Abstract: Online group advisor selection is described. According to a computer-implemented method, users are formed into an online group. Online group membership is based at least in part on a shared interest in a particular topic. Based on online interactions between members of the group and the online activity of group members, a group advisor is identified from among the members of the online group. Administrative rights over online activity for the group is assigned to the group advisor.

Abstract: A method, system and computer readable program storage device for facilitating a collaboration experience. In embodiments, the method comprises identifying a group of people for a specified collaboration experience; identifying specified conditions and preferences for the group of people; using the identified specified conditions and preferences for the group of people for determining an environment for the specified collaboration experience and one or more factors for improving the specified collaboration experience; and sending a specified set of information to one or more prospective collaboration entities to determine if any one of the prospective collaboration entities has the determined environment for the specified collaboration experience.

Abstract: A computer-implemented method includes receiving, by a computer device, an electronic notice of a current transaction being attempted by a first user at an electronic transaction device, the current transaction requiring access to a joint account, the first user and a second user having authority to access an asset in the joint account; comparing in real time, by the computer device, the current transaction to historical classification data; classifying in real time, by the computer device, the current transaction based on the comparing; and transmitting in real time, by the computer device, to the electronic transaction device an electronic communication indicating the current transaction is approved based on determining one of: the current transaction is classified as pre-approved; and the current transaction is classified as non-pre-approved and the current transaction does not exceed a predetermined threshold.

Abstract: Utilizing a computing device to share a social media post with automatically generated dynamic text in a social media service in real time. A computing device receives a social media post from a social media user computer. The computing device monitors social media activities of a social media user computer. The computing device accesses one or more social media activities of social media follower computers. The computing device compares social media activities of the social media user computer with the one or more social media activities of social media follower computers. The computing device aligns the received social media post to a preference model. The computing device generates dynamic text in real time to accompany the received social media post. The computing device outputs the generated dynamic text to the social media user computer to accompany the received social media post.

Abstract: Processors are configured to analyze message text content to determine whether the text content proposes a meeting event at a specified location and a specified time. In response to determining that the text content proposes said meeting event, processors determine whether a meeting is possible at the specified location and the specified time as a function of forum availability. In response to determining that the meeting is possible, some processors generate a confirming appointment message comprising text content that identifies creation of a meeting event at the meeting place at the specified location and at the specified time. In response to determining that the meeting is not possible, processors create an alternative meeting proposal message that includes alternative text content, including an alternative, different location or an alternative, different time.

Abstract: Approaches presented herein enable evaluating a multimedia item to be posted to a website (e.g., social networking site, forum, blog, etc.) to determine whether a censoring action needs to be performed on the multimedia item prior to posting the multimedia item. Specifically, in response to a request to post a multimedia item to a website, the multimedia item is analyzed to determine a context of the multimedia item. The context may be derived from specific elements depicted in the multimedia item. Also, an entity (e.g., a person, logo, trademark, brand) may be identified. The preferences related to the entity are retrieved. The context is compared against the preferences of the entity to determine whether a variance exists. When a variance is determined, a censoring action related to the multimedia item may be performed prior to posting the multimedia item.

Abstract: By performing Natural Language Processing (NLP) on a comment to a social media post, an entity that is referenced in the comment is extracted. The entity is an object other than a human face that is depicted in an image in the post. The image is analyzed to determine whether the entity is represented in the image. When the entity is represented in the image, a sentiment value of the comment is computed relative to the entity. A value corresponding to the sentiment value is assigned to a characteristic of a graphical artifact. A position is determined relative to an area occupied by the entity in the image. The graphical artifact is caused to be overlaid on the image at the position and with the value of the characteristic.

Abstract: A method comprises a computer-implemented virtual assistant (VA) determining user information to communicate to a recipient, receiving VA input information, and determining a recipient context. In response to determining the recipient context, the VA composes a preferred presentation based on information attributes and recipient attributes. The VA outputs the user information according to the preferred presentation. A virtual assistant system comprises personal information, a preferred presentation, and a computer-implemented VA. The VA is configured to compose user information and to receive VA input information. In response to receiving the VA input information, the VA determines a recipient context and composes the preferred presentation based on the user information, recipient context, information attributes, and recipient attributes. The VA outputs the user information according to the preferred presentation. A computer program product can embody the method.

Abstract: Methods and systems for balanced conformity in chat conversations are disclosed. A method includes: collecting, by a computing device, data from an ongoing group chat; determining, by the computing device, a baseline tone for a plurality of participants in the ongoing group chat using the collected data; determining, by the computing device, a current tone for the plurality of participants in the ongoing group chat using the collected data; determining, by the computing device, a conformity risk score using the baseline tone and the current tone for the plurality of participants in the ongoing group chat; and in response to determining that the conformity risk score exceeds a first predetermined threshold, the computing device automatically inviting an additional participant to join the ongoing group chat.

