Probabilistic approaches for social media analysis : data, community and influence / Kun Yue, Jin Li, Hao Wu, Weiyi Liu, Zidu Yin, Yunnan University, China.

Format:

Book

Author/Creator:

Yue, Kun, author.

Series:

East China Normal University scientific reports ; vol. 11.

East China Normal University scientific reports, 2382-5715 ; vol. 11

Language:

English

Subjects (All):

Social media--Data processing.

Social media.

Text processing (Computer science).

Quantitative research--Statistical methods.

Quantitative research.

Machine learning.

Content analysis (Communication)--Data processing.

Content analysis (Communication).

Statistics.

Physical Description:

xxii, 265 pages : illustrations ; 23 cm.

Place of Publication:

New Jersey : World Scientific, [2020]

Summary:

"This unique compendium focuses on the acquisition and analysis of social media data. The approaches concern both the data-intensive characteristics and graphical structures of social media. The book addresses the critical problems in social media analysis, which representatively cover its lifecycle. The must-have volume is an excellent reference text for professionals, researchers, academics and graduate students in AI and databases"-- Provided by publisher.

Contents:

1.2 Challenges and Basic Ideas p. 3

1.2.1 Acquisition of social media data from OBGs p. 3

1.2.2 Incremental learning of probabilistic graphical models p. 3

1.2.3 Discovering user similarities in social behavioral interactions p. 5

1.2.4 Associative categorization of frequent patterns in social media p. 6

1.2.5 Latent link analysis and community detection from social media p. 6

1.2.6 Probabilistic inferences of latent entity associations p. 7

1.2.7 Containment of influence spread on social networks p. 8

2 Adaptive and Parallel Acquisition of Social Media Data from Online Big Graphs p. 11

2.1 Motivation and Basic Idea p. 11

2.3 Adaptive Data Collection Based on QMC Sampling p. 16

2.3.1 Basic idea and algorithm p. 16

2.4 Updating Sampling Results by Incremental Maintenance p. 23

2.4.1 Overview of incremental maintenance p. 23

2.4.2 Entropy-based data updating p. 24

2.5.1 Experiment setup p. 26

2.5.2 Effectiveness p. 27

2.5.3 Efficiency p. 30

3 A Bayesian Network-Based Approach for Incremental Learning of Uncertain Knowledge p. 39

3.1 Motivation and Basic Idea p. 39

3.1.2 Ideas and contributions p. 41

3.3 Influence Degree of BN Nodes p. 46

3.4 Incremental Learning of BNs p. 50

3.4.1 Markov equivalence and its properties p. 50

3.4.2 A scoring-based algorithm for BN's incremental learning p. 54

3.5.1 Correctness of influence degree p. 59

3.5.2 Effectiveness of revised BNs p. 62

3.5.3 Efficiency of incremental learning p. 63

4 Discovering User Similarities in Social Behavioral Interactions Based on Bayesian Network p. 71

4.1 Motivation and Basic Idea p. 71

4.3 Bayesian Network Based Measurement of User Similarities p. 78

4.3.1 Definitions and problem statement p. 78

4.3.2 Constructing user Bayesian network based on MapReduce p. 80

4.4 Deriving Indirect Similarity by Probabilistic Inferences p. 84

4.4.1 Graphical structure-based indirect similarities p. 85

4.4.2 Probabilistic inference-based indirect similarities p. 87

4.4.3 Combining structure-based and inference-based indirect similarities p. 89

4.5.1 Experiment setup p. 92

4.5.2 Efficiency of UBN construction and inferences p. 93

4.5.3 Effectiveness of UBN and its inferences p. 100

4.5.4 Effectiveness of UBN-based user similarity p. 101

5 Associative Categorization of Frequent Patterns in Social Media Based on Markov Network p. 109

5.1 Motivation and Basic Idea p. 109

5.2 Constructing Item-Association Markov Network from Behavioral Interactions in Social Media p. 114

5.3 IAMN-Based Hierarchical Categorization p. 122

5.4.1 Experiment setup p. 127

5.4.2 Efficiency of IAMN construction p. 128

5.4.3 Effectiveness of IAMN p. 131

5.4.4 Effectiveness of associative categorization p. 132

5.5 Empirical Study on Hierarchical Categorization of Microblog Users p. 135

5.5.1 Basic idea p. 135

5.5.2 Graph model of microblog users p. 137

5.5.3 Hierarchical categorization of microblog users p. 141

5.5.4 Performance studies p. 144

6 Markov Network Based Latent Link Discovery and Community Detection in Social Behavioral Interactions p. 153

6.1 Motivation and Basic Idea p. 153

6.3 Community Detection from IAMN-based Latent Links p. 160

6.3.2 Algorithm for community detection p. 162

6.3.3 Community combination p. 165

6.4.1 Experiment setup p. 168

6.4.2 Effectiveness p. 168

6.4.3 Efficiency p. 175

7 Probabilistic Inferences of Latent Entity Associations in Textual Web Contents p. 179

7.1 Motivation and Basic Idea p. 179

7.3 Definitions and Problem Formalization p. 183

7.4 Generating Samples of EABN Nodes p. 184

7.5 Learning an EABN and Ranking EAs p. 186

7.5.1 BIC metric and division of TWC dataset p. 186

7.5.2 Scoring-based construction of EABN p. 190

7.5.3 Ranking EAs by probabilistic inferences of EABN p. 193

7.6.1 Experiment setup p. 195

7.6.2 Effectiveness p. 196

7.6.3 Efficiency p. 199

8 Containment of Competitive Influence Spread on Social Networks p. 205

8.1 Motivation and Basic Idea p. 205

8.3 Diffusion-Containment Model p. 211

8.3.1 Graph model p. 211

8.3.2 Interaction strategy p. 212

8.3.3 D-State probability and C-State probability p. 213

8.3.4 Influence propagation rules p. 215

8.4 Propagation of Vertex Activation Probabilities p. 216

8.5 Finding C-Seeds for D-Influence Minimization p. 219

8.6.1 Experiment setup p. 224

8.6.2 Feasibility p. 225

8.6.3 Functionality and relationship of relevant parameters p. 230

9 Locating Sources in Online Social Networks via Random Walk p. 235

9.1 Motivation and Basic Idea p. 235

9.3 Influence Propagation Model and Source Location Problem p. 239

9.3.1 Influence propagation model p. 239

9.3.2 Source location problem p. 240

9.4 Bayes Backtracking Model p. 241

9.5 Random Walk Based Sources Location p. 244

9.6.1 Experiment setup p. 247

9.6.2 Performance studies p. 248.

Notes:

Includes bibliographical references and index.

ISBN:

9780000987709

0000987700

9789811207372

9811207372

OCLC:

1137194365