Airbnb, Inc.

A session shared data system accesses a first communication between a user and a support agent on a first communication channel and stores communication data associated with the first communication in a session shared data object. The session shared data system accesses a subsequent communication between the user and a second agent on a second communication channel, receives a query associated with the subsequent communication and transmits the response to a device of the second agent.

A session shared data system accesses a first communication between a user and a support agent on a first communication channel and stores communication data associated with the first communication in a session shared data object. The session shared data system accesses a subsequent communication between the user and a second agent on a second communication channel, receives a query associated with the subsequent communication and transmits the response to a device of the second agent.

There is provided a method that is performed while a host and a guest are using a conversational messaging interface. For a message thread, in response to receiving a guest message, the method computes a probability for guest issues by inputting feature vectors from the guest message to a guest issue detection model. In response to receiving a host message, the message computes a probability for host issues by inputting feature vectors from the host message to a host issue detection model. If the message thread includes particular keywords, and if the probability for the guest issues is above a guest issue predetermined threshold, the method includes providing alerts that is visible only to the guest. If the probability for the host issues is above a host issue predetermined threshold, the method also includes providing alerts that is visible only to the host.

A method for predicting the behavior of an electronic social network (ESN) includes identifying one user's connections with other users and creating a data structure in a memory that represents the users and their connections in the ESN. A plurality of data sources for electronic communications between users are analyzed and assigned a relative importance value. A weight is also assigned to each of the connections between the users. The weight is an encoded value computed based on a link structure of the connections where the link structure includes metadata indicating a category and a status of the respective connection. The probability that one user will communicate with one of the other users is calculated based on the analyzed plurality of data sources calculating, and the user's connections with respect to other users are ranked based on the calculated probabilities.

An approach is described for addressing propagation of inaccurate information in a social networking environment. An associated method may include identifying inaccurate information within the social networking environment, facilitating creation of countering content to address the inaccurate information, and disseminating the countering content. The countering content may be determined by identifying behavior of one or more users among a plurality of users within the social networking environment. Identifying the inaccurate information within the social networking environment may include receiving information provided within the social networking environment. Upon determining that the received information is factual and thus objectively verifiable, it may be determined whether the received information matches analogous information verified as accurate. Upon determining that the received information does not match the analogous information verified as accurate, the received information may be marked as inaccurate.

Network site users can be selected to receive a communication based on a network site event, such as incomplete registration. A hybrid user interaction machine learning scheme can select a portion of the selected users based on user interaction estimates and network sampling data. The electronic document sent to the users can have portions that undergo two-pass ranking for ordering of content items to be included in the electronic document, such as an email.

Network site users can be selected to receive a communication based on a network site event, such as incomplete registration. A hybrid user interaction machine learning scheme can select a portion of the selected users based on user interaction estimates and network sampling data. The electronic document sent to the users can have portions that undergo two-pass ranking for ordering of content items to be included in the electronic document, such as an email.

A method for predicting the behavior of an electronic social network (ESN) includes identifying one user's connections with other users and creating a data structure in a memory that represents the users and their connections in the ESN. A plurality of data sources for electronic communications between users are analyzed and assigned a relative importance value. A weight is also assigned to each of the connections between the users. The weight is an encoded value computed based on a link structure of the connections where the link structure includes metadata indicating a category and a status of the respective connection. The probability that one user will communicate with one of the other users is calculated based on the analyzed plurality of data sources calculating, and the user's connections with respect to other users are ranked based on the calculated probabilities.

A method, system and computer program product for identifying anomalous behavior (e.g., suspicious transactions). Information from at least one social media source (e.g., a posting) and from at least one non-social media source (e.g., a booking) are monitored. A transaction (e.g., credit card transaction) involving a user is identified. The monitored information is then analyzed to identify one or more characteristics (e.g., location of the user) of the user. A rating of invalidity of the transaction is generated based on the one or more characteristics, where the rating of invalidity refers to the likelihood that the transaction is likely to be anomaly, such as a suspicious transaction. If the rating exceeds a threshold, then an anomaly may be said to have occurred. By identifying anomalous behavior using both social media and non-social media sources, anomalous activities that truly occurred will be more accurately detected.

Correspondences in a social networking system are analyzed to determine at least one topic. An activity stream with the at least one topic is analyzed. A target audience for the activity steam is identified. The activity stream is analyzed according to a uniqueness and a relationship criteria to form an assessment. The assessment is analyzed to a predetermined action criteria. Performing an action responsive to determining the assessment satisfies the predetermined action criteria.