Visualizing topics with bubbles including pixels
First Claim
1. A method comprising:
- receiving, by a system including a processor, topics identified from records based on scoring candidate terms in the records according to a user-specified metric received by the system, and at least one further metric selected from among frequencies of occurrence of records pertaining to the candidate terms, and negativity of sentiment expressed with respect to the candidate terms in the records;
determining if each of the candidate terms corresponds to a critical event based on event detection data associated with each of the candidate terms;
generating for display, by the system, a visualization including bubbles representing the topics using the candidate terms that correspond to the critical event, wherein the bubbles each include pixels representing corresponding records, and further wherein a given bubble of the bubbles has a shape dependent upon a number of records represented by the given bubble and a time interval represented by the given bubble;
assigning, by the system, visual indicators to the pixels in the given bubble according to values of an attribute expressed in the corresponding records for a topic of the topics represented by the given bubble;
updating the visualization to create a new time interval if a newly received record is outside a current time interval; and
visualizing the newly received record in the new time interval.
8 Assignments
0 Petitions
Accused Products
Abstract
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.
25 Citations
20 Claims
-
1. A method comprising:
-
receiving, by a system including a processor, topics identified from records based on scoring candidate terms in the records according to a user-specified metric received by the system, and at least one further metric selected from among frequencies of occurrence of records pertaining to the candidate terms, and negativity of sentiment expressed with respect to the candidate terms in the records; determining if each of the candidate terms corresponds to a critical event based on event detection data associated with each of the candidate terms; generating for display, by the system, a visualization including bubbles representing the topics using the candidate terms that correspond to the critical event, wherein the bubbles each include pixels representing corresponding records, and further wherein a given bubble of the bubbles has a shape dependent upon a number of records represented by the given bubble and a time interval represented by the given bubble; assigning, by the system, visual indicators to the pixels in the given bubble according to values of an attribute expressed in the corresponding records for a topic of the topics represented by the given bubble; updating the visualization to create a new time interval if a newly received record is outside a current time interval; and visualizing the newly received record in the new time interval. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 16)
-
-
11. A system comprising:
at least one processor to; receive records including user feedback; identify candidate terms in the records; score the candidate terms according to a user-specified metric received by the system, and at least one further metric selected from among frequencies of occurrence of records pertaining to the candidate terms, and negativity of sentiment expressed with respect to the candidate terms in the records; select, based on the scoring, a subset of the candidate terms as topics; determine if each of the candidate terms corresponds to a critical event based on event detection data associated with each of the candidate terms; generate for display a visualization including bubbles representing the topics using the candidate terms that correspond to the critical event, wherein the bubbles each include pixels representing corresponding records, and further wherein a given bubble of the bubbles has a size and shape dependent upon a number of records represented by the given bubble and a time interval represented by the given bubble, and wherein the pixels in the given bubble are assigned visual indicators according to sentiments expressed in the corresponding records for a topic of the topics represented by the given bubble; update the visualization to create a new time interval if a newly received record is outside a current time interval; and visualize the newly received record in one of the bubbles in the new time interval. - View Dependent Claims (12, 13, 14, 17, 18)
-
15. An article comprising at least one non-transitory machine-readable storage medium storing instructions that upon execution cause a system to:
-
receive topics identified in records based on scoring candidate terms in the records according to a user-specified metric and at least two metrics selected from the group consisting of;
frequencies of occurrence of records pertaining to the candidate terms, negativity of sentiment expressed with respect to the candidate terms in the records, and a context coherence metric that indicates whether text expressed by multiple ones of the records pertaining to each candidate term relate to a common topic;determine if each of the candidate terms corresponds to a critical event based on event detection data associated with each of the candidate terms; generate for display a visualization including bubbles representing the topics using the candidate terms that correspond to the critical event, wherein the bubbles each include pixels representing corresponding records, and further wherein a given bubble of the bubbles has a size and shape dependent upon a number of records represented by the given bubble and a time interval represented by the given bubble, wherein points along a first axis of the visualization correspond to different ones of the topics, and points along a second axis of the visualization corresponds to different times, and wherein multiple bubble of the bubbles are arranged along a line parallel to the second axis, each of the multiple bubbles corresponding to one of the topics; assign visual indicators to the pixels in the given bubble according to sentiments expressed in the corresponding records for the topic represented by the given bubble; update the visualization to create a new time interval if a newly received record is outside a current time interval; and visualize the newly received record in one of the bubbles in the new time interval. - View Dependent Claims (19, 20)
-
Specification