Our Project

Our given dataset includes information about streaming media consumption in the Middle East between early 2019 and mid-2020. This dataset tells us information about what kinds of content people were watching during that time period, such as genres, languages, movies, or TV shows.  It also contains numerical information for each entry, such as unique users and total duration watched, for each week of the specified time frame.

In addition to this dataset, our group explored other options to analyze. We chose to examine written user data in the form of IMDb reviews. This dataset included highly polarized reviews, which were organized into positives and negatives. Our goal with this additional dataset was to examine which genres tended to receive positive reviews from users and determine whether those matched with the popular content from our given consumption dataset.

Our end goal with this project is to determine what variables tend to have the most impact on user engagement, which we have chosen to measure using the number of unique users. This will allow film and TV producers to determine what factors they should consider when releasing their content on media streaming services. For example, a company may consider adding a holiday movie on a streaming platform closer to the holiday season. 

In the future, we would love to explore other datasets that include current streaming data. We hope to explore the extent to which the trends we observed from our time period is reflected in today's streaming patterns!