Prediction of social bookmarking based on a behavior transition model

Tadanobu Furukawa, Seishi Okamoto, Yutaka Matsuo, Mitsuru Ishizuka

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

1 Citation (Scopus)

Abstract

We propose an algorithm to predict users' future bookmarking using social bookmarking data. It is a problem that primitive collaborative filtering cannot exactly catch users' preferences in social bookmarkings containing enormous items (URLs) because in many cases user's adoption data is sparse. There can be various influences on bookmarking such as effects from the environment and changes in user preference. We use temporal sequence among the bookmarking-users to represent word-of-mouth and among the bookmarked-URLs to represent user's interest, and model each sequential order as a continuous-time Markov chain. This idea comes from diffusion of innovation theory. A transition probability from a state (user/URL) to another state is defined by the transition rate calculated from the time taken for the transition. We predicted user's preferences through a combination of estimating the most likely transition between users using URLs as input and between URLs using users as input. We conducted evaluation experiments with a social bookmarking service in Japan called Hatena bookmark. The proposed algorithm predicts users' preferences with higher accuracy than collaborative filtering or simple transition models based on either user or URL.

Original languageEnglish
Title of host publicationProceedings of the ACM Symposium on Applied Computing
Pages1741-1747
Number of pages7
DOIs
Publication statusPublished - 2010
Externally publishedYes
Event25th Annual ACM Symposium on Applied Computing, SAC 2010 - Sierre
Duration: 2010 Mar 222010 Mar 26

Other

Other25th Annual ACM Symposium on Applied Computing, SAC 2010
CitySierre
Period10/3/2210/3/26

Fingerprint

Websites
Collaborative filtering
Markov processes
Innovation
Experiments

Keywords

  • collaborative filtering
  • information flow
  • Markov chain
  • recommender system
  • social tagging

ASJC Scopus subject areas

  • Software

Cite this

Furukawa, T., Okamoto, S., Matsuo, Y., & Ishizuka, M. (2010). Prediction of social bookmarking based on a behavior transition model. In Proceedings of the ACM Symposium on Applied Computing (pp. 1741-1747) https://doi.org/10.1145/1774088.1774460

Prediction of social bookmarking based on a behavior transition model. / Furukawa, Tadanobu; Okamoto, Seishi; Matsuo, Yutaka; Ishizuka, Mitsuru.

Proceedings of the ACM Symposium on Applied Computing. 2010. p. 1741-1747.

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

Furukawa, T, Okamoto, S, Matsuo, Y & Ishizuka, M 2010, Prediction of social bookmarking based on a behavior transition model. in Proceedings of the ACM Symposium on Applied Computing. pp. 1741-1747, 25th Annual ACM Symposium on Applied Computing, SAC 2010, Sierre, 10/3/22. https://doi.org/10.1145/1774088.1774460
Furukawa T, Okamoto S, Matsuo Y, Ishizuka M. Prediction of social bookmarking based on a behavior transition model. In Proceedings of the ACM Symposium on Applied Computing. 2010. p. 1741-1747 https://doi.org/10.1145/1774088.1774460
Furukawa, Tadanobu ; Okamoto, Seishi ; Matsuo, Yutaka ; Ishizuka, Mitsuru. / Prediction of social bookmarking based on a behavior transition model. Proceedings of the ACM Symposium on Applied Computing. 2010. pp. 1741-1747
@inproceedings{a73f88d137d340d997ea7a7fda5eb69b,
title = "Prediction of social bookmarking based on a behavior transition model",
abstract = "We propose an algorithm to predict users' future bookmarking using social bookmarking data. It is a problem that primitive collaborative filtering cannot exactly catch users' preferences in social bookmarkings containing enormous items (URLs) because in many cases user's adoption data is sparse. There can be various influences on bookmarking such as effects from the environment and changes in user preference. We use temporal sequence among the bookmarking-users to represent word-of-mouth and among the bookmarked-URLs to represent user's interest, and model each sequential order as a continuous-time Markov chain. This idea comes from diffusion of innovation theory. A transition probability from a state (user/URL) to another state is defined by the transition rate calculated from the time taken for the transition. We predicted user's preferences through a combination of estimating the most likely transition between users using URLs as input and between URLs using users as input. We conducted evaluation experiments with a social bookmarking service in Japan called Hatena bookmark. The proposed algorithm predicts users' preferences with higher accuracy than collaborative filtering or simple transition models based on either user or URL.",
keywords = "collaborative filtering, information flow, Markov chain, recommender system, social tagging",
author = "Tadanobu Furukawa and Seishi Okamoto and Yutaka Matsuo and Mitsuru Ishizuka",
year = "2010",
doi = "10.1145/1774088.1774460",
language = "English",
isbn = "9781605586380",
pages = "1741--1747",
booktitle = "Proceedings of the ACM Symposium on Applied Computing",

}

TY - GEN

T1 - Prediction of social bookmarking based on a behavior transition model

AU - Furukawa, Tadanobu

AU - Okamoto, Seishi

AU - Matsuo, Yutaka

AU - Ishizuka, Mitsuru

PY - 2010

Y1 - 2010

N2 - We propose an algorithm to predict users' future bookmarking using social bookmarking data. It is a problem that primitive collaborative filtering cannot exactly catch users' preferences in social bookmarkings containing enormous items (URLs) because in many cases user's adoption data is sparse. There can be various influences on bookmarking such as effects from the environment and changes in user preference. We use temporal sequence among the bookmarking-users to represent word-of-mouth and among the bookmarked-URLs to represent user's interest, and model each sequential order as a continuous-time Markov chain. This idea comes from diffusion of innovation theory. A transition probability from a state (user/URL) to another state is defined by the transition rate calculated from the time taken for the transition. We predicted user's preferences through a combination of estimating the most likely transition between users using URLs as input and between URLs using users as input. We conducted evaluation experiments with a social bookmarking service in Japan called Hatena bookmark. The proposed algorithm predicts users' preferences with higher accuracy than collaborative filtering or simple transition models based on either user or URL.

AB - We propose an algorithm to predict users' future bookmarking using social bookmarking data. It is a problem that primitive collaborative filtering cannot exactly catch users' preferences in social bookmarkings containing enormous items (URLs) because in many cases user's adoption data is sparse. There can be various influences on bookmarking such as effects from the environment and changes in user preference. We use temporal sequence among the bookmarking-users to represent word-of-mouth and among the bookmarked-URLs to represent user's interest, and model each sequential order as a continuous-time Markov chain. This idea comes from diffusion of innovation theory. A transition probability from a state (user/URL) to another state is defined by the transition rate calculated from the time taken for the transition. We predicted user's preferences through a combination of estimating the most likely transition between users using URLs as input and between URLs using users as input. We conducted evaluation experiments with a social bookmarking service in Japan called Hatena bookmark. The proposed algorithm predicts users' preferences with higher accuracy than collaborative filtering or simple transition models based on either user or URL.

KW - collaborative filtering

KW - information flow

KW - Markov chain

KW - recommender system

KW - social tagging

UR - http://www.scopus.com/inward/record.url?scp=77954698284&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77954698284&partnerID=8YFLogxK

U2 - 10.1145/1774088.1774460

DO - 10.1145/1774088.1774460

M3 - Conference contribution

AN - SCOPUS:77954698284

SN - 9781605586380

SP - 1741

EP - 1747

BT - Proceedings of the ACM Symposium on Applied Computing

ER -