A Dynamic and Task-Oriented Social Network Extraction System Based on Analyzing Personal Social Data

(1)

1

A Dynamic and Task-Oriented Social

Network Extraction System Based on

Analyzing Personal Social Data

Kai-Yu Wang1_{, I-Hsien Ting}2_{, Hui-Ju Wu}2_{, Pei-Shan Chang}2 1_{Department of Marketing, International Business and Strategy}

Brock University, Canada

2_{Department of Information Management}

National University of Kaohsiung, Taiwan

iting@nuk.edu.tw

(2)

2

Outline

 1. Introduction

 2. Literature Review

 Social Networks Analysis  Social Networks Extraction

 Web Mining Techniques for Social Networking

 3. The System Architecture

 4. The Data Collection System and Extraction engine

 5. System Implementation

 6. Conclusion and Future Research

(3)

Introduction (1/3)

Communication and Social Activities in the

Internet

E-mail, Instant Messenger (MSN), Blog, etc.

Large amount of Communication data

Valuable data to understand the social

structure

Useful techniques to analyze the social data

Data Mining, Visualization……

(4)

Introduction (2/3)

How to collect, pre-process, organize and for

social network extraction and for decision

support?

In this paper

An system architecture will be proposed

Some detail about how to process e-mail and

Instant Messenger data

Social Network Extraction

(5)

Introduction (3/3)

 A system architecture will be proposed and implemented in this paper

– E-mail and Instant Messenger history can be uploaded to the system

– User can input keyword for a particular task

– Network for the task will be generated dynamically

 The system can also be used as a very useful decision support system

(6)

Literature Review (1/3)

 Social Network Analysis

 To understand the relationship between “Actors”

• each actor is presented as a node and each pair of nodes can be connected by lines to show the relationships

 Three important elements

• actors, ties, and relationships

 The most important measurements of SNA include

• network size, diameter, density, centrality and structure holes (Scott, 2000)

(7)

Literature Review (2/3)

 Social Network Extraction

 Bird et al. propose a method to extract social networks from e-mail communications

 Agrawal et. al using web mining techniques to understand the behavior of users in newsgroup

 Jin et al. and Matsuo et al. developed systems and tried to extract social networks from the web

 Furukawa et al. were trying to identify social networks from blogspace

 Most of the researches that discussed above are

focusing on a single source for social network

(8)

8

E-mail Instant Messenger

Data Preprocessing &

Extraction Engine

Database

Ontologybase

Social Network Analysis Engine

Social Network Visualization Engine

User Input _{Visualized Social Network}

(9)

The Data Collection System (1/3)

9

Return-path: <eri@xx.xx.xx.xx> Envelope-to: RSs@xx.xxxx.xx.xx

Received: from funnelweb.cs.york.ac.uk ([144.32.161.232] Message-ID: <47552CF4.70806@xx.xxx.xx.xx>

Date: Tue, 04 Dec 2007 10:33:24 +0000 From: E Rid <eri@xx.xxx.xx.xx>

Reply-To: eri@xx.xx.xx.xx

User-Agent: Thunderbird 2.0.0.9 (Windows/20071031) MIME-Version: 1.0

To: RSs@xx.xxx.xx.xx

Subject: java versus C benchmarks

Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit

Status: RO

A Sample E-mail Format

The system is a web-based system, and it allows the user to upload email file (in *.eml or text format), MSN history data (in *.xml format) and client side logging data (in *.log or text format).

(10)

The Data Collection System (2/3)

10

(11)

The Data Collection System (3/3)

11

<?xml version="1.0"?>

<?xml-stylesheet type='text/xsl' href='MessageLog.xsl'?> <Log FirstSessionID="1" LastSessionID="12">

<From><User FriendlyName="Want SAP, Netweaver, J2EE consultant"/></From> <To><User FriendlyName="Derrick-"/></To><Text Style="font-family:;

color:#000000; "> ok...I got it...

</Text> </Message> </Log>

(12)

The Data Extraction System (1/6)

From the email file, some necessary fields will

be extracted, including

“deliver-to”, “receive-id”, “date”, “to”, “from”,

“subject”, “msg-id”, “priority”, “reply-to”, “mailer

(agent)”, “encode”. “content-type”, “content”, “cc”

MSN history file. The fields will be extracted

including

from”, to”, content”,

datetime”, id”, sessionid”,

(13)

The Data Extraction System (2/6)

13

(14)

The Data Extraction System (3/6)

From Social Data to Social Networking

How to measure the relationship

Relationship from Email

14



R

_i





W

₁



E

_i



W

₂



M

_i



W

₃



B

_i





(15)

The Data Extraction System (4/6)

 Relationship from MSN

 Relationship from Blog

15



M

_i



W

₁



M

_send



W

₂



M

_receive



W

₃



M

_multi



M_iW₁M_{se nd}W₂M_{r e c e i v e}W₃M_{mul t i}W₄M_{i nt e r ac t i on}



B

_i



W

₁



B

_{b ro wsin g}



W

₂



B

_{b o o k ma rk in g}



W

₃



B

_{in tera ctio n}



(16)

System Implementation(1/6)

16

(17)

System Implementation(2/6)

17

(18)

System Implementation(2/6)

18

(19)

System Implementation(2/6)

19

(20)

System Implementation(2/6)

20

(21)

Conclusion

 Social and communication data are very common data in our daily life

 Useful for making decision

 An system architecture has been proposed

 Data collection, processing, social network extraction and visualization

 Future research  Ontology base

 Including data mining techniques

 Measurement the performance of the system

(22)

22

Thank You!

Any Questions?

I-Hsien Ting

Department of Information Management National University of Kaohsiung, Taiwan

iting@nuk.edu.tw