Abstract: A computer-implemented method according to one embodiment includes identifying a summary of a single instance of content, monitoring user interaction with the summary, and determining a relevancy of the summary to the single instance of content, based on the user interaction.

Abstract: A method for identifying sensitive information in a communication may include analyzing a plurality of communications associated with a user in a social networking system for concept and entity sharing to create a relationship graph of concept and entity sharing history. The method may also include analyzing a current communication from the user to extract one or more elements from the current communication. Each element may include an associated concept or entity and an associated sensitivity level. The method may additionally include determining a recipient based sensitivity level for each element based on an identity of each recipient and a relationship or connection of each recipient with each element using the relationship graph. The method may further include providing an indication of sending sensitive information in response to the recipient based sensitivity level of a particular element exceeding a configurable risk level threshold.

Abstract: Sentiment scores for a first set of text can be normalized based on a statistical measure of sentiment of a corpus of text authored by a set of authors having respective personality profiles similar to a personality profile of an author of the first set of text. The set of authors can be grouped in a first cluster based on a range of at least one metric of a personality profile. A plurality of respective sentiment scores for portions of the corpus can be generated for the first cluster. A statistical measure of the plurality of respective sentiment scores can be generated. The plurality of respective sentiment scores can be normalized based on the statistical measure. The plurality of respective normalized sentiment scores can be applied to the first set of text to generate one or more sentiment scores for the first set of text.

Abstract: A method for interpreting interpersonal communication includes monitoring a first interaction between two or more individuals using a set of monitoring devices including a camera, a microphone, and the like. A culture and personality type of at least one individual is identified based on the monitored first interaction. First cultural/personality profile information specific to the identified culture and personality type is retrieved from a database of cultural/personality profile information. A second interaction between the two or more individuals is monitored using the set of monitoring devices. A first facial expression, gesture, vocal intonation, or indication of emotional state derived from biometric data of the at least one individual is identified based on the monitored second interaction. The identified first expression is interpreted using the first cultural/personality profile information. The interpretation of the identified first expression is communicated to a user.

Abstract: Mechanisms for generating a cognitive traits avatar are provided. The mechanisms analyze a portion of content submitted by a user to extract features of the portion of content. The mechanisms map the extracted features to one or more cognitive traits and select an image corresponding to the one or more cognitive traits. The mechanisms further generate a cognitive traits avatar comprising the selected image and cognitive traits data defining a graphical representation of the one or more cognitive traits for output in association with the selected image. The cognitive traits avatar is output as part of an interaction of the user with another entity, or representation of another entity, via a computing device.

Abstract: A method for interpreting interpersonal communication includes monitoring a first interaction between two or more individuals using a set of monitoring devices including a camera, a microphone, and the like. A culture and personality type of at least one individual is identified based on the monitored first interaction. First cultural/personality profile information specific to the identified culture and personality type is retrieved from a database of cultural/personality profile information. A second interaction between the two or more individuals is monitored using the set of monitoring devices. A first facial expression, gesture, vocal intonation, or indication of emotional state derived from biometric data of the at least one individual is identified based on the monitored second interaction. The identified first expression is interpreted using the first cultural/personality profile information. The interpretation of the identified first expression is communicated to a user.

Abstract: Techniques presented herein describe rotating text content rendered on a mobile device to a preferred orientation based on the mobile device orientation and language of the text content. A display tool executing on the mobile device detects an orientation of the mobile device changing from a first orientation to a second orientation. The mobile device currently displays the characters in the text content according to the first orientation. The display tool determines that the text content is written in a specified language. The display tool re-renders the display of the characters in the text content and any accompanying images according to the second orientation.

Abstract: An approach is provided in which a knowledge manager receives a review request from a user to review an item. The knowledge manager identifies importance factors corresponding to the user and locates reviews of the item that include opinion phrases corresponding to the user's importance factors. In turn, the knowledge manager displays the set of located reviews on a display.

Abstract: Embodiments include method, systems and computer program products for dynamic national language support. In some embodiments, a request may be received from a client. An operation associated with the request may be determined. Context information may be extracted from the request. An artifact service instance may be selected based on the operation and the context information. Transmission of processed content from the artifact service instance may be facilitated in response to the request from the client.

Abstract: Techniques presented herein describe rotating text content rendered on a mobile device to a preferred orientation based on the mobile device orientation and language of the text content. A display tool executing on the mobile device detects an orientation of the mobile device changing from a first orientation to a second orientation. The mobile device currently displays the characters in the text content according to the first orientation. The display tool determines that the text content is written in a specified language. The display tool re-renders the display of the characters in the text content and any accompanying images according to the second orientation.

