Context

For one of my projects, I decided to build a video game recommender based on user review text. As many recommenders are built on numerical ratings, I thought it would be interesting to recommend based on what other users are saying.

Content

I used Selenium and BeautifulSoup to gather the data. The release year of the games can range from as far as 1998 to present (2018). You can find more of my work on this in my GitHub:

https://github.com/dahlia25/game_recommender

Some future project ideas:

• Classify genres of video games based on user comments
• Using NLP, find features that users liked/disliked in games

Acknowledgements

All data is from Metacritic.com. Without the support of my Metis classmates and instructors, this dataset would not be here.

Inspiration

Your data will be in front of the world's largest data science community. What questions do you want to see answered?