Researchers decode the science of creating engaging travel videos

By combining data, psychology and evolving digital platforms, brands are now learning not only who their customers are, but what they’ll do next.  

At the University of New Mexico in the US, Assistant Professor Hyunsang Son is using machine-learning technologies to explore how marketers can use social media data to their advantage.  

His recent research, published in the academic journal Tourism Management, focuses on influencer marketing in the tourism industry, using Instagram as a case study to determine what kinds of videos drive the most user engagement. 

The study analysed over 4,000 Instagram videos from 40 top travel influencers using a technique known as the transfer learning approach. This allows researchers to extract features from videos – including the video length, sentiment, facial expressions, colour saturation and brightness. 

“I can actually quantify the exact level of contribution each feature has on the number of likes and comments,” Son says. “It’s a combination of computer vision for feature extraction and traditional econometric modelling to estimate effects.” 

Without transfer learning, Son explains, the accuracy rate for classifying content might fall below 10%. But with it, that rate can rise to 96%. 

The study aimed to uncover what types of video content best engages users. Using an automatic video-feature extraction process, the team noted several important results: 

• Short-form videos performed better than longer ones. 

• Too much smiling reduced engagement. 

• Emotionally expressive content, including anger and sadness, increased engagement. 

• Product size visibility positively affected user interaction. 

• Brightness contributed to positive engagement, but too much contrast or rapid scene changes hurt performance. 

• Overuse of hashtags lowered engagement levels. 

• Emojis and post text also positively impacted user response when used strategically. 

“We wanted to see what kinds of factors influence user engagement – clicks, likes, comments,” Son says. “This data can help influencers and industries better understand how to craft their content.” 

The findings suggest that marketers can now offer content creators more than just creative direction – they can provide data-backed guidelines. For instance, creators can receive recommendations on how to act, express emotion, or place products in a video to boost engagement. 

You can find out more about the study here.