An alphanumeric information entry process that includes provision and use of a personal context model that correlates various examples of user context against a unique personal language model for the user. The personal language model itself along with considerable correlation examples can be developed by statistical analysis of user documents and files including particularly email files (including address books). Such processing can be done locally or remotely. The personal context model is used to predict subsequent alphanumeric entries for a given user. In one embodiment predictions are presented one word at a time. Predictions can be automatically changed in one embodiment when the user fails to make any input for a predetermined period of time.