Big Data and Social Media Analytics: Trending Applications

Description

This edited book provides techniques which address various aspects of big data collection and analysis from social media platforms and beyond. It covers efficient compression of large networks, link prediction in hashtag graphs, visual exploration of social media data, identifying motifs in multivariate data, social media surveillance to enhance search and rescue missions, recommenders for collaborative filtering and safe travel plans to high risk destinations, analysis of cyber influence campaigns on YouTube, impact of location on business rating, bibliographical and co-authorship network analysis, and blog data analytics. All these trending topics form a major part of the state of the art in social media and big data analytics. Thus, this edited book may be considered as a valuable source for readers interested in grasping some of the most recent advancements in this high trending domain. Contents Twenty Years of Network Science: A Bibliographic and Co-authorship Network Analysis 1 Introduction 2 Scholarly Networks Analysis 3 Preliminaries and Data 3.1 Co-authorship Network of Network Scientists 3.2 Glossary 3.3 Data Collection and Preparation 4 Analysis of Network Science Papers 5 Analysis of the Co-authorship Network 6 Conclusion References Impact of Locational Factors on Business Ratings/Reviews: A Yelp and TripAdvisor Study 1 Introduction 2 Related Work 3 Methodology and Datasets 3.1 Methodology 3.2 Restaurant Success Metric 3.3 Restaurant Dataset 3.3.1 Yelp-2019 Dataset 3.3.2 TripAdvisor Dataset 3.4 Location Dataset 4 Effect of Location Parameters on Restaurant Success 4.1 Location Characteristic Parameters 4.1.1 Living Standard 4.1.2 Tourism Significance 4.1.3 Business Convenience 4.1.4 Combined Parameters 4.2 Correlation Metrics 4.2.1 Spearman's Correlation 4.2.2 Kendall's Correlation 4.3 Correlation Results 4.3.1 State-Wise Correlation Using All Restaurants 4.3.2 Cluster-Wise Correlation Using All Restaurants 5 Conclusion References Identifying Reliable Recommenders in Users' Collaborating Filtering and Social Neighbourhoods 1 Introduction 2 Related Work 3 SN CF Prediction Formulation Foundations 4 The Proposed Algorithm and the Partial Prediction Combination Alternatives 4.1 The Proposed Algorithm 4.2 Alternatives for Combining the CF and SN Partial Predictions 4.3 Complexity Analysis 5 Experimental Evaluation 5.1 Prediction Accuracy Experiments Using the PCC as the Similarity Metric 5.2 Prediction Accuracy Experiments Using the CS as the Similarity Metric 6 Conclusions and Future Work References Safe Travelling Period Recommendation to High Attack Risk European Destinations Based on Past Attack Information 1 Introduction 2 Related Work 3 Algorithm Prerequisites 4 Prediction Algorithm 5 Experimental Results 5.1 Number of Attacks as the Evaluation Parameter 5.2 Number of Fatalities as the Evaluation Parameter 6 Conclusion and Future Work References Analyzing Cyber Influence Campaigns on YouTube Using YouTubeTracker 1 Introduction 2 State of the Art in YouTube Analysis 3 YouTubeTracker 3.1 Tracker Feature 3.2 Posting Frequency 3.3 Content Analysis 3.4 Content Engagement 4 Case Study: 2018 Trident Juncture Exercise 5 Extended Work 5.1 Elasticsearch 5.2 2019 Canadian Elections Use-Case 5.3 Video Characterization Using T-SNE and Barcode Visualization 6 Conclusion and Future Works References Blog Data Analytics Using Blogtrackers 1 Introduction 2 State of the Art in Blog Monitoring and Analysis 3 Blogtrackers: Analytical Capabilities 4 Analysis of Asia-Pacific Blogs: A Case Study 5 Conclusion and Future Works References Using Social Media Surveillance in Order to Enhance the Effectiveness of Crew Members in Search and Rescue Missions 1 Introduction 2 Related Work 2.1 Search and Rescue Missions (SARs) 2.2 Social Media in Crisis Situations 2.3 Visual Search Principles & Patterns 3 Problem Statement 4 Methodology 4.1 Description 4.2 Simulation Platform 4.3 Scenario 5 Experimental Analysis 5.1 Experimental Description 5.2 Results 6 Conclusions References Visual Exploration and Debugging of Machine Learning Classification over Social Media Data 1 Introduction 2 Related Work 3 SAVIZ: Brief Overview 3.1 User Experience 4 Conclusion References Efficient and Flexible Compression of Very Sparse Networksof Big Data 1 Introduction 2 Background and Related Work 3 Our Efficient and Flexible Compression Model 3.1 Graph Representation of a Social Network 3.2 Matrix Representation of a Social Network 3.3 Bit Vector Representation of a Follower in a Social Network 3.4 Word-Aligned Hybrid (WAH) Compressed Bitmap Representation of a Follower in a Social Network 3.4.1 An Example of WAH Compressed Bitmap 3.5 Improved Position List Word-Aligned Hybrid (IPLWAH) Compressed Bitmap Representation of a Follower in a Social Network 3.5.1 An Example of IPLWAH(1) Compressed Bitmap 3.5.2 An Example of IPLWAH(2) Compressed Bitmap 3.6 Multi-group Position List Word-Aligned Hybrid (MPLWAH) Compressed Bitmap Representation of a Follower in a Social Network 3.6.1 An Example of MPLWAH(2) Compressed Bitmap 3.6.2 An Example of MPLWAH(3) Compressed Bitmap 3.6.3 Other Examples of MPLWAH(3) Compressed Bitmaps 4 Our Data Science Solution for Social Network Mining on MPLWAH Compressed Bitmaps 4.1 An Example of Discovering Frequently Followed Groups of Followees from a Social Network Represented by a Collection of MPLWAH(3) Compressed Bitmaps 5 Evaluation 5.1 Evaluation on Memory Consumption 5.2 Evaluation on Runtime 5.3 Evaluation on Scalability 6 Conclusion References Weather Big Data Analytics: Seeking Motifs in Multivariate Weather Data 1 Introduction 2 Related Work 3 Temperatures Time Series Analysis and Clustering 3.1 Data Acquisition 3.2 Data Preparation and Curation 3.3 Discretization 3.4 LERP-RSA Construction 3.5 ARPaD Pattern Discovery 3.6 Similarity Meta-analysis 4 Experimental Analysis 5 Conclusions References Analysis of Link Prediction Algorithms in Hashtag Graphs 1 Introduction 2 Background and Motivation 3 Foundation of the Hashtag Graph 3.1 Unweighted Heuristic Link Prediction Methods 3.2 Edge-Weighted Heuristic Link Prediction Methods 3.3 Graph Neural Network Link Prediction with SEAL 3.3.1 SEAL 3.3.2 Node Labelling 3.4 Other Heuristic Link Prediction Methods 3.4.1 Katz Index 3.4.2 SimRank 3.4.3 Rooted PageRank 4 Methodology: Vertex-and-Edge-Weighted Heuristic Link Prediction Methods 5 Experimental Setup 5.1 Data Collection 5.2 Data Pre-processing 6 Results 6.1 Heuristic Link Prediction Methods 6.2 SEAL 7 Conclusions and Future Research References