The information diffusion model in the blog world

Yong Suk Kwon, Sang Wook Kim, Sunju Park, Seung Hwan Lim, Jae Bum Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

12 Citations (Scopus)

Abstract

In the blog network, the posts in a blog can be diffused to other blogs through trackbacks and scraps. Analyzing information diffusion in the blog network is an important research issue that can be used for predicting information diffusion, detecting abnormality, marketing, and revitalizing the blog world. Existing studies on information diffusion in a blog network define explicit relationships between blogs and analyze the word-of-mouth effect through such explicit relationships only. However, it has been observed that more than 85% of all information diffusion in a blog network occurs through non-explicit relationships. In this paper, we propose a new model that considers both the explicit and non-explicit relationships between blogs in order to explain the information diffusion phenomena in a blog network. We add a super node and the relationships between the super node and blogs as broadcast edges and register edges to the existing information diffusion model and assign the assimilation probability to every relationship. The expanded information diffusion model improves the accuracy of the basic model by taking into account the degrees of diffusion powers of posts. We verify the superiority of the proposed model through extensive experiments of information diffusion at a real blog network. The experimental results show that our expanded information diffusion model generates 77% less errors than the existing model.

Original languageEnglish
Title of host publicationProceedings of the 3rd Workshop on Social Network Mining and Analysis, SNA-KDD '09
DOIs
Publication statusPublished - 2009 Dec 1
Event3rd Workshop on Social Network Mining and Analysis, SNA-KDD '09 - Paris, France
Duration: 2009 Jun 282009 Jun 28

Publication series

NameProceedings of the 3rd Workshop on Social Network Mining and Analysis, SNA-KDD '09

Other

Other3rd Workshop on Social Network Mining and Analysis, SNA-KDD '09
CountryFrance
CityParis
Period09/6/2809/6/28

Fingerprint

Blogging
Blogs
Computer networks
Marketing

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Computer Science Applications
  • Social Psychology

Cite this

Kwon, Y. S., Kim, S. W., Park, S., Lim, S. H., & Lee, J. B. (2009). The information diffusion model in the blog world. In Proceedings of the 3rd Workshop on Social Network Mining and Analysis, SNA-KDD '09 [1731015] (Proceedings of the 3rd Workshop on Social Network Mining and Analysis, SNA-KDD '09). https://doi.org/10.1145/1731011.1731015
Kwon, Yong Suk ; Kim, Sang Wook ; Park, Sunju ; Lim, Seung Hwan ; Lee, Jae Bum. / The information diffusion model in the blog world. Proceedings of the 3rd Workshop on Social Network Mining and Analysis, SNA-KDD '09. 2009. (Proceedings of the 3rd Workshop on Social Network Mining and Analysis, SNA-KDD '09).
@inproceedings{a3e587db5a784954bf56eeeba305b29b,
title = "The information diffusion model in the blog world",
abstract = "In the blog network, the posts in a blog can be diffused to other blogs through trackbacks and scraps. Analyzing information diffusion in the blog network is an important research issue that can be used for predicting information diffusion, detecting abnormality, marketing, and revitalizing the blog world. Existing studies on information diffusion in a blog network define explicit relationships between blogs and analyze the word-of-mouth effect through such explicit relationships only. However, it has been observed that more than 85{\%} of all information diffusion in a blog network occurs through non-explicit relationships. In this paper, we propose a new model that considers both the explicit and non-explicit relationships between blogs in order to explain the information diffusion phenomena in a blog network. We add a super node and the relationships between the super node and blogs as broadcast edges and register edges to the existing information diffusion model and assign the assimilation probability to every relationship. The expanded information diffusion model improves the accuracy of the basic model by taking into account the degrees of diffusion powers of posts. We verify the superiority of the proposed model through extensive experiments of information diffusion at a real blog network. The experimental results show that our expanded information diffusion model generates 77{\%} less errors than the existing model.",
author = "Kwon, {Yong Suk} and Kim, {Sang Wook} and Sunju Park and Lim, {Seung Hwan} and Lee, {Jae Bum}",
year = "2009",
month = "12",
day = "1",
doi = "10.1145/1731011.1731015",
language = "English",
isbn = "9781605586762",
series = "Proceedings of the 3rd Workshop on Social Network Mining and Analysis, SNA-KDD '09",
booktitle = "Proceedings of the 3rd Workshop on Social Network Mining and Analysis, SNA-KDD '09",

