Human curation refers to the process of selecting and organizing content by human editors, while algorithmic recommendation technology relies on algorithms to make decisions about what content to display to users based on various factors such as user preferences, popularity, and relevance.
In the study, the researchers analyzed a large dataset of user interactions with an online news outlet over a period of several months. They compared the performance of two different content presentation strategies: one that relied solely on algorithmic recommendations, and another that used a combination of human curation and algorithmic recommendations.
The results showed that the combination approach outperformed the algorithm-only approach in terms of user engagement metrics, such as click-through rates and time spent on the website. Specifically, the study found that:
Users who were presented with a mix of human-curated and algorithmically recommended content spent more time on the website compared to those who were only shown algorithm-generated content.
Users were more likely to click on links to articles that were presented in a human-curated section of the website than those that were only shown in an algorithm-generated section.
However, the study also found that the algorithm-only approach was more effective in promoting diversity of content and exposing users to new and emerging topics.
Overall, the study suggests that a combination of human curation and algorithmic recommendation technology may be the most effective approach for online news outlets seeking to optimize user engagement while also promoting diversity of content. By leveraging the strengths of both approaches, news outlets can provide users with a more personalized and enjoyable experience.
