Finding keyword from online broadcasting content for targeted advertising

  • Authors:
  • Hua Li;Duo Zhang;Jian Hu;Hua-Jun Zeng;Zheng Chen

  • Affiliations:
  • Microsoft Research Asia;Tsinghua University;Microsoft Research Asia;Microsoft Research Asia;Microsoft Research Asia

  • Venue:
  • Proceedings of the 1st international workshop on Data mining and audience intelligence for advertising
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

Content targeted advertising has been a successful way of delivering ads, as effective technologies were developed to find keywords from the webpage a user is browsing. However, existing technologies cannot be easily applied to find keywords from online broadcasting content, which usually contain more specific phrases and wordings in certain communities than in general webpage content. In this paper, motivated by some existing research works on information extraction field, we suggest a sequential pattern mining-based method to discover language patterns from online broadcasting content. With selected keyword seeds, iteratively applying the language pattern mining and keyword extraction, the proposed technique avoids any tedious labeling work for this task. Our experiments on real-world data show that the proposed keyword extraction algorithm significantly outperforms the baseline method.