}

Kwon, YS, Kim, SW, Park, S, Lim, SH & Lee, JB 2009, The information diffusion model in the blog world. in Proceedings of the 3rd Workshop on Social Network Mining and Analysis, SNA-KDD '09., 1731015, Proceedings of the 3rd Workshop on Social Network Mining and Analysis, SNA-KDD '09, 3rd Workshop on Social Network Mining and Analysis, SNA-KDD '09, Paris, France, 09/6/28. https://doi.org/10.1145/1731011.1731015

The information diffusion model in the blog world. / Kwon, Yong Suk; Kim, Sang Wook; Park, Sunju; Lim, Seung Hwan; Lee, Jae Bum.

Proceedings of the 3rd Workshop on Social Network Mining and Analysis, SNA-KDD '09. 2009. 1731015 (Proceedings of the 3rd Workshop on Social Network Mining and Analysis, SNA-KDD '09).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - The information diffusion model in the blog world

AU - Kwon, Yong Suk

AU - Kim, Sang Wook

AU - Park, Sunju

AU - Lim, Seung Hwan

AU - Lee, Jae Bum

PY - 2009/12/1

Y1 - 2009/12/1

N2 - In the blog network, the posts in a blog can be diffused to other blogs through trackbacks and scraps. Analyzing information diffusion in the blog network is an important research issue that can be used for predicting information diffusion, detecting abnormality, marketing, and revitalizing the blog world. Existing studies on information diffusion in a blog network define explicit relationships between blogs and analyze the word-of-mouth effect through such explicit relationships only. However, it has been observed that more than 85% of all information diffusion in a blog network occurs through non-explicit relationships. In this paper, we propose a new model that considers both the explicit and non-explicit relationships between blogs in order to explain the information diffusion phenomena in a blog network. We add a super node and the relationships between the super node and blogs as broadcast edges and register edges to the existing information diffusion model and assign the assimilation probability to every relationship. The expanded information diffusion model improves the accuracy of the basic model by taking into account the degrees of diffusion powers of posts. We verify the superiority of the proposed model through extensive experiments of information diffusion at a real blog network. The experimental results show that our expanded information diffusion model generates 77% less errors than the existing model.

AB - In the blog network, the posts in a blog can be diffused to other blogs through trackbacks and scraps. Analyzing information diffusion in the blog network is an important research issue that can be used for predicting information diffusion, detecting abnormality, marketing, and revitalizing the blog world. Existing studies on information diffusion in a blog network define explicit relationships between blogs and analyze the word-of-mouth effect through such explicit relationships only. However, it has been observed that more than 85% of all information diffusion in a blog network occurs through non-explicit relationships. In this paper, we propose a new model that considers both the explicit and non-explicit relationships between blogs in order to explain the information diffusion phenomena in a blog network. We add a super node and the relationships between the super node and blogs as broadcast edges and register edges to the existing information diffusion model and assign the assimilation probability to every relationship. The expanded information diffusion model improves the accuracy of the basic model by taking into account the degrees of diffusion powers of posts. We verify the superiority of the proposed model through extensive experiments of information diffusion at a real blog network. The experimental results show that our expanded information diffusion model generates 77% less errors than the existing model.

UR - http://www.scopus.com/inward/record.url?scp=77951482912&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77951482912&partnerID=8YFLogxK

U2 - 10.1145/1731011.1731015

DO - 10.1145/1731011.1731015

M3 - Conference contribution

SN - 9781605586762

T3 - Proceedings of the 3rd Workshop on Social Network Mining and Analysis, SNA-KDD '09

BT - Proceedings of the 3rd Workshop on Social Network Mining and Analysis, SNA-KDD '09

ER -

Kwon YS, Kim SW, Park S, Lim SH, Lee JB. The information diffusion model in the blog world. In Proceedings of the 3rd Workshop on Social Network Mining and Analysis, SNA-KDD '09. 2009. 1731015. (Proceedings of the 3rd Workshop on Social Network Mining and Analysis, SNA-KDD '09). https://doi.org/10.1145/1731011.1731015