Abstract: The disclosure herein describes a system for measuring probability of influence in digital communications to determine if communication content originated in a person's own prior knowledge or new information more recently obtained from interaction with communications of others. An estimated probability a new communication by a first user comes from the same distribution as prior communications of the first user are generated using multidimensional statistics on embeddings representing the communications. A second estimated probability that the new communication comes from the same distribution as communication(s) of a second user that were accessible to the first user are generated. If the second probability is greater than the first probability, the new communication is more likely influenced by exposure of the first user to the second user's communications rather than the first user's own historical knowledge.

Abstract: Examples provide a personalized data feed having progress indicators showing progress indicators associated with goal-related action items in the feed to assist users in achieving personalized objectives. A goal-related progress indicator is generated within the personalized data feed indicating a user's progress towards completing the goal. A per-item progress indicator is generated for each uncompleted item indicating additional predicted progress towards achieving the personalized goal if the item is completed by the user. A visual augmentation is provided within the data feed to identify items in the feed which assist the user in achieving the personalized goal, such as documents to read or review. This motivates the user to interact with the item to work towards completing their goal, as well as provides a comparative and/or quantitative measure of potential goal-related benefit to be gained by interacting with various items in the feed.