Hewlett-packard Development Company, L.p.

Hewlett Packard Enterprise Development LP

Micro Focus Lcc

Christian Rohrdantz

Ming C Hao

Umeshwar Dayal

Meichun Hsu

Riddhiman Ghosh

Lars-Erik Haug

Daniel Keim

Mohamed E Dekhil

Nelson L Chang

Cheng Chang

Michael Hund

Bao-Yao Zhou

A technique for visualizing topics includes depicting topic bubbles including pixels. In one example, selected topics are identified from records based on scoring candidate terms in the records according to a user-specified metric and a metric selected from among frequencies of occurrence of records pertaining to the respective candidate terms, and negativity of sentiment expressed with respect to the candidate terms in the records. A visualization is generated including bubbles representing topics, the bubbles including pixels representing corresponding records. A bubble has a shape dependent upon a number of records and a time interval represented by the bubble. Visual indicators are assigned to the pixels in a given bubble according to values of an attribute expressed in the corresponding records for the topic represented by the given bubble, resulting in the analysis of the selected topics being less time consuming and labor intensive.

Visualizing topics with bubbles including pixels

An event occurring in a particular geographic region is identified based on disseminated information containing public commentary in the particular geographic region. Attributes that are related to the event are identified, and sentiment words relating to the identified event are extracted from the disseminated information, where the extracted sentiment words are in a local language of the particular geographic region. A sentiment trend visualization is generated that depicts a trend of sentiments of at least a particular one of the identified attributes, wherein the sentiments are based on the sentiment words for at least the particular attribute.

Sentiment trent visualization relating to an event occuring in a particular geographic region

A system causes display of a visual representation of a cell-based calendar having cells representing data records, where the cells have corresponding visual indicators corresponding to values of the respective data records. The cells are arranged in plural blocks corresponding to time intervals of the cell-based calendar. Event visual indicators transparently overlay cells in at least some of the plural blocks, where the event visual indicators represent events that occurred in time intervals corresponding to the at least some blocks. The events are separate from activities represented by the data records. Providing the event visual indicators transparently overlaid over the cells in the at least some blocks depict a relationship and relative impact between the data records and the events.

Visual representation of a cell-based calendar transparently overlaid with event visual indicators for mining data records

A system may include an extraction engine to extract candidate phrases from a content stream, and an analysis engine to assign the candidate phrases visual cues and display the visual cues to an operator.

Visual analysis of phrase extraction from a content stream

Attributes in data records are identified. Episodes corresponding to the respective attributes include respective data records. The episodes are scored, where scoring of a particular one of the episodes is based on relative time densities between successive data records of the particular episode. A visualization of at least some of the episodes to provide an alert of time-dense episodes.

Visualizing time-dense episodes

Sentiment analysis of user feedback is performed, using uncertainty rules. Different levels of uncertainty associated with sentiment results of the sentiment analysis are determined, where the sentiment results identify user sentiments contained in the user feedback. At least one visualization of the sentiment result is provided, where the visualization has first visual indicators to represent respective user sentiments, and second visual indicators associated with the first visual indicators to represent respective levels of uncertainty associated with the respective user sentiments.

Visualizing sentiment results with visual indicators representing user sentiment and level of uncertainty

Data records containing user feedback regarding at least one offering are received. From among candidate attributes in the received data records, a subset of attributes that relate to user sentiment regarding the at least one offering is selected, where the selecting is according to selection criteria including frequency of occurrence of the candidate attributes, relative amounts of negative and positive feedback associated with the candidate attributes, and time density of feedback associated with the candidate attributes. A visualization of at least one sentiment characteristic of the selected subset of attributes that relate to user sentiment is presented for display.

Growing community of inventors

Constance, Germany

Christian Rohrdantz