The disclosure herein describes a system for generating customizable summaries of multi-message conversations in email threads and other multi-message and multi-participant messaging applications. A summary icon is displayed if the number of messages in a thread exceeds a threshold number. Message data is cleaned and analyzed by ML models to generate feature vectors representing the messages content. Multiple loglinear regression models compute similarity between message sentences. Clustering algorithm(s) to generate a multi-message conversation thread summary based on the values. If the user selects the summary icon, the multi-message conversation thread summary is displayed. The summary includes summary sentences and/or annotations describing content of the messages in the thread, participants contributing to the messages in the thread, links back to the original messages in the thread and/or a count of the number of messages contributed by each participant.

The disclosure herein describes a system for generating customizable summaries of multi-message conversations in email threads and other multi-message and multi-participant messaging applications. A summary icon is displayed if the number of messages in a thread exceeds a threshold number. Message data is cleaned and analyzed by ML models to generate feature vectors representing the messages content. Multiple loglinear regression models compute similarity between message sentences. Clustering algorithm(s) to generate a multi-message conversation thread summary based on the values. If the user selects the summary icon, the multi-message conversation thread summary is displayed. The summary includes summary sentences and/or annotations describing content of the messages in the thread, participants contributing to the messages in the thread, links back to the original messages in the thread and/or a count of the number of messages contributed by each participant.

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.

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.

Stepwise relationship cadence management can include generating a discourse cadence and confidence (DCC) measure based on a response message. The response message is made in replying to an originating message during a multi-party discourse over an electronic communication channel. The DCC measure indicates a likelihood of improving cadence and confidence with respect to an originator of the originating message and is based on a stepwise relational confidence model (SRCM) generated from an analysis of a plurality of prior multi-party discourses. Stepwise relationship cadence management can also include prompting a user to provide a follow-on message in response to determining that the response message made in replying to the originating message is not likely to improve cadence and confidence.

Various embodiments of the present invention are directed to an improved group-based communication apparatus that is configured to render one or more workflow interface objects to a group-based communication apparatus in association with an operational sequence set returned by a query. The group-based communication apparatus is configured to detect a workflow trigger event associated with a workflow identifier, retrieve an operational sequence set based upon at least the workflow identifier from a group-based communication workflow repository, initiate the operational sequence set, and cause rendering of one or more workflow interface objects to the group-based communication interface. In some embodiments, the operational sequence sets are associated with a group-defined template.

Various embodiments of the present invention are directed to an improved group-based communication apparatus that is configured to render one or more workflow interface objects to a group-based communication apparatus in association with an operational sequence set returned by a query. The group-based communication apparatus is configured to detect a workflow trigger event associated with a workflow identifier, retrieve an operational sequence set based upon at least the workflow identifier from a group-based communication workflow repository, initiate the operational sequence set, and cause rendering of one or more workflow interface objects to the group-based communication interface. In some embodiments, the operational sequence sets are associated with a group-defined template.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for creating and managing custom timelines. One of the methods includes receiving, from a user using a user account of a social messaging platform, input to a user interface displaying a message timeline of a social messaging platform, the user input requesting that the platform save a first message from the message timeline and, in response, saving the message to a custom timeline of the user account, wherein saving the message to the custom timeline includes associating with the custom timeline an identifier that identifies the first message; monitoring engagements by one or more other accounts with the first message with respect to one or more notification criteria; and in response to determining that the monitored engagements satisfy a trigger condition, providing a notification to the user account associated with the first message through the custom timeline.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for creating and managing custom timelines. One of the methods includes receiving, from a user using a user account of a social messaging platform, input to a user interface displaying a message timeline of a social messaging platform, the user input requesting that the platform save a first message from the message timeline and, in response, saving the message to a custom timeline of the user account, wherein saving the message to the custom timeline includes associating with the custom timeline an identifier that identifies the first message; monitoring engagements by one or more other accounts with the first message with respect to one or more notification criteria; and in response to determining that the monitored engagements satisfy a trigger condition, providing a notification to the user account associated with the first message through the custom timeline.

An online system allows users to exchange messages with other users, including entities such as businesses. The online system determines a metric describing measure of an entity's responsiveness to messages received via the online system based on a number of messages to which the entity responds and times for the entity to respond to messages. The online system displays an indication of the metric for an entity in connection with content identifying the entity. For example, the indication is displayed in conjunction with a content item identifying the entity, such as a content item including a link to initiate communication of a message to the entity.