Document Server@UHasselt >
Research >
Research publications >

Please use this identifier to cite or link to this item: http://hdl.handle.net/1942/20417

Title: Geo-spatial Trend Detection through Twitter Data Feed Mining
Authors: Wijnants, Maarten
Blazejczak, Adam
Quax, Peter
Lamotte, Wim
Issue Date: 2015
Publisher: Springer International Publishing
Citation: Monfort, Valérie; Krempels, Karl-Heinz (Ed.). Web Information Systems and Technologies: 10th International Conference, WEBIST 2014, Barcelona, Spain, April 3-5, 2014, Revised Selected Papers, p. 212-227
Series/Report: Lecture Notes in Business Information Processing
Series/Report no.: 226
Abstract: Present-day Social Networking Sites are steadily progressing towards becoming representative data providers. This paper proposes TweetPos, a versatile web-based tool that facilitates the analytical study of geographic tendencies in crowd-sourced Twitter data feeds. To accommodate the cognitive strengths of the human mind, TweetPos predominantly resorts to graphical data structures such as intensity maps and diagrams to visualize (geo-spatial) tweet metadata. The web service’s asset set encompasses a hybrid tweet compilation engine that allows for the investigation of both historic and real-time tweet posting attitudes, temporal trend highlighting via an integrated animation system, and a layered visualization scheme to support tweet topic differentiation. TweetPos’ data mining features and the (geo-spatial) intelligence they can amount to are comprehensively demonstrated via the discussion of two representative use cases. Courtesy of its generic design, the TweetPos service might prove valuable to an interdisciplinary customer audience including social scientists and market analysts.
Notes: Wijnants, M (reprint author), Hasselt Univ tUL iMinds, Expertise Ctr Digital Media, Wetenschapspk 2, B-3590 Diepenbeek, Belgium. maarten.wijnants@uhasselt.be
URI: http://hdl.handle.net/1942/20417
DOI: 10.1007/978-3-319-27030-2_14
ISI #: 000369168500014
ISBN: 978-3-319-27030-2
ISSN: 1865-1348
Category: B2
Type: Book Section
Validation: ecoom, 2017
Appears in Collections: Research publications

Files in This Item:

There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.