Generating ad creatives using deep learning for search advertising
Generating ad creatives using deep learning for search advertising
thumbnail.default.placeholder
Tarih
2022-01-01
Yazarlar
Cogalmis, Kevser Nur
Bulut, Ahmet
Süreli Yayın başlığı
Süreli Yayın ISSN
Cilt Başlığı
Yayınevi
Scientific and Technological Research Council Turkey
Dergi Adı
TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES
Özet
We generated advertisement creatives programmatically using deep neural networks. A landing page contains relevant text data, which can be used for generating advertisement creatives, i.e. ads. We treated the ad generation task as a text summarization problem and built a sequence to sequence model. In order to assess the validity of our approach, we conducted experiments on four datasets. Our empirical results showed that our model generated relevant ads on a template-based dataset with moderate hyperparameters. Training the model with more content increased the performance of the model, which we attributed to rigorous hyperparameter tune-up. The choice of word embedding used in the representation of the input altered the model's performance. When the source and the target shared common sequences during training, the model produced the best results.
Açıklama
Anahtar kelimeler
Online advertising, ad creative generation, deep learning