Muutke küpsiste eelistusi

E-raamat: Network Data Mining And Analysis

(S'pore Management Univ, S'pore), (S'pore Management Univ, S'pore), (East China Normal Univ, China)
Teised raamatud teemal:
  • Formaat - EPUB+DRM
  • Hind: 81,90 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Lisa ostukorvi
  • Lisa soovinimekirja
  • See e-raamat on mõeldud ainult isiklikuks kasutamiseks. E-raamatuid ei saa tagastada.
Teised raamatud teemal:

DRM piirangud

  • Kopeerimine (copy/paste):

    ei ole lubatud

  • Printimine:

    ei ole lubatud

  • Kasutamine:

    Digitaalõiguste kaitse (DRM)
    Kirjastus on väljastanud selle e-raamatu krüpteeritud kujul, mis tähendab, et selle lugemiseks peate installeerima spetsiaalse tarkvara. Samuti peate looma endale  Adobe ID Rohkem infot siin. E-raamatut saab lugeda 1 kasutaja ning alla laadida kuni 6'de seadmesse (kõik autoriseeritud sama Adobe ID-ga).

    Vajalik tarkvara
    Mobiilsetes seadmetes (telefon või tahvelarvuti) lugemiseks peate installeerima selle tasuta rakenduse: PocketBook Reader (iOS / Android)

    PC või Mac seadmes lugemiseks peate installima Adobe Digital Editionsi (Seeon tasuta rakendus spetsiaalselt e-raamatute lugemiseks. Seda ei tohi segamini ajada Adober Reader'iga, mis tõenäoliselt on juba teie arvutisse installeeritud )

    Seda e-raamatut ei saa lugeda Amazon Kindle's. 

Online social networking sites like Facebook, LinkedIn, and Twitter, offer millions of members the opportunity to befriend one another, send messages to each other, and post content on the site — actions which generate mind-boggling amounts of data every day. To make sense of the massive data from these sites, we resort to social media mining to answer questions like the following: What are social communities in bipartite graphs and signed graphs? How robust are the networks? How can we apply the robustness of networks? How can we find identical social users across heterogeneous social networks? Social media shatters the boundaries between the real world and the virtual world. We can now integrate social theories with computational methods to study how individuals interact with each other and how social communities form in bipartite and signed networks. The uniqueness of social media data calls for novel data mining techniques that can effectively handle user generated content with rich social relations. The study and development of these new techniques are under the purview of social media mining, an emerging discipline under the umbrella of data mining. Social Media Mining is the process of representing, analyzing, and extracting actionable patterns from social media data.

