generating, for first text data, a first vector, wherein each element of the first vector comprises a value indicating whether the first text data includes a respective n-gram included in a corpus of text data;

determining, for the first text data, first label data indicating that a user associated with the first text data has connected to a first computer-implemented service more than a threshold number of times during a past time period;

training a first machine learning model based at least in part on the first vector and the first label data;

determining, using the first machine learning model, a first probability associated with a first n-gram of the first vector; and

determining at least a first user associated with the first n-gram.