Please use this identifier to cite or link to this item: http://hdl.handle.net/10125/50294

Selfies of Twitter Data Stream through the Lens of Information Theory: A Comparative Case Study of Tweet-trails with Healthcare Hashtags

File SizeFormat 
paper0407.pdf1.35 MBAdobe PDFView/Open

Item Summary

Title: Selfies of Twitter Data Stream through the Lens of Information Theory: A Comparative Case Study of Tweet-trails with Healthcare Hashtags
Authors: Zhang, Yuan
Chang, Hsia-Ching
Keywords: Personal Health Management and Technologies
data visualization, entropy, information theory, structural analysis, Twitter
Issue Date: 03 Jan 2018
Abstract: Little research in information system has been carried out on the subject of user’s choice of different components when composing a tweet through the analytical lens of information theory. This study employs a comparative case study approach to examine the use of hashtags of medical-terminology versus lay-language in tweet-trails and (1) introduces a novel H(x) index to reveal the complexity in the statistical structure and the variety in the composition of a tweet-trail, (2) applies radar graph and scatter plot as intuitive data visualization aids, and (3) proposes a methodological framework for structural analysis of Twitter data stream as a supplemental tool for profile analysis of Twitter users and content analysis of tweets. This systematic framework is capable of unveiling patterns in the structure of tweet-trails and providing quick and preliminary snap shots (selfies) of Twitter data stream because it’s an automatic and objective approach which requires no human intervention.
Pages/Duration: 10 pages
URI/DOI: http://hdl.handle.net/10125/50294
ISBN: 978-0-9981331-1-9
DOI: 10.24251/HICSS.2018.406
Rights: Attribution-NonCommercial-NoDerivatives 4.0 International
Appears in Collections:Personal Health Management and Technologies


Please contact sspace@hawaii.edu if you need this content in an alternative format.

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