Since data is too large to upload into the github, the datasets we are using is posted here
steam_games(39 MB) data in https://drive.google.com/file/d/1XrJUAfwMvg15HCGT80Cd5xpijYj8xd8U/view?usp=share_link steam_reviews(8 GB) data in https://drive.google.com/file/d/159DFZ9CHX_XX8YFn-JTzw4PSOHzuIPSY/view?usp=sharing
5000.csv(https://drive.google.com/file/d/1E42wT14WGFcZ7Sjks7N0uNsWO0tjY7Hp/view?usp=share_link) is the smaller dataset cut from the steam_reviews, and will be used in the newest version of the sentiment analysis
citation:
[Marko M.]. (2021). [Steam Reviews Dataset 2021]. Retrieved [Jan.27,2023] from [https://www.kaggle.com/datasets/najzeko/steam-reviews-2021].
[Tristan]. (2022; Nov.8th). [All 55,000 Games on Steam (November 2022)]. Retrieved [Feb.10,2023] from [https://www.kaggle.com/datasets/tristan581/all-55000-games-on-steam-november-2022].