Topic taxonomy adaptation for group profiling

Lei Tang, Huan Liu, Jianping Zhang, Nitin Agarwal, John J. Salerno

Research output: Contribution to journalArticle

23 Citations (Scopus)

Abstract

A topic taxonomy is an effective representation that describes salient features of virtual groups or online communities. A topic taxonomy consists of topic nodes. Each internal node is defined by its vertical path (i.e., ancestor and child nodes) and its horizonal list of attributes (or terms). In a text-dominant environment, a topic taxonomy can be used to flexibly describe a group's interests with varying granularity. However, the stagnant nature of a taxonomy may fail to timely capture the dynamic change of a group's interest. This article addresses the problem of how to adapt a topic taxonomy to the accumulated data that reflects the change of a group's interest to achieve dynamic group profiling. We first discuss the issues related to topic taxonomy. We next formulate taxonomy adaptation as an optimization problem to find the taxonomy that best fits the data. We then present a viable algorithm that can efficiently accomplish taxonomy adaptation. We conduct extensive experiments to evaluate our approach's efficacy for group profiling, compare the approach with some alternatives, and study its performance for dynamic group profiling. While pointing out various applications of taxonomy adaption, we suggest some future work that can take advantage of burgeoning Web 2.0 services for online targeted marketing, counterterrorism in connecting dots, and community tracking.

Original languageEnglish (US)
Article number15
JournalACM Transactions on Knowledge Discovery from Data
Volume1
Issue number4
DOIs
StatePublished - Jan 1 2008

Fingerprint

Taxonomies
Web services
Marketing

Keywords

  • Dynamic profiling
  • Group interest
  • Taxonomy adjustment
  • Text hierarchical classification
  • Topic taxonomy

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Topic taxonomy adaptation for group profiling. / Tang, Lei; Liu, Huan; Zhang, Jianping; Agarwal, Nitin; Salerno, John J.

In: ACM Transactions on Knowledge Discovery from Data, Vol. 1, No. 4, 15, 01.01.2008.

Research output: Contribution to journalArticle

Tang, Lei ; Liu, Huan ; Zhang, Jianping ; Agarwal, Nitin ; Salerno, John J. / Topic taxonomy adaptation for group profiling. In: ACM Transactions on Knowledge Discovery from Data. 2008 ; Vol. 1, No. 4.
@article{162fec6729da41a494e8fcc4bfd19aaa,
title = "Topic taxonomy adaptation for group profiling",
abstract = "A topic taxonomy is an effective representation that describes salient features of virtual groups or online communities. A topic taxonomy consists of topic nodes. Each internal node is defined by its vertical path (i.e., ancestor and child nodes) and its horizonal list of attributes (or terms). In a text-dominant environment, a topic taxonomy can be used to flexibly describe a group's interests with varying granularity. However, the stagnant nature of a taxonomy may fail to timely capture the dynamic change of a group's interest. This article addresses the problem of how to adapt a topic taxonomy to the accumulated data that reflects the change of a group's interest to achieve dynamic group profiling. We first discuss the issues related to topic taxonomy. We next formulate taxonomy adaptation as an optimization problem to find the taxonomy that best fits the data. We then present a viable algorithm that can efficiently accomplish taxonomy adaptation. We conduct extensive experiments to evaluate our approach's efficacy for group profiling, compare the approach with some alternatives, and study its performance for dynamic group profiling. While pointing out various applications of taxonomy adaption, we suggest some future work that can take advantage of burgeoning Web 2.0 services for online targeted marketing, counterterrorism in connecting dots, and community tracking.",
keywords = "Dynamic profiling, Group interest, Taxonomy adjustment, Text hierarchical classification, Topic taxonomy",
author = "Lei Tang and Huan Liu and Jianping Zhang and Nitin Agarwal and Salerno, {John J.}",
year = "2008",
month = "1",
day = "1",
doi = "10.1145/1324172.1324173",
language = "English (US)",
volume = "1",
journal = "ACM Transactions on Knowledge Discovery from Data",
issn = "1556-4681",
publisher = "Association for Computing Machinery (ACM)",
number = "4",

}

TY - JOUR

T1 - Topic taxonomy adaptation for group profiling

AU - Tang, Lei

AU - Liu, Huan

AU - Zhang, Jianping

AU - Agarwal, Nitin

AU - Salerno, John J.

PY - 2008/1/1

Y1 - 2008/1/1

N2 - A topic taxonomy is an effective representation that describes salient features of virtual groups or online communities. A topic taxonomy consists of topic nodes. Each internal node is defined by its vertical path (i.e., ancestor and child nodes) and its horizonal list of attributes (or terms). In a text-dominant environment, a topic taxonomy can be used to flexibly describe a group's interests with varying granularity. However, the stagnant nature of a taxonomy may fail to timely capture the dynamic change of a group's interest. This article addresses the problem of how to adapt a topic taxonomy to the accumulated data that reflects the change of a group's interest to achieve dynamic group profiling. We first discuss the issues related to topic taxonomy. We next formulate taxonomy adaptation as an optimization problem to find the taxonomy that best fits the data. We then present a viable algorithm that can efficiently accomplish taxonomy adaptation. We conduct extensive experiments to evaluate our approach's efficacy for group profiling, compare the approach with some alternatives, and study its performance for dynamic group profiling. While pointing out various applications of taxonomy adaption, we suggest some future work that can take advantage of burgeoning Web 2.0 services for online targeted marketing, counterterrorism in connecting dots, and community tracking.

AB - A topic taxonomy is an effective representation that describes salient features of virtual groups or online communities. A topic taxonomy consists of topic nodes. Each internal node is defined by its vertical path (i.e., ancestor and child nodes) and its horizonal list of attributes (or terms). In a text-dominant environment, a topic taxonomy can be used to flexibly describe a group's interests with varying granularity. However, the stagnant nature of a taxonomy may fail to timely capture the dynamic change of a group's interest. This article addresses the problem of how to adapt a topic taxonomy to the accumulated data that reflects the change of a group's interest to achieve dynamic group profiling. We first discuss the issues related to topic taxonomy. We next formulate taxonomy adaptation as an optimization problem to find the taxonomy that best fits the data. We then present a viable algorithm that can efficiently accomplish taxonomy adaptation. We conduct extensive experiments to evaluate our approach's efficacy for group profiling, compare the approach with some alternatives, and study its performance for dynamic group profiling. While pointing out various applications of taxonomy adaption, we suggest some future work that can take advantage of burgeoning Web 2.0 services for online targeted marketing, counterterrorism in connecting dots, and community tracking.

KW - Dynamic profiling

KW - Group interest

KW - Taxonomy adjustment

KW - Text hierarchical classification

KW - Topic taxonomy

UR - http://www.scopus.com/inward/record.url?scp=39149100915&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=39149100915&partnerID=8YFLogxK

U2 - 10.1145/1324172.1324173

DO - 10.1145/1324172.1324173

M3 - Article

AN - SCOPUS:39149100915

VL - 1

JO - ACM Transactions on Knowledge Discovery from Data

JF - ACM Transactions on Knowledge Discovery from Data

SN - 1556-4681

IS - 4

M1 - 15

ER -