From the surface, being a travel influencer (literally) looks like the best job in the world. After all, they get to see incredible sights and stay in luxurious hotels and take eye-catching photos of their experiences. Instagram is the go-to platform for influencers because it gives them a chance to not only add flair and filters to the pictures but to also showcase their visuals to billions of users.
However, what does their day-to-day job look like when there is a global crisis?
The COVID-19 outbreak is putting a chokehold on the travel industry, as governments are urging citizens to not travel for both vacation and business. As a result, airports are nearly empty and What does this mean for a travel influencer? It doesn’t mean they are completely out of the job, but they are going to be creating content that is different than what their audiences are used to.
However, their previous vacation/location-oriented content is, in terms of follower engagement, still performing well. Certain pieces of content are still receiving likes and comments and it may tie into what colors and objects are featured predominately in the pictures. In these instances, Instagram users are engaging with pictures of the influencers nearby water and/or riding vehicles.
Now, the why behind users engaging with specific Instagram content could be for a variety of reasons. But, the patterns of engagement can be uncovered through a type of data science called unsupervised learning.
But, what a minute…what is unsupervised learning?
Datasets are consistently changing, and user’s data on a social media platform is no exception. But, how do marketing teams uncover patterns in those data to create content? They will use unsupervised machine learning.
It can be best described as a machine learning algorithm that will specifically look for patterns in datasets that may or may not have labeled responses. This will be commonly used to find patterns within large datasets, but those using unsupervised learning may not yet have a goal in mind with what to do with the results. It can also be used to reduce the dataset into groups that can be analyzed for further use.
The most common type of data classification with unsupervised machine learning is cluster analysis, which will put data into specific groups, based on shared characteristics. This usually follows into two groups; hard clustering and soft clustering. The difference between the two is hard clustering involves data points only belonging to one cluster and soft clustering, where each data point can belong to multiple clusters.
By using unsupervised machine learning, data can be easily put into categories that will be useful for creating content.
And what can be used to show this data?
Cortex’s enterprise SaaS platform utilizes unsupervised machine learning to analyze the performance of visual content. It can be used on social media platforms, such as Instagram, to point out several factors of engagement. This can include what colors are most prominent and what objects are found in a person’s Instagram photos. As this data is gathered, it is then sorted into clusters based on those characteristics.
Let’s circle back to the above paragraphs; specifically the ones about previous content doing well with user engagement. Both Lauren Bullen and Jack Morris are not the only travel influencers with pictures predominantly showcasing particular colors and/or image subjects. When it comes to taking pictures of seasonal fashion, several influencers, including Lindsay Silberman and Alyssa Griffith, are still performing well. What about colors? Bright shades of gray blue and pink are appealing to the eye, and those colors are found in some of the better performing Instagram photos.
By using the Cortex, an influencer can gain a deeper insight into what content they can produce during a slow period or, be a little more optimistic when things are beginning to return to normal and they can resume their job of going to incredible places.