The software development process is a lengthy process and an area where most companies spend a great amount of capital. Approximately half of this time developers are spending on fixing bugs in their code. Faulty software is difficult to identify both in location and reason. After finding a bug, it takes even more time to identify the correct solution to the problem. In this internship, we propose to create a novel approach that identifies topics and relationships between bugs in code. This approach will both identify and explain the faults in the software codebases, unlike any previous approach. This project will be more scalable than current static code analysis toolboxes that are rule-based and provide, at most, template explanations and recommendations. The generation of text will be based on state-of-the-art generation methods that create context-dependent recommendations for code bugs. This research will help developers understand bugs more and allow them to work more efficiently.