Are you taking context into consideration? For example, Donald Trump's tweets will be much higher than an ordinary person's.

Yes, we take expected count of a particular user/source node into consideration.

Will it work if anomalies are more in number than normal?

We assume (like any anomaly detection algorithm) that the majority is normal sample. In your context, the normal samples will be considered as outliers and therefore caught by the algorithm. One way to mitigate this is to either swap the labels. Another way is to sample a subset of the anomalies and then try.

Thank you. Is there a Java implementation available?

Currently MIDAS is available in Rust, Python, Ruby and R at https://github.com/bhatiasiddharth/MIDAS. If someone is interested to convert MIDAS to other languages, please feel free to do so and let me know so that I can add a link in the repository.