A deep learning approach to identify unhealthy advertisements in street view images



Palmer, Gregory, Green, Mark ORCID: 0000-0002-0942-6628, Boyland, Emma ORCID: 0000-0001-8384-4994, Vasconcelos, Yales Stefano Rios, Savani, Rahul ORCID: 0000-0003-1262-7831 and Singleton, Alex
(2021) A deep learning approach to identify unhealthy advertisements in street view images. SCIENTIFIC REPORTS, 11 (1). 4884-.

This is the latest version of this item.

Access the full-text of this item by clicking on the Open Access link.
[img] Text
2007.04611v1.pdf - Submitted version

Download (3MB) | Preview
[img] Text
Using_AI_to_identify_unhealthy_advertisements.pdf - Author Accepted Manuscript

Download (2MB) | Preview

Abstract

While outdoor advertisements are common features within towns and cities, they may reinforce social inequalities in health. Vulnerable populations in deprived areas may have greater exposure to fast food, gambling and alcohol advertisements, which may encourage their consumption. Understanding who is exposed and evaluating potential policy restrictions requires a substantial manual data collection effort. To address this problem we develop a deep learning workflow to automatically extract and classify unhealthy advertisements from street-level images. We introduce the Liverpool [Formula: see text] Street View (LIV360SV) dataset for evaluating our workflow. The dataset contains 25,349, 360 degree, street-level images collected via cycling with a GoPro Fusion camera, recorded Jan 14th-18th 2020. 10,106 advertisements were identified and classified as food (1335), alcohol (217), gambling (149) and other (8405). We find evidence of social inequalities with a larger proportion of food advertisements located within deprived areas and those frequented by students. Our project presents a novel implementation for the incidental classification of street view images for identifying unhealthy advertisements, providing a means through which to identify areas that can benefit from tougher advertisement restriction policies for tackling social inequalities.

Item Type: Article
Additional Information: 13 pages, 5 figures, 3 table. To appear in Nature Scientific Reports
Uncontrolled Keywords: cs.CY, cs.CY, cs.LG
Depositing User: Symplectic Admin
Date Deposited: 09 Feb 2021 08:11
Last Modified: 18 Jan 2023 23:00
DOI: 10.1038/s41598-021-84572-4
Open Access URL: https://doi.org/10.1038/s41598-021-84572-4
Related URLs:
URI: https://livrepository.liverpool.ac.uk/id/eprint/3115344

Available Versions of this Item