An algorithm for suffix stripping
Readings in information retrieval
Foundations of statistical natural language processing
Foundations of statistical natural language processing
A vector space model for automatic indexing
Communications of the ACM
Impedance coupling in content-targeted advertising
Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval
A semantic approach to contextual advertising
SIGIR '07 Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval
A noisy-channel approach to contextual advertising
Proceedings of the 1st international workshop on Data mining and audience intelligence for advertising
| Hi-index | 0.00 |
Contextual advertising is an important part of the Web economy today. Profit is linked to the interest that users find in the ads presented to them. The problem is for contextual advertising platforms to select the most relevant ads. Simple keyword matching techniques for matching ads to page content give poor accuracy. Problems such as homonymy, polysemy, limited intersection between content and selection keywords as well as context mismatch can significantly degrade the precision of ads selection. In this paper, we propose a method for improving the relevance of contextual ads based on "Wikipedia matching". It is a technique that uses Wikipedia articles as "reference points" for ads selection. In our research, we worked on English language, but it is possible to port the algorithm to other languages.