Do Specific Text Features Influence Click Probabilities in Paid Search Advertising?
Research output: Contributions to collected editions/works › Published abstract in conference proceedings › Research › peer-review
Authors
Paid Search Advertisers have only very few options to influence the user's decision to click on one of their ads. The textual content of the creatives seems to be one important influencing factor beneath its position on the Search Engine Results Page (SERP) and the perceived relevance of the given ad to the present search query. In this study we perform a non reactive multivariate test that enables us to evaluate the influence of specific textual signals in Paid Search creatives. A Bayesian Analysis of Variance (BANOVA) is applied to evaluate the influence of various text features on click probabilities. We conclude by finally showing that differences in the formulation of the textual content can have influence on the click probability of Paid Search ads
| Original language | English |
|---|---|
| Title of host publication | ICE-B 2014 - Proceedings of the 11th International Conference on e-Business, Part of ICETE 2014 - 11th International Joint Conference on e-Business and Telecommunications |
| Editors | Andreas Holzinger, Marten van Sinderen, Peter Dolog, Mohammad S. Obaidat |
| Number of pages | 8 |
| Publisher | Science and Technology Publications, Lda (SciTePress) |
| Publication date | 01.01.2014 |
| Pages | 55-62 |
| ISBN (print) | 9789897580437 |
| ISBN (electronic) | 9789897580437 |
| DOIs | |
| Publication status | Published - 01.01.2014 |
| Event | 11th International Conference on e-Business - ICE-B 2014 - Wien, Austria Duration: 28.08.2014 → 30.08.2014 Conference number: 11 http://www.ice-b.icete.org/?y=2014 |
Bibliographical note
Publisher Copyright:
© 2014 SCITEPRESS - Science and Technology Publications.
- Business informatics - Bayesian analysis of variance, Bayesian statistics, Multivariate testing, Paid search advertising, Search engine advertising, Sponsored search