East China Normal University Scientific Reports v
Preface vii
About the Authors ix
Acknowledgments xi
1 Introduction to Social Networks
1(4)
1.1 Social Networks
1(2)
1.2 Challenges of Social Network Mining
3(1)
1.3
Chapter Organization
4(1)
2 Network Modeling
5(18)
2.1 The Types of Networks
5(6)
2.1.1 Graph
5(3)
2.1.2 Signed Graph
8(1)
2.1.3 Bipartite Graph
9(2)
2.2 Network Modeling
11(5)
2.2.1 Adjacency Matrix
11(1)
2.2.2 Random Walk
12(1)
2.2.3 Laplacian Matrix
13(1)
2.2.4 Normalized Laplacian Matrix
14(2)
2.3 Topological Structure
16(7)
2.3.1 Balanced Theory
16(1)
2.3.2 Robustness
17(6)
3 R-energy for Evaluating Robustness of Dynamic Networks
23(26)
3.1 Introduction
23(2)
3.2 Related Work
25(2)
3.2.1 Robustness
25(1)
3.2.2 Graph Energy
26(1)
3.3 R-energy
27(4)
3.3.1 2-step Commute Probability
27(3)
3.3.2 R-energy
30(1)
3.4 Computation of R-energy
31(4)
3.4.1 Properties
31(2)
3.4.2 Computation
33(2)
3.5 Robustness of Large Static Networks
35(5)
3.5.1 Experimental Network
35(2)
3.5.2 Efficiency and Scalability of R-energy
37(1)
3.5.3 Impact of Vertex Removal to R-energy
38(2)
3.6 Detecting Events and Trends Using Robustness
40(7)
3.6.1 Data Collection
40(1)
3.6.2 Event Detection
41(3)
3.6.3 Periodic Trend Pattern Detection
44(3)
3.7 Conclusion
47(2)
4 Network Linkage Across Heterogeneous Networks
49(30)
4.1 Introduction
49(2)
4.1.1 Challenges
50(1)
4.1.2 Objectives and Contributions
50(1)
4.2 Related Work
51(2)
4.2.1 Network Linkage Across Social Platforms
51(2)
4.2.2 Record Linkage
53(1)
4.3 Problem Definition
53(1)
4.4 Solution Overview
54(4)
4.4.1 Framework
54(3)
4.4.2 Running Example
57(1)
4.5 Linkage Algorithm
58(10)
4.5.1 User Attribute and Social Similarity
58(4)
4.5.2 Parameter Learning and Matching Score Computation
62(4)
4.5.3 Scale-up CNL
66(2)
4.6 Experiments
68(10)
4.6.1 Dataset and Settings
68(2)
4.6.2 User Self-linkage Evaluation
70(4)
4.6.3 Heterogeneous User Linkage Evaluation
74(4)
4.7 Conclusion
78(1)
5 Quasi-biclique Detection from Bipartite Graphs
79(34)
5.1 Introduction
79(1)
5.2 Related Work
80(2)
5.3 Problem Definition
82(5)
5.3.1 Basic Concepts
82(3)
5.3.2 MQBCD
85(2)
5.4 Pruning Rules
87(12)
5.4.1 Input Graph Pruning
87(1)
5.4.2 Induced Graph Pruning
88(8)
5.4.3 Combined Pruning Rules for an Induced Graph
96(2)
5.4.4 Complexity Analysis
98(1)
5.5 Enumeration of Maximal Quasi-biclique Communities
99(6)
5.5.1 Enumeration Tree
99(2)
5.5.2 Enumerating Vertex Set
101(1)
5.5.3 Enumerating all QBCs of a Candidate Graph
102(2)
5.5.4 Verifying QBC
104(1)
5.5.5 Complexity Analysis
105(1)
5.6 MQBCD Algorithm
105(2)
5.6.1 Outline of the Algorithm
106(1)
5.7 Experiments
107(5)
5.7.1 Datasets and Settings
107(1)
5.7.2 Performance Results of MQBCD
108(2)
5.7.3 Comparison with Baseline
110(1)
5.7.4 Case Study
111(1)
5.8 Conclusion
112(1)
6 On Detecting Antagonistic Community Detection from Signed Graphs
113(52)
6.1 Introduction
113(6)
6.1.1 Motivation
113(4)
6.1.2 Research Objectives
117(2)
6.2 Related Work
119(1)
6.3 Problem Definition
120(3)
6.3.1 Related Concepts
120(2)
6.3.2 MASCOT
122(1)
6.4 Pruning Rules
123(10)
6.4.1 Input Graph Pruning
124(1)
6.4.2 Induced Graph Pruning
125(5)
6.4.3 Combined Pruning Rules for an Induced Graph
130(2)
6.4.4 Complexity Analysis
132(1)
6.5 Enumeration Stage
133(5)
6.5.1 Enumeration Tree
133(2)
6.5.2 Enumerating All QACs of a Candidate Graph
135(2)
6.5.3 Verifying QAC
137(1)
6.5.4 Complexity Analysis
138(1)
6.6 MASCOT Algorithm
138(4)
6.6.1 Outline of Algorithm
138(3)
6.6.2 Variants of MASCOT
141(1)
6.7 Experiments on Synthetic Graph
142(12)
6.7.1 Graph Generation
142(4)
6.7.2 Performance Results
146(8)
6.8 Experiments on Real Networks
154(8)
6.8.1 Description of Datasets
154(1)
6.8.2 Performance Results
155(4)
6.8.3 Example Cases
159(1)
6.8.4 Predicting Polarity of Links
160(2)
6.8.5 Discussion: Coverage and Applicability
162(1)
6.9 Conclusion
162(3)
7 Summary
165(4)
7.1 Conclusions
165(1)
7.2 Discussion of Future Directions
166(3)
Bibliography 169(8)
Index 177