Cover Image

Computational advertising techniques for targeting relevant ads

Computational Advertising, popularly known as online advertising or Web advertising, refers to finding the most relevant ads matching a particular context on the Web. The context depends on the type of advertising and could mean - content where the ad is shown, the user who is viewing the ad or the...

Full description

Saved in:
Bibliographic Details
Main Authors: Dave, Kushal (Author), Varma, Vasudeva (Author)
Format: Electronic Book
Language:English
Published: Hanover, Massachusetts Now Publishers 2014.
Series:Foundations and trends in information retrieval volume 8, issue 4-5
Subjects:
Internet advertising
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • 1. Introduction
  • 1.1 Introduction to computational advertising
  • 1.2 Issues and challenges
  • 1.3 Scope of the survey
  • 1.4 Organization of the survey 2. Finding advertising keywords on web pages
  • 2.1 Keyword extraction as a classification task
  • 2.2 Pattern based keyword extraction
  • 2.3 Using external resources
  • 2.4 Multi-label learning with millions of labels
  • 2.5 Summary 3. Dealing with short text in ads for contextual advertising
  • 3.1 Expanding vocabulary to overcome vocabulary mismatch
  • 3.2 Leveraging taxonomy
  • 3.3 Combining semantics with the syntax
  • 3.4 Topic modeling
  • 3.5 Matching concepts
  • 3.6 Machine learning approach to ad retrieval
  • 3.7 Time-constrained retrieval of ads for web pages
  • 3.8 Dealing with the sentiments in the content
  • 3.9 Summary 4. Handling the short search query for sponsored search
  • 4.1 Query substitution and rewriting
  • 4.2 Leveraging ad-click data for ad retrieval
  • 4.3 Summary 5. Ad quality and spam
  • 5.1 Determining ad quality based on relevance
  • 5.2 Exploiting structural features to find adversarial ads
  • 5.3 Identify when to (not) show ads
  • 5.4 Predicting bounce rate of an ad
  • 5.5 Identifying click spam
  • 5.6 Summary 6. Ranking retrieved ads for sponsored search
  • 6.1 Modeling presentation and position bias
  • 6.2 Predicting the click-through rates of ads
  • 6.3 Ranking ads by machine learning ranking (MLR)
  • 6.4 Impression forecasting
  • 6.5 Summary 7. Ranking ads in contextual advertising
  • 7.1 Learning to rank techniques for ranking ads
  • 7.2 Using hierarchies to impute CTR
  • 7.3 Combining collaborative filtering with feature based models
  • 7.4 Click prediction in display advertising
  • 7.5 Ads ranking
  • going ahead 8. How much can behavioral targeting help online advertising?
  • 8.1 Analyzing user behavior
  • 8.2 Profile based user targeting
  • 8.3 Personalized click prediction
  • 8.4 Moving over to display advertising 9. Display advertising and real time bidding
  • 9.1 RTB ecosystem
  • 9.2 How real time bidding happens?
  • 9.3 Benefits of RTB
  • 9.4 Contrasting display advertising and contextual advertising
  • 9.5 Summary 10. Emerging topics in computational advertising
  • 10.1 Blurred line between DA, ConAd, SS
  • 10.2 Advertising in a stream/newsfeed
  • 10.3 Social targeting
  • 10.4 Advertising on handheld devices
  • 10.5 Interactive and incentive based advertising 11. Resources
  • 11.1 Datasets
  • 11.2 Relevant conferences and journals
  • 11.3 Academic courses in computational advertising 12. Summary and concluding remarks
  • 12.1 Is ad retrieval/ranking a solved problem?
  • 12.2 Research topics
  • 12.3 Conclusion

Similar Items