Activity modeling in email or other forms of communication

A machine-readable storage device having instructions for execution by a processor of a machine to cause the processor to perform operations, the operations comprising:

• receiving a communication generated by a sender;
• determining an activity implied by the communication using a sender personalized latent activity model created by applying language analysis to one or more electronic prior sender communications to automatically extract language and contextual features from the one or more prior sender communications, using the language and contextual features to generate probability distributions, and combining the probability distributions;
• and
• tagging the communication with an indication of the activity.

A system comprising:

• a receiver port to receive content of messages and documents;
• one or more processors;
• and
• memory storing instructions that, when executed by the one or more processors, configure the one or more processors to perform operations comprising:
• receiving a communication generated by a sender;
• determining an activity implied by the communication using a sender personalized latent activity model created by applying language analysis to one or more electronic prior sender communications to automatically extract language and contextual features from the one or more prior sender communications, using the language and contextual features to generate probability distributions, and combining the probability distributions;
• and
• tagging the communication with an indication of the activity.