewing behavior. However, great concern is expressed about the treatment of the user's right to privacy amongst consumer groups and legislators.

Contextual advertising scans the content of webpages, seeking to identify keywords, against which advertisers have bid to have their ad linked. If a match is made the ad is placed alongside the content, through an automated process. However, such systems are unable to identify the context of the entire page and therefore, a placement could be made against content that is inappropriate, derogatory or insensitive to the subject. They are also unable to identify the sense or meaning of words, leading to a misplacement of ads. For example, the word "orange" can be a color, a fruit, a telecommunications company, a mountain bike, and countless other variants.

How semantic targeting works

Semantic targeting aims to match the specific context of content on page within a website to an available advertising campaign. A key difference of semantic targeting to a contextual advertising system is that, instead of scanning a page for bidded keywords, a semantic system examines all the words and identifies the senses of those words. Because most words are polysemous, i.e. have more than one meaning, without having an understanding of the true context in which words occur, it is possible to incorrectly assign an advertisement where there is no contextual link. A semantic targeting system has to examine all the words before it can accurately identify the subject matter of the entire text and deliver an in context advertisement. For example, if the user is viewing a website relating to golf, where that website uses semantic targeting, the user may see advertisements for golf related topics, such as golf equipment, golf holidays etc. Advertisers can locate their ads in given categories using an Ontology (computer science) or taxonomy, ensuring that their ads will only appear in the context that they request.

Semantic targeting is also capable of identifying the sentiment of a webpage, through effective analysis of the language used on page. The systems would determine if the content was talking about a subject in a positive or negative light. If the page was being detrimental about a particular subject, the the semantic targeting system could deter the placement of a related ad alongside the story.

Other capabilities of a semantic targeting system include the availability of brand protection filtering. This can enable the blocking of an ad placed alongside content of a controversial nature. Such systems can deter placement against such subjects as as Adult/Erotica, Alcohol, Nudity, Offensive language, Bad News and other such topics. This would then avoid the potentially brand damaging occurrence of, for example, and airline advertising alongside a story about an air disaster.

Semantic targeting providers

Semantic targeting is an emerging technology in advertising automation. Several companies have launched semantic targeting technologies:

• ad pepper media (http://www.adpepper.com), based in Nurnberg, Germany, the market leader in semantic advertising with its isense semantic advertising solution (http://www.isense.net). Developed by linguist David Crystal, the system was the first semantic targeting technology, launched by Crystal Semantics in 2004. Subsequently acquired by adpepper in 2006.
• Clikkit (http://www.clikkit.com), based in San Francisco, has developed SemSense, a semantic targeting technology to link video to the context of webpages
• Collective Media - Personifi (http://www.collective.com) through its acquisition of Personifi, Collective provides an automated, multi-lingual semantic targeting platform with an interface that allows users to customize their own taxonomies.
• Peer39 (http://www.peer39.com) has developed an automated semantic targeting platform called SemanticMatch.
• 4AdNetworks (http://www.4adnetworks.com) offers ad networks a Semantic Targeting Solution based on a semantic technology that has been developed for 7 years by experienced linguists and IT specialists.