A Comprehensive Ensemble Deep Learning Method for Identifying Native Advertising in News Articles

Brian Rizqi Paradisiaca Darnoto, Daniel Siahaan*, Diana Purwitasari

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Native ads are a popular form of online advertisement that has a similar style and function to that of the original content of the platform they are displayed on. There are several problems in the sponsorship disclosure of native ads, namely their positioning, eminence, and lucidity of meaning, causing readers to not recognize them as advertisement. Unlike the selling message of traditional ads that are explicit, the selling message of native ads are implicit. This study aims to carry out the detection of native ads using deep ensemble-based models. The ensemble learning approach is adopted by combining two deep learning models using dense layers. Furthermore, to overcome the overfitting problem, an attention mechanism using a dense layer is implemented within the model. The experimental results show that the BiLSTM-CNN model with attention mechanism and parameter tuning was able to overcome the overfitting problem and achieve the highest accuracy of 95% for the detection of native ads.

Original languageEnglish
Title of host publication8th International Conference on Software Engineering and Computer Systems, ICSECS 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages164-169
Number of pages6
ISBN (Electronic)9798350310931
DOIs
Publication statusPublished - 2023
Event8th IEEE International Conference on Software Engineering and Computer Systems, ICSECS 2023 - Penang, Malaysia
Duration: 25 Aug 202327 Aug 2023

Publication series

Name8th International Conference on Software Engineering and Computer Systems, ICSECS 2023

Conference

Conference8th IEEE International Conference on Software Engineering and Computer Systems, ICSECS 2023
Country/TerritoryMalaysia
CityPenang
Period25/08/2327/08/23

Keywords

  • BiLSTM
  • CNN
  • Ensemble Learning
  • LSTM
  • Native Ads

Fingerprint

Dive into the research topics of 'A Comprehensive Ensemble Deep Learning Method for Identifying Native Advertising in News Articles'. Together they form a unique fingerprint.

Cite this