Presentation 2014-06-21
Development and Performance Evaluation for Diffusion Analysis System on Social Media
Miki ENOKI, Masato OGUCHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In a microblogging service like Twitter, many short messages are posted each day. Some of them represent replies or messages forward among users. Creating a diffusion network to represent such forwarded messages is important to understand who forwarded the message and to identify the most influential users in the diffusion network. It is important to do this information diffusion analysis at a rapidly because social media data quickly loses its value. We are working on an information diffusion analysis system. To access the data more quickly, we developed a matrix index containing some of the data needed for diffusion analysis in a data access layer within an application server. This is a large and sparse matrix, so we use data compression techniques. We are currently studying the performance and overhead when encoding and decoding the matrix.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Social Network / Microblogging / Information Diffusion / Data Compression
Paper # DE2014-15
Date of Issue

Conference Information
Committee DE
Conference Date 2014/6/14(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Data Engineering (DE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Development and Performance Evaluation for Diffusion Analysis System on Social Media
Sub Title (in English)
Keyword(1) Social Network
Keyword(2) Microblogging
Keyword(3) Information Diffusion
Keyword(4) Data Compression
1st Author's Name Miki ENOKI
1st Author's Affiliation IBM Research-Tokyo:Ochanomizu University()
2nd Author's Name Masato OGUCHI
2nd Author's Affiliation Ochanomizu University
Date 2014-06-21
Paper # DE2014-15
Volume (vol) vol.114
Number (no) 101
Page pp.pp.-
#Pages 6
Date of Issue