Abstract: Embodiments of the invention relate to identification of material that contains linguistically related content. Key phrases are filtered through a content store to ascertain the linguistically related content and to move the identified content to a target corpus. At least two iterations of the filtering process are employed. Each subsequent iteration of the filtering process identifies at least one new key phrase within the filtered material. In addition, each subsequent iteration takes place with a union of each previously employed key phrase and each new key phrase. As new content is identified, the content is populated to the target corpus.

Abstract: Embodiments of the invention relate to identification of material that contains linguistically related content. Key phrases are filtered through a content store to ascertain the linguistically related content and to move the identified content to a target corpus. At least two iterations of the filtering process are employed. Each subsequent iteration of the filtering process identifies at least one new key phrase within the filtered material. In addition, each subsequent iteration takes place with a union of each previously employed key phrase and each new key phrase. As new content is identified, the content is populated to the target corpus.

Abstract: Embodiments include method, systems and computer program products for coaching an individual during an interaction with a client to produce a desired outcome. Aspects include receiving a user profile for the client, one or more needs of the client, and a goal of the interaction and receiving a modeling profile for the client and relevant environmental information for the client. Aspects also include monitoring the interaction between the individual and the client and analyzing a feedback of the client to actions of the individual and providing guidance to the individual to assist the individual in producing the desired outcome, wherein the guidance is based on the feedback.

Abstract: A computer program product for generating content and context aware reminders for a user to take action on notes is provided. The computer program product includes a computer readable storage medium having program instructions embodied therewith. The program instructions are readable and executable by a processing circuit to cause the processing circuit to receive a user command to generate a note comprising note text relating to an action to be taken by the user, analyze the note text to find categorically identifiable keywords and temporal signatures, respectively associate the categorically identifiable keywords and temporal signatures with corresponding physical locations and corresponding times and remind the user to take the action based on one or more of spatial correlations between a current user location with the physical locations corresponding to the categorically identifiable keywords and temporal correlations between a current time and the times corresponding to the temporal signatures.

Abstract: An approach is provided that improves a question answering (QA) computer system by reducing a number of vague questions submitted to the QA system. When a question is submitted to the QA system, the approach performs a vagueness question analysis on the question. The vagueness question analysis results in a vagueness score. The question is submitted to the QA system in response to the vagueness score reaching a threshold value that indicates a lack of vagueness in the question. The approach inhibits submission of the question to the QA system in response to the vagueness score failing to reach the threshold value.

Abstract: An approach is provided that improves a question answering (QA) computer system by reducing a number of vague questions submitted to the QA system. When a question is submitted to the QA system, the approach performs a vagueness question analysis on the question. The vagueness question analysis results in a vagueness score. The question is submitted to the QA system in response to the vagueness score reaching a threshold value that indicates a lack of vagueness in the question. The approach inhibits submission of the question to the QA system in response to the vagueness score failing to reach the threshold value.

Abstract: A system and a computer program product are provided for evaluating question-answer pairs in an answer key by comparing a first answer key answer to a plurality of candidate answers to determine if the answer key may have a problem if the plurality of candidate answers are more similar to one another than to the first answer and to determine if the plurality of candidate answers has gradient information which may be used to update the answer key if not already included in the answer key.

Abstract: A system, method, and computer-readable medium are disclosed for cognitive personalized nutrition analysis comprising: performing a visual recognition operation to identify ingredients being used by a chef; analyzing sensor data to identify ingredients being used by a chef; determining a cooking style based upon the visual recognition operation and the sensor data; cross referencing ingredients and cooking style to locate potential recipes corresponding to the ingredients and cooking style; and, notifying the chef of identified recipes and possible substitutions.

Abstract: According to one exemplary embodiment, a method for generating an answer in a question answering system is provided. The method may include receiving a question. The method may also include identifying a candidate answer from a corpus. The method may then include determining a plurality of sentences based on the identified candidate answer. The method may further include calculating a similarity value for each sentence within the plurality of sentences based on comparing the plurality of sentences to the candidate answer and the received question. The method may also include identifying at least one sentence within the plurality of sentences with a calculated similarity value that exceeds a threshold value. The method may then include generating the answer based on the candidate answer and the identified at least one sentence.

Abstract: According to one exemplary embodiment, a method for generating an answer in a question answering system is provided. The method may include receiving a question. The method may also include identifying a candidate answer from a corpus. The method may then include determining a plurality of sentences based on the identified candidate answer. The method may further include calculating a similarity value for each sentence within the plurality of sentences based on comparing the plurality of sentences to the candidate answer and the received question. The method may also include identifying at least one sentence within the plurality of sentences with a calculated similarity value that exceeds a threshold value. The method may then include presenting the answer, whereby the answer comprises the plurality of sentences, the candidate answer, and metadata.