A system and method of predicting a user's rating of a new item in a collaborative filtering system in which an initial set of correlation coefficients for the intended users is used to bootstrap the system is described. The users are members of a predetermined organization and the initial correlation coefficient for each pair of users is based on the organizational relationship between the users. Prior organizational relationship information pertaining to the strength of ties, such as a formal organization chart and social network maps built using interviews or deduced from observed (online and/or offline) interaction patterns between potential users, is used to bootstrap the filtering system. Correlation coefficients can be updated as users rate or rerate items in the system.
A web-based shared document repository includes recommender system functions to allow users of the repository to input reviews of documents contained in the repository and to read inputted reviews. The recommender system functions appear as a seamless integration in the document repository by loosely coupling the shared document repository to a web-based recommender system.
A computer system models human memory by deriving associations between objects, events, and the context of the computer user or users. These associations can be dynamically generated, changing depending on the behavior of the user and context. Examples of areas in which this system can be used include time management (e.g., a calendar that presents time-based groupings of objects), people management (e.g., use analysis of user communications to rank importance of people to the user, groupings, and associations between people/groups and other objects such as documents, email), and general computer management (e.g., use analysis of user behavior to identify important objects and objects that are related to a current focus and context of the computer user).
The visibility of shared documents in a collaborative recommender system is managed by analyzing both the document's substance and user actions that are performed on the document. The document's substance includes both metadata and content. User actions include both user ratings and semantic actions. The visibility of the shared documents is updated when either a user action or an event occurs.
Remote site connections are screened based on assessments performed by members of a trust community. Data based on a plurality of end-user assessments of particular remote sites are received at a server from a plurality of end-users. Each end-user is associated with a specific client machine which is in communication with the server. The server generates assessment scores based on the data. Each of the assessment scores may be a ratio of end-users. The server transmits the assessment scores to the client machines. The client machine selectively takes protective action against ones of the particular remote sites that have an undesirable assessment score generated by the server. The protective action may be determined by comparing the assessment score against an individually specified end-user rule, wherein at least two client machines have different rules.
The method of the invention overcomes the problems in a community when the amount of interaction drops off through the use of "community crickets." A community cricket monitors the amount of community activity, establishes criteria for deciding when a community is sleeping and uses that criteria for initiating a recovery mechanism for "re-awakening" the community. A community is "sleeping" if the level of activity falls below some predetermined level or criteria. By monitoring the community's activity, the community cricket can prevent sleeping communities from dying. Various methods to detect and to re-awaken sleeping communities are defined.
