Abstract

Native advertising is a type of commercial hybrid content that has successfully targeted online consumers. Native ads have become popular, especially on online platforms. People often don't realize that they are reading sponsored and paid content making native advertising very effective. Despite these benefits, native advertising has provoked strong negative responses, often accompanied by criticism and avoidance of the ads. This study aims to investigate the performance of different word embedding methods (BERT, GloVe, FastText) when used in combination with different deep learning methods (BiLSTM, CNN, LSTM) in detecting native ads in electronic news. The dataset used in this study was collected from the news portal, detik.com. Among these models, the BERT-BiLSTM model achieved the highest accuracy, f1 score, recall, precision and AUC score, all with the same value of 95%, compared to the other models, showing that the BERT-BiLSTM model outperformed the other models.

Original languageEnglish
Title of host publicationProceedings - 11th Electrical Power, Electronics, Communications, Control, and Informatics Seminar, EECCIS 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages304-309
Number of pages6
ISBN (Electronic)9781665406482
DOIs
Publication statusPublished - 2022
Event11th Electrical Power, Electronics, Communications, Control, and Informatics Seminar, EECCIS 2022 - Malang, Indonesia
Duration: 23 Aug 202225 Aug 2022

Publication series

NameProceedings - 11th Electrical Power, Electronics, Communications, Control, and Informatics Seminar, EECCIS 2022

Conference

Conference11th Electrical Power, Electronics, Communications, Control, and Informatics Seminar, EECCIS 2022
Country/TerritoryIndonesia
CityMalang
Period23/08/2225/08/22

Keywords

  • Comparative Study
  • Deep Learning
  • Electronic News
  • Native Ads
  • Word Embedding

Fingerprint

Dive into the research topics of 'Deep Learning for Native Advertisement Detection in Electronic News: A Comparative Study'. Together they form a unique fingerprint.

Cite this