Enhancing Personalized Ads Using Interest Category Classification of SNS Users Based on Deep Neural Networks - PubMed Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2020 Dec 30;21(1):199.
doi: 10.3390/s21010199.

Enhancing Personalized Ads Using Interest Category Classification of SNS Users Based on Deep Neural Networks

Taekeun Hong  1 , Jin-A Choi  2 , Kiho Lim  2 , Pankoo Kim  1
Affiliations

Enhancing Personalized Ads Using Interest Category Classification of SNS Users Based on Deep Neural Networks

Taekeun Hong et al. Sensors (Basel). .

Abstract

The classification and recommendation system for identifying social networking site (SNS) users' interests plays a critical role in various industries, particularly advertising. Personalized advertisements help brands stand out from the clutter of online advertisements while enhancing relevance to consumers to generate favorable responses. Although most user interest classification studies have focused on textual data, the combined analysis of images and texts on user-generated posts can more precisely predict a consumer's interests. Therefore, this research classifies SNS users' interests by utilizing both texts and images. Consumers' interests were defined using the Curlie directory, and various convolutional neural network (CNN)-based models and recurrent neural network (RNN)-based models were tested for our user interest classification system. In our hybrid neural network (NN) model, CNN-based classification models were used to classify images from users' SNS postings while RNN-based classification models were used to classify textual data. The results of our extensive experiments show that the classification of users' interests performed best when using texts and images together, at 96.55%, versus texts only, 41.38%, or images only, 93.1%. Our proposed system provides insights into personalized SNS advertising research and informs marketers on making (1) interest-based recommendations, (2) ranked-order recommendations, and (3) real-time recommendations.

Keywords: SNS; deep learning; interest classification; neural networks; personalized ads.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 3
Figure 3
(a) Inception v3 model; (b) ResNet v2 model.
Figure 1
Figure 1
Architecture of category classification system for personalized ads.
Figure 2
Figure 2
(a) Inception res v3 model; (b) MobileNet v2 model.
Figure 4
Figure 4
EfficientNet b7 model.
Figure 5
Figure 5
(a) Vanilla recurrent neural network (RNN) model; (b) long short-term memory (LSTM) model.
Figure 6
Figure 6
(a) Gated recurrent unit (GRU) model; (b) bidirectional LSTM model.
Figure 7
Figure 7
Accuracy comparison of the CNN-based models.
Figure 8
Figure 8
Loss comparison of the CNN-based models.
Figure 9
Figure 9
Accuracy comparison of the RNN-based models.
Figure 10
Figure 10
Loss comparison of the RNN-based models.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Voorveld H. Brand communication in social media: A research agenda. J. Advert. 2019;48:14–26. doi: 10.1080/00913367.2019.1588808. - DOI
    1. Ashley C., Tracy T. Creative Strategies in Social Media Marketing: An Exploratory Study of Branded Social Content and Consumer Engagement. Psychol. Mark. 2015;32:15–27. doi: 10.1002/mar.20761. - DOI
    1. Gritten A. Forum-Media Proliferation and Demands for New Forms of Research. Int. J. Mark. Res. 2007;49:15–23. doi: 10.1177/147078530704900105. - DOI
    1. Kelly L., Kerr G., Drennan J. Avoidance of advertising in social networking sites: The teenage perspective. J. Interact. Advert. 2010;10:16–27. doi: 10.1080/15252019.2010.10722167. - DOI
    1. De Keyzer F., Dens N., De Pelsmacker P. Is this for me? How consumers respond to personalized advertising on social network sites. J. Interact. Advert. 2015;15:124–134. doi: 10.1080/15252019.2015.1082450. - DOI

LinkOut - more resources