I think you have to pick the tools that will allow you to get things done as fast as possible. Get you to something thats releasable (MVP) and allows you to test your assumptions. If you read a lot of the articles on HN you will see a lot are about how fast and cheap can you run experiments on your assumptions and execution. I think you are thinking in the opposite of what you need to be in saying, "I want to do it right, not necessarily quickly". So yeah my advice is .. if you know Java do Java, if you can pick up PHP fast, do it. Whatever makes sense and can get you a working prototype that clearly shows your vision.