Daphna Buchsbaum

US Patent:

8103682, Jan 24, 2012

Filed:

Aug 24, 2010

Appl. No.:

12/862242

Inventors:

Pablo Funes - Somerville MA, US
Elena Popovici - Boston MA, US
Paolo Gaudiano - Essex MA, US
Daphna Buchsbaum - Berkeley CA, US
Denis Garagic - Wayland MA, US
M. Ihsan Ecemis - Boston MA, US
Eric Bonabeau - Winchester MA, US
Chris Bingham - Cambridge MA, US

Assignee:

Icosystem Corporation - Cambridge MA

International Classification:

G06F 7/00

US Classification:

707755

Abstract:

Methods and systems for text data analysis and visualization enable a user to specify a set of text data sources and visualize the content of the text data sources in an overview of salient features in the form of a network of words. A user may focus on one or more words to provide a visualization of connections specific to the focused word(s). The visualization may include clustering of relevant concepts within the network of words. Upon selection of a word, the context thereof, e. g. , links to articles where the word appears, may be provided to the user. Analyzing may include textual statistical correlation models for assigning weights to words and links between words. Displaying the network of words may include a force-based network layout algorithm. Extracting clusters for display may include identifying “communities of words” as if the network of words was a social network.

US Patent:

20090070320, Mar 12, 2009

Filed:

May 12, 2008

Appl. No.:

12/119028

Inventors:

Julien Budynek - Boston MA, US
Una-May O'Reilly - Weston MA, US
Daphna Buchsbaum - Somerville MA, US
Pablo Funes - Somerville MA, US
Eric Bonabeau - Winchester MA, US
Siegfried Martens - Waltham MA, US

Assignee:

Icosystem Corporation - Cambridge MA

International Classification:

G06F 17/30

US Classification:

707 5, 707 3, 707E17014, 707E17015

Abstract:

Methods and apparatus include presenting an initial set of names to a user. The user selects a set of names from those presented. An Interactive Evolutionary Algorithm (IEA) extracts features of each selected name from a database of names and features to form a feature set. The IEA forms a set of match features that are chosen from the feature set according to a priority function and/or weighting of the features, either of which may vary in succeeding iterations. The IEA searches the database to obtain a candidate set of names, where each name has features matching the match features. One or more names is chosen from the candidate set and added into a presentation set of names. The IEA may repeat the formation of the match features, candidate set, and selection of one or more names from the candidate set until the new presentation set is complete.

US Patent:

20090144617, Jun 4, 2009

Filed:

Jan 31, 2008

Appl. No.:

12/023693

Inventors:

Pablo Funes - Somerville MA, US
Elena Popovici - Boston MA, US
Paolo Gaudiano - Essex MA, US
Daphna Buchsbaum - Berkeley CA, US
Denis Garagic - Wayland MA, US
M. Ihsan Ecemis - Boston MA, US
Chris Bingham - Cambridge MA, US
Eric Bonabeau - Winchester MA, US

International Classification:

G06F 17/21

US Classification:

715256

Abstract:

Methods and systems for text data analysis and visualization enable a user to specify a set of text data sources and visualize the content of the text data sources in an overview of salient features in the form of a network of words. A user may focus on one or more words to provide a visualization of connections specific to the focused word(s). The visualization may include clustering of relevant concepts within the network of words. Upon selection of a word, the context thereof, e.g., links to articles where the word appears, may be provided to the user. Analyzing may include textual statistical correlation models for assigning weights to words and links between words. Displaying the network of words may include a force-based network layout algorithm. Extracting clusters for display may include identifying “communities of words” as if the network of words was a social network.