Abstract: Systems and methods for tagging video content are disclosed. A method includes: receiving a video stream from a user computer device, the video stream including audio data and video data; determining a candidate audio tag based on analyzing the audio data; establishing an audio confidence score of the candidate audio tag based on the analyzing of the audio data; determining a candidate video tag based on analyzing the video data; establishing a video confidence score of the candidate video tag based on the analyzing of the video data; determining a correlation factor of the candidate audio tag relative to the candidate video tag; and assigning a tag to a portion in the video stream based on the correlation factor exceeding a correlation threshold value and at least one of the audio confidence score exceeding an audio threshold value and the video confidence score exceeding a video threshold value.

Abstract: Aspects analyze published items to identify and distinguish a graphic image content or text string content element from other elements within the content of the published item, wherein the item is published with user comments. In response to a selection of the distinguished element, metadata and text content of the comments are analyzed to identify associations to the selected element. Aspects differentially display a subset of the comments in association with the published item, relative to display of remaining others of the comments, in response to determining that the analyzed metadata or analyzed text content of the subset of comments is associated with the selected element, and that the analyzed metadata or analyzed text content of the remaining others of the comments is not associated with the selected element.

Abstract: Utilizing a computing device to share a social media post with automatically generated dynamic text in a social media service in real time. A computing device receives a social media post from a social media user computer. The computing device monitors social media activities of a social media user computer. The computing device accesses one or more social media activities of social media follower computers. The computing device compares social media activities of the social media user computer with the one or more social media activities of social media follower computers. The computing device aligns the received social media post to a preference model. The computing device generates dynamic text in real time to accompany the received social media post. The computing device outputs the generated dynamic text to the social media user computer to accompany the received social media post.

Abstract: A sentiment analysis of a chat session in which a plurality of chat messages are posted is performed. Based on the sentiment analysis, at least one emotive model is derived for the chat session. A sentiment of users in the chat session can be determined using the emotive model. A user composing a new chat message for the chat session can be monitored. Based on the monitoring, an impact on the sentiment of the users in the chat session by the new chat message can be determined. A client device can be initiated to display the impact on the sentiment of the users in the chat session by the new chat message before the new chat message is posted in the chat session.

Abstract: Provided are a computer program product, system, and method for using remote words in data streams from remote devices to autocorrect input text. Remote words included in a at least one data stream are accessed from at least one remote device over a network to store in a remote word corpus. User input text is received in a text entry field in a user interface rendered by the computer device. Local words are maintained in a local word corpus stored in the computer device. The local words and the remote words are used to autocorrect and validate the user input text.

Abstract: A system, method and computer program product for cognitive copy and paste. The method includes: receiving, at a hardware processor of a computer system, an input representing a selection of a content captured from a source application program, and receiving an input representing an identified target application program that will receive the selected content to be copied and rendered in the target application program. The selected content is analyzed to determine a context for the selected content; and a rendering of the selected content at a location within the destination application based on the determined context, the rendering achieving a best representation of the selected content on the destination application. The analyzing includes invoking a natural language processor to determine an intent, meaning, or an intended use of the selected content based on the determined context, and employs a support vector machine for determining a best format change when rendering.

Abstract: A map-display-based, computer-implemented approach is provided for providing directions to a user to assist the user in reaching a destination. The approach includes, for instance, collecting at a map display user input data, where the user input data includes the user's destination. In addition, the approach includes generating, by a directions generating facility associated with the map display, directions for the user to use in navigating from a current location to the user's destination, and downloading the directions generated by the directions generating facility to a mobile device of the user to assist the user in reaching the desired destination after leaving the map display. The downloading of directions to the user's mobile device may include downloading the directions in at least one of text data format or voice data format.

Abstract: A method for controlling a device may include obtaining a conflict-resolution setting from a plurality of available conflict settings. The conflict resolution settings may establish one or more rules for resolving conflicting commands received by the device from a first user and a second user. The method may further include determining, based at least in part on the conflict-resolution setting, a response to a second command issued by the second user that conflicts with a first command issued by the first user. The method may further include performing the response.

Abstract: Delivering content based on predicted effect can include analyzing, using computer hardware, digital content before providing the digital content to a device of a user, predicting, using the computer hardware, an effect that the digital content will have on a circadian rhythm of the user, based on the predicted effect, modifying, using the computer hardware, the digital content to generate modified digital content, and providing, using the computer hardware, the modified digital content to the device of the user.

Abstract: An approach is provided to detect pronouns that are included in textual posts that are found in an online discussion. The textual posts are analyzed using a natural language processing speech classification technique, that results in an identification of a noun to which the detected pronoun refers. The system then displays, on a display device, the noun to which the pronoun refers.

Abstract: An embodiment of the invention may include a method, computer program product and system for communicating information to a user via a graphical user interface of a computer. An embodiment may include displaying a visual cue corresponding to a suggestion for text substitution within a text representation of a media file, wherein the suggestion for text substitution is generated in response to identification of any one or combination of a repeated word, a repeated phrase, and a filler, and wherein the suggestion for text substitution is based on an aggregation of one or more of characteristics of the text representation of the media file.