A Database Approach to Group Preference Problems in Social Networks and Geo-Rich Applications (eBook)

Florian Wenzel (Autor)

eBook Download: PDF

2016 | 1. Auflage
194 Seiten
Books on Demand (Verlag)
978-3-7412-1191-1 (ISBN)

Infos

Smart Data is the new trend following the Big Data hype. The focus shifts from pure mass towards quality of data and the added value that data analysis can provide. To this end, Location-Based Social Networks (LBSN) are emerging as new area of application due to a vast amount of available personal information and the predominant demand for personalized user recommendations. In this social environment, personalization is extended from individual users to groups of users. Application scenarios include the recommendation of items to a group of users, recommending one user to another, or forming groups of users via recommendation of users to groups. As a work of applied computer science, the goal of this thesis is to systematically establish solutions for group preference problems of mentioned application scenarios. Technical challenges are met by following a database approach which is scalable to LBSN datasets of Big Data magnitude and allows for a fast computation of recommendation results. Semantic aspects are met by application of Preference SQL as database-driven preference framework which facilitates data-adaptive recommendations. By this design, user models can be formulated and evaluated on social network data and recommendations can be easily integrated into existing system architectures. The development of individual solutions requires extensions of Preference SQL towards geo-social domains and group preferences. For item-to-group recommendations, novel means for the individual statement of preferences as well as the formation of group preferences become of importance. Applications in user-to-user recommendation require data aggregation from different user profiles and subsequent preference analytics for the generation of extended implicit preferences. In addition, the definition of data-adaptive similarity measures based on social and psychological aspects of real-life interactions is a major factor. These concepts are leveraged for user-to-group scenarios to implement effective strategies for problem instances of large user sets. In the course of solving these practical application problems, superior theoretical questions emerged, such as heuristic algorithms for hyper-exponential solution spaces, that are also addressed by this work. The validity of proposed solutions is verified by demo applications and the implementation of semantic benchmarks.

Florian Wenzel was born in Bayreuth (Germany) in 1983. From 2003 to 2009 he studied Computer Science at the University of Würzburg, Germany and UT Austin, TX, USA Since 2009 he works as a researcher at the Chair for Databases and Information Systems at the University of Augsburg, Germany. His research topics include preferences in Location-Based Social Networks, graph databases, and mobile applications as well as group preference problems and recommendations. In 2015 he received his doctor's degree for the thesis presented in this book.

Inhalt

Title Page 5
Copyright 6
Dedication 7
Table of Contents 9
Abstract 13
Acknowledgment 14
1 Introduction 15
1.1 Motivation 15
1.2 Contribution and Organization 18
2 Preference Overview 21
2.1 Basic Structures for Preference Modeling 22
2.2 Preferences in Economics 25
2.3 Preferences in Psychology 25
2.4 Preferences in Artificial Intelligence 27
2.5 Preferences in Database Systems 30
3 Preference SQL Background 33
3.1 Preference Algebra 34
3.2 Preference Constructors 36
3.2.1 Base Preferences 36
3.2.2 Complex Preferences 41
3.3 Domain-Specific Extensions 44
3.3.1 Spatial Preferences 45
3.3.2 Social Preferences 47
3.4 Group Preferences 57
3.5 Preference Query Evaluation 58
3.5.1 The BMO Query Model 59
3.5.2 Data-Adaptivity 59
3.6 The Preference SQL System 63
4 Group Recommendations 67
4.1 Area of Application 68
4.2 A Demo Application for Group Recommendations 70
4.3 Use Cases 74
4.4 Semantic Evaluation 76
4.5 Related Work 79
4.5.1 Decision Support Systems 80
4.5.2 Computational Social Choice 81
4.5.3 Spatial and Location-Dependent Skylines 82
4.5.4 Recommender Systems 83
5 User-to-User Recommendation in LBSN 87
5.1 Area of Application 88
5.2 Aggregation of Social Network Profiles 90
5.3 A User-to-User Recommendation Framework 93
5.3.1 Enriched User Models 93
5.3.2 Similarity Computation 95
5.3.3 Adaptation for Social Preferences 96
5.3.4 Benchmarks 97
5.4 Similarity Measures 99
5.5 Preference Analytics 103
5.5.1 User Profiles 103
5.5.2 Preference Generation 105
5.5.3 Benchmarks 110
5.6 Related Work 112
5.6.1 Friendship Recommendation 114
5.6.2 Preference and Profile Matching 115
5.6.3 Reciprocal Recommender Systems 116
6 Data-Adaptive Group Analysis in LBSN 119
6.1 Area of Application 120
6.2 Fundamentals of Group Formation 121
6.3 Solution Space Inspection Approach 123
6.3.1 Solution Space 123
6.3.2 Data-Adaptive Preference-Based Approach 124
6.3.3 Benchmarks 126
6.3.4 Demo Scenario 128
6.4 P-Means: Preference-Enhanced k-Means 132
6.4.1 User Representation 134
6.4.2 Centroid Generation and Computation 135
6.4.3 Cluster Assignment and Distance Measure 136
6.4.4 Satisfaction of Hard Constraints 136
6.4.5 Benchmarks 137
6.5 Preference-Based MIN-K Algorithm 139
6.5.1 Group Similarity 140
6.5.2 Seed Selection 141
6.5.3 User Allocation 141
6.5.4 Benchmarks 144
6.6 Semantic Benchmarks 145
6.6.1 User Generation 146
6.6.2 Evaluation Criteria 147
6.6.3 Evaluation Results 148
6.7 Related Work 150
6.7.1 Clustering 150
6.7.2 Community Detection 152
6.7.3 Matching under Preferences 152
7 Conclusion 155
7.1 Summary 156
7.2 Future Work 157
A Algebraic Laws for Group Preferences 159
B Definition of User Stereotypes 167
Bibliography 171
List of Figures 187
List of Tables 189
List of Algorithms 191
Curriculum Vitae 193

Produkt-Details

• Erscheint lt. Verlag: 17.6.2016
• Sprache: englisch
• Themenwelt: Mathematik / Informatik ► Informatik ► Netzwerke
• ISBN-10: 3-7412-1191-5 / 3741211915
• ISBN-13: 978-3-7412-1191-1 / 9783741211911