Kaya / Alhajj Influence and Behavior Analysis in Social Networks and Social Media

1. Auflage 2018
ISBN: 978-3-030-02592-2
Verlag: Springer International Publishing
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, 235 Seiten

Reihe: Lecture Notes in Social Networks

This timely book focuses on influence and behavior analysis in the broader context of social network applications and social media.  Twitter accounts of telecommunications companies are analyzed.  Rumor sources in finite graphs with boundary effects by message-passing algorithms are identified.

The coherent, state-of-the-art collection of chapters was initially selected based on solid reviews from the IEEE/ACM International Conference on Advances in Social Networks, Analysis, and Mining (ASONAM '17). Chapters were then improved and extended substantially, and the final versions were rigorously reviewed and revised to meet the series standards. Original chapters coming from outside of the meeting round out the coverage. The result will appeal to researchers and students working in social network and social media analysis.

Autoren/Hrsg.

Kaya, Mehmet

Alhajj, Reda

Inhaltsverzeichnis

1;Contents;6
2;Social Network to Improve the Educational Experience with the Deployment of Different Learning Models;8
2.1;1 Introduction;8
2.2;2 Social Networks in Education;10
2.2.1;2.1 Facebook;11
2.2.2;2.2 Twitter;12
2.2.3;2.3 YouTube;13
2.3;3 SLNs: Sporadic Learning Networks;14
2.4;4 OPPIA Platform;18
2.4.1;4.1 Layer Model;18
2.4.2;4.2 OPPIA Architecture;21
2.4.3;4.3 OPPIA Operation;24
2.5;5 OPPIA Implementation;27
2.6;6 Conclusions and Future Work;29
2.7;References;30
3;Temporal Model of the Online Customer Review Helpfulness Prediction with Regression Methods;33
3.1;1 Introduction;33
3.2;2 Related Works;34
3.2.1;2.1 Linear Regression;35
3.2.2;2.2 The Coefficient of Determination;36
3.2.3;2.3 The Akaike Information Criterion;36
3.3;3 Method;36
3.3.1;3.1 Corpus Collection;37
3.3.2;3.2 Morphological Preprocessing;37
3.3.3;3.3 Feature Set;38
3.3.4;3.4 Sentiment Feature Selection;38
3.3.5;3.5 Evaluation Index;39
3.4;4 Experiments;39
3.4.1;4.1 Authors and Affiliations of Chinese Customer Review Corpus;40
3.4.2;4.2 Experimental Tools;40
3.4.3;4.3 Experimental Results;40
3.4.4;4.4 Discussion;42
3.5;5 Conclusion and Future Works;43
3.6;References;44
4;Traits of Leaders in Movement Initiation: Classification and Identification;45
4.1;1 Introduction;45
4.2;2 The Proposed Approach;46
4.2.1;2.1 Bidirectional Agreement in Multi-Agent Systems;47
4.2.2;2.2 Bidirectional Agreement Condition;47
4.2.3;2.3 Leaders as State Changers;48
4.2.4;2.4 Approach Overview;49
4.2.5;2.5 FLICA;49
4.2.6;2.6 Leadership Trait Characterization Scheme;51
4.3;3 Experimental Setup;55
4.3.1;3.1 Trait of Leadership Model;55
4.3.2;3.2 Datasets;56
4.3.3;3.3 Sensitivity Analysis in Model Classification;57
4.3.4;3.4 Hypotheses Tests;57
4.3.5;3.5 Parameter Setting;58
4.4;4 Results;58
4.4.1;4.1 Traits of Leader Classification: Sensitivity Analysis;58
4.4.2;4.2 Trait Identification of Baboon Movement;60
4.4.3;4.3 Trait Identification of Fish Movement;63
4.4.4;4.4 Traits of Leaders as Measure of Degree of Hierarchy Structure;65
4.5;5 Conclusions;66
4.6;References;67
5;Emotional Valence Shifts and User Behavior on Twitter, Facebook, and YouTube;69
5.1;1 Introduction;69
5.2;2 Related Work;70
5.3;3 Data Analysis Procedure;72
5.3.1;3.1 Data Extraction;72
5.3.2;3.2 Data Preprocessing;74
5.3.3;3.3 Emotion Extraction;74
5.3.4;3.4 Data Analysis and Research Questions;75
5.4;4 Results;76
5.4.1;4.1 Emotion Intensity During Positive, Negative, and Polarizing Events;76
5.4.2;4.2 User Behavior;81
5.5;5 Discussion;85
5.6;6 Conclusion;86
5.7;References;87
6;Diffusion Algorithms in Multimedia Social Networks: A Novel Model;90
6.1;1 Introduction;90
6.2;2 Related Works;92
6.3;3 The Data Model;94
6.3.1;3.1 Definitions;94
6.3.2;3.2 Hypergraph Building and Computation;97
6.4;4 Influence Diffusion and Maximization in OSNs;98
6.5;5 Experimental Results;99
6.6;6 Conclusion and Discussions;104
6.7;References;106
7;Detecting Canadian Internet Satisfaction by Analyzing Twitter Accounts of Shaw Communications;109
7.1;1 Introduction;109
7.1.1;1.1 Problem Definition;110
7.1.2;1.2 Motivation;110
7.1.3;1.3 Summary;111
7.2;2 Related Work;111
