Exploring the Power of Multimodal Features for Predicting the Popularity of Social Media Image in a Tourist Destination

Vibhuti Gupta,Seung-Chul Yoo,Kwanghee Jung

doi:10.3390/mti4030064

Abstract

Social media platforms are widely used nowadays by various businesses to promote their products and services through multimedia content. Instagram is one of those platforms, which is used not only by companies to promote their products but also by local governments to promote tourist destinations. Predicting the popularity of the promotional tourist destination images helps marketers to plan strategically. However, given the abundance of images posted on Instagram daily, identifying the factors that determine the popularity of an image is a big challenge, due to informal and noisy visual content, frequent content evolution, a lack of explicit visual elements, and people’s informal behavior in liking, commenting on, and viewing the images. We present an approach to identify the factors most responsible for the popularity of tourist destinations-related images on Instagram. Our approach provides a proof of concept for an artificial intelligence (AI)-based real-time content management system, which will help to promote a tourist destination. The experiments on a collection of posts crawled from the official Instagram account of Jeju Island, which is one of the most popular tourist destinations in Korea, show that the recency of the post is the most important predictor of the number of likes and comments it will receive. Moreover, the combination of visual content and context features is an excellent predictor of popularity. The number of likes and comments are found to be complementary to each other for predicting image popularity.

Highlights

The reason why mass media used to be popular in marketing tourist destinations in the past is that mass media could reach a considerably broad target audience at a relatively low cost
Different from existing work, which identifies the factors responsible for the popularity of user-uploaded images, we focused on a specific domain of interest, tourist destination marketing, where the user’s liking behavior is different and less informal
Instead of using a time-consuming deep learning process of visual content feature extraction, we used an automated visual content analysis tool that reduces the extraction time, which will further help in real-time popularity predictions

Summary

Introduction

The reason why mass media used to be popular in marketing tourist destinations in the past is that mass media could reach a considerably broad target audience at a relatively low cost Another advantage is that the advertiser could control their promotional message. The problem is that outreach through mass media has become complicated, and it is very hard to obtain the desired advertising outcomes through a ‘pushing’ method centered on forced exposure, as consumers are using multiple media at the same time [1]. In this context, the application of digital media is rapidly increasing in the field of destination marketing.

Objectives

Results

Conclusion