Gently

Gently was a project that my team and I built during a 36-hour hackathon called StartHack. We chose Supercell’s case, which was about reducing online vulgarity in their games. The main idea of the project was to promote positive in-game behavior and discourage negative behavior through a behavior score system that we implemented.
To achieve this, we first analyzed the different in-game behaviors that players could exhibit, such as trolling, deserting, and other unsportsmanlike conduct. We then used machine learning techniques to develop an algorithm that could analyze players’ behaviors in real-time, assigning them a score based on their conduct. Players with high scores would receive rewards and bonuses, while those with low scores would be penalized.
We also analyzed the in-game chat for any harmful or vulgar language that could lead to negative behavior. To do this, we used a natural language processing (NLP) model to analyze players’ chat messages and determine if they contained harmful language. If harmful language was detected, our system would suggest nicer alternatives for the player to use instead.
Overall, Gently was a successful project, and we were able to present it to Supercell during the hackathon. Our project was well received, and we received a lot of positive feedback from the judges. The project demonstrated the potential of using technology and machine learning to promote positive behavior and reduce online vulgarity, which could be useful not only for games but also for other online communities.