Evaluation of COVID-۱۹ Spread Effect on the Commercial Instagram Posts using ANN: A Case Study on The Holy Shrine in Mashhad, Iran

The widespread deployment of social media has helped researchers access an enormous amount of data in various domains, including the the COVID-۱۹ pandemic. This study draws on a heuristic approach to classify Commercial Instagram Posts (CIPs) and explores how the businesses around the Holy Shrine were impacted by the pandemic. Two datasets of Instagram posts (one gathered data from March ۱۴th to April ۱۰th, ۲۰۲۰, when Holy Shrine and nearby shops were closed, and one extracted data from the same period in ۲۰۱۹), two word embedding models – aimed at vectorizing associated caption of each post, and two neural networks – multi-layer perceptron and convolutional neural network – were employed to classify CIPs in ۲۰۱۹. Among the scenarios defined for the ۲۰۱۹ CIPs classification, the results revealed that the combination of MLP and CBoW achieved the best performance, which was then used for the ۲۰۲۰ CIPs classification. It was found out that the fraction of CIPs to total Instagram posts has increased from ۵.۵۸% in ۲۰۱۹ to ۸.۰۸% in ۲۰۲۰, meaning that business owners were using Instagram to increase their sales and continue their commercial activities to compensate for the closure of their stores during the pandemic. Moreover, the portion of non-commercial Instagram posts (NCIPs) in total posts has decreased from ۹۴.۴۲% in ۲۰۱۹ to ۹۱.۹۲% in ۲۰۲۰, implying the fact that since the Holy Shrine was closed, Mashhad residents and tourists could not visit it and take photos to post on their Instagram accounts.

Keywords:

Social Media , Classification , Coronavirus , Word embedding , Artificial Intelligence