International Business Machines Corporation

Rogelio Vazquez-Rivera

Jonathan D Dunne

Dennis Jinlone Chen

Jonathan Frederick Brunn

Ami H Dewar

Ethan A Geyer

Scott E Chapman

Amy D Travis

Andrew T Penrose

Vijay Francis

Rachael M Dickens

Liam S Harpur

Bo Jiang

Brendan P Arthurs

Charlotte Hutchinson

Rachael M H Dickens

Michael Celedonia

Katelyn Applegate

Thomas J Blanchflower

Identification of content classes deemed important by users is received. Classifiers are trained on user communication text to recognize content matching content classes. A composite classifier is applied to text of communication among users of a second set of users, including tagging, by the composite classifier, content in text of communication among the users of the second set. The tagging is responsive to the classifiers recognizing their respective content classes in text of communication among the users of the second set.

Composable natural language lenses for collaborative streams

A method, system and computer program product for providing enhanced action fulfillment using classification valency. At least a first message from a user in a channel is analyzed, the first message containing first data of a first data type, and a classification of the first message is inferred based on the first data's content. At least a second message from the user in the channel is analyzed, the second message containing second data of a second data type different from the first data type, and a classification model of the second message is derived based on the second data's content. The classification of the first message and the classification model of the second message are used to determine whether an additional inference is available based on the classification valency. The additional inference is incorporated to determine the enhanced action fulfillment, and the enhanced action is presented to the user for fulfillment.

Enhanced action fulfillment using classification valency

Various embodiments for managing dialog comments by a processor are provided. Each communication of a dialog communicated by one or more users using one of a plurality of applications may be monitored, tracked, and/or analyzed using a machine learning operation and/or a natural language processing operation. A topic trajectory of the dialog may be identified between one or more users using one of a plurality of applications. A selected comment submitted by the one or more users may be automatically transformed according to one or more corrective actions upon the selected communication deviating from the topic trajectory.

Managing dialog comments

A thread delta prediction and cognitive conversation opportunity generation. A prediction model may be generated based on chat space conversation data, and predicts a chat thread delta associated with a current chat conversation data. A data package may be created based on the chat thread delta. Based on the data package, a conversation opportunity may be determined for a given topic for given user in the chat space, to conduct during a time period of the chat thread delta in real-time.

Chat delta prediction and cognitive opportunity system

Synchronizing collaboration times for members of a team includes extracting emotive content and topical indicia from conversation data generated from multiple electronically captured conversations involving the team members. A model for generating time-based collaboration profiles for each member with respect to a specific topic can be constructed based on the emotive content and topical indicia. A synchronized collaboration time for the members of the team can be determined based on comparisons of each team member's respective collaboration profile.

Collaboration synchronization

A method, computer system, and computer program product for cognitively summarizing one or more collaborative moments is provided. An embodiment may include receiving a plurality of communications sent during a collaborative session. The embodiment may also include grouping the plurality of received communications into one or more bursts. The embodiment may further include assigning one or more keywords or one or more entities to each burst. The embodiment may also include generating a summary for each burst using one or more natural language processing techniques based on the assigned one or more keywords or one or more entities. The embodiment may further include transmitting the generated summary to each user participating in the collaborative session.

Cognitive collaborative moments

Growing community of inventors

Acton, MA, United States of America

Rogelio Vazquez-Rivera