International Business Machines Corporation

Christine T Wolf

Dulce Beatriz Ponceleon

Yunyao Li

Shivakumar Vaithyanathan

Jorge Andres Moros Ortiz

Raphael I Arar

Rajasekar Krishnamurthy

Ioannis Katsis

Khoi-Nguyen Dao Tran

Erick Oduor

A computer system, a computer program product, and a computer-implemented system are provided for leveraging a national language processing (NLP) system for dynamically generating natural language output data. A NLP module investigates text or communication data from one or more platforms and derives global characteristic data from the investigated data. The derived global characteristic data is subject to modulation with a captured local writing style corresponding to a captured relationship. Contextual information is dynamically identified. Real-time natural language output communication data is generated that incorporates communication dynamics from the modulated global characteristic data and the dynamically identified contextual information.

Context aware personalization

A method, computer system, and a computer program product for feedback analysis is provided. The present invention may include, in response to identifying, using a natural language processing (NLP) component, a verb-related tag in a feedback data associated with a current version of a product or service, classifying the feedback data into a temporal class based on the identified verb-related tag. The present invention may also include, analyzing, using the NLP component, the classified feedback data within the temporal class. The present invention may further include, determining, based on the analyzed feedback data, a user perception associated with the current version of the product or service relative to the temporal class of the analyzed feedback data.

Analyzing temporal classes in user feedback

Embodiments are provided for analysis of errors of a predictive model. In some embodiments, a system can include a processor that executes computer-executable components stored in memory. The computer-executable components can include an overview component that causes a client device to present first data identifying an error corresponding to a cell of a confusion matrix for a classification model, the error representing a mismatch between a first label generated by the classification model and a second label corresponding to a ground-truth observation. The computer-executable components also can include an element view component that receives second data defining a root cause of the error. The computer-executable components can further include an error annotation component that can embed the second data into a first data structure containing the first data, resulting in a first annotated data structure.

Error analysis of a predictive model

Growing community of inventors

San Jose, CA, United States of America

Christine T Wolf