7.2.1;2.1 Internet Issues;111
7.2.2;2.2 Sentiment Analysis;112
7.2.3;2.3 Consumer Satisfaction;113
7.3;3 Methodology;115
7.3.1;3.1 Internet Issues;115
7.3.1.1;Reported Outages;115
7.3.1.2;Common Internet Issues;116
7.3.1.3;Average Sentiment on Outage Days;116
7.3.1.4;Locations;117
7.3.2;3.2 Consumer Satisfaction;118
7.3.2.1;Sentiment;118
7.3.2.2;Word Usage;119
7.3.2.3;Hashtags;119
7.3.2.4;Response Time;119
7.4;4 Results;120
7.4.1;4.1 Internet Issues;120
7.4.1.1;Reported Outages;120
7.4.1.2;Common Internet Issues;121
7.4.1.3;Average Sentiment on Outage Days;121
7.4.1.4;Locations;122
7.4.2;4.2 Consumer Satisfaction;123
7.4.2.1;Sentiment;123
7.4.2.2;Word Usage;127
7.4.2.3;Hashtags;128
7.4.2.4;Response Time;128
7.5;5 Conclusions and Future Work;129
7.6;References;130
8;Editing Behavior Analysis for Predicting Active and Inactive Users in Wikipedia;131
8.1;1 Introduction;131
8.2;2 Related Work;133
8.3;3 Dataset;135
8.4;4 Differences in Editing Behavior;136
8.5;5 Predicting Active and Inactive Users;138
8.5.1;5.1 Most Important Features;139
8.6;6 Experimental Results;142
8.6.1;6.1 Comparison with Related Work;143
8.6.2;6.2 Early Prediction of Inactive Users;144
8.6.3;6.3 Varying the Threshold ?;145
8.7;7 Conclusions;149
8.8;References;149
9;Incentivized Social Sharing: Characteristics and Optimization;152
9.1;1 Introduction;152
9.2;2 Incentivized Sharing: A Motivating Example and Evaluation Framework;154
9.3;3 Notation and Problem Statement;157
9.4;4 Theoretical Analysis;158
9.5;5 Characteristics of the Me+3 Incentive;160
9.5.1;5.1 Incentivized Sharing Degree Distribution;161
9.5.2;5.2 Social Pressure and Adoption;162
9.5.3;5.3 Purchase Probabilities and Free Deals;164
9.5.4;5.4 Shares and Recipient Purchase References;165
9.5.5;5.5 Impact of the Incentive Amount;167
9.5.6;5.6 Arrivals and Awakening;168
9.6;6 Me+N: A Model for Incentivized Sharing Optimization;169
9.6.1;6.1 Arrival and Awakening Functions;170
9.6.2;6.2 Creating a Me+N Sharing Distribution;171
9.6.3;6.3 Generated Purchase Probabilities;172
9.6.4;6.4 Cost of Sharing Incentives;173
9.7;7 Experiments;173
9.8;8 Related Work;174
9.9;9 Conclusions;176
9.10;References;176
10;Rumor Source Detection in Finite Graphs with Boundary Effects by Message-Passing Algorithms;178
10.1;1 Introduction;178
10.1.1;1.1 Our Contributions;179
10.2;2 Preliminaries of Rumor Centrality;179
10.3;3 Trees with a Single End Vertex;181
10.3.1;3.1 Impact of Boundary Effects on P(Gn "026A30C v);181
10.3.2;3.2 Analytical Characterization of Likelihood Function;183
10.3.3;3.3 Optimality Characterization of Likelihood Estimate;185
10.3.4;3.4 Likelihood Ratio Between Centroid and End Vertex on Different Network Topology;186
10.4;4 Trees with Multiple End Vertices;188
10.4.1;4.1 Degree-Regular Tree (d?3) Special Case: Gn is Broom-Shaped;188
10.4.2;4.2 Message-Passing Algorithm;190
10.4.3;4.3 Simulation Results for Finite d-Regular Tree Networks;192
10.4.4;4.4 Simulation Results for Finite General Tree Networks;193
10.5;5 Conclusion;194
10.6;References;194
11;Robustness of Influence Maximization Against Non-adversarial Perturbations;196
11.1;1 Introduction;196
11.2;2 Related Work;199
11.3;3 Preliminaries and Problem Formulation;200
11.4;4 Methodology;201
11.4.1;4.1 Networks;201
11.4.2;4.2 Influence Spread Probability and Types of Perturbations;201
11.4.3;4.3 Influence Maximization Algorithms;203
11.5;5 Results;204
11.5.1;5.1 Overlap of Seed Nodes;204
11.5.2;5.2 Influence Spread;205
11.5.3;5.3 Relation Between Amount of Error and Effectiveness of Algorithm;207
11.6;6 Discussion;210
11.6.1;6.1 Implication;210
11.6.2;6.2 Limitations;211
11.7;7 Conclusion;211
11.8;References;211
12;Analyzing Social Book Reading Behavior on Goodreads and How It Predicts Amazon Best Sellers;214
12.1;1 Introduction;214
12.2;2 Related Works;217
12.3;3 Dataset Preparation;219
12.4;4 Characteristic Behavior;220
12.4.1;4.1 Book Ratings and Reviews;220
12.4.2;4.2 Book Genres and Book Shelves;221
12.4.3;4.3 Goodreads Users' Status Posts;223
12.4.4;4.4 Author Characteristics;225
12.5;5 Will a Book Become an Amazon Best Seller?;226
12.5.1;5.1 Performance of the Prediction Model;228
12.5.2;5.2 Discriminative Power of the Features;229
12.6;6 Close Competitors;230
12.6.1;6.1 Comparisons;231
12.7;7 Conclusions and Future Works;235
12.8;References;235