Information management and big data : 7th Annual International Conference, SIMBig 2020, Lima, Peru, October 1-3, 2020, Proceedings

Description

This book constitutes the refereed proceedings of the 7th International Conference on Information Management and Big Data, SIMBig 2020, held in Lima, Peru, in October 2020.* The 32 revised full papers and 7 revised short papers presented were carefully reviewed and selected from 122 submissions. The papers address topics such as natural language processing and text mining; machine learning; image processing; social networks; data-driven software engineering; graph mining; and Semantic Web, repositories, and visualization. *The conference was held virtually. Preface Keynote Speakers’ Resumes Organization Contents Natural Language Processing and Text Mining Comparative Analysis of Question Answering Models for HRI Tasks with NAO in Spanish 1 Introduction 2 Background 2.1 Spanish Datasets 2.2 Model Architecture and Main Algorithms 2.3 Human Robot Interaction (HRI) 3 Main Contribution 4 Related Work 5 Experiments 5.1 Train Question Answering Pre-trained Models Using a Spanish Datasets 5.2 Human Robot Interaction Experiments and Results 6 Conclusions References Peruvian Citizens Reaction to Reactiva Perú Program: A Twitter Sentiment Analysis Approach 1 Introduction 1.1 Sentiment Analysis with Twitter 1.2 Applicability of Sentiment Analysis in the Field of Public Policy 2 “Reactiva Perú” 3 Method 3.1 Scraping Tweets #ReactivaPerú from Twitter 3.2 Pre-procesing 3.3 Polarity Classification 4 Results 4.1 What Do Citizens Think About #ReactivaPerú? 5 Conclusions References Twitter Early Prediction of Preferences and Tendencies Based in Neighborhood Behavior 1 Introduction 2 Related Work 3 Dataset 3.1 Social Graph 3.2 Content 3.3 Retweet-Time-Window 4 Early Prediction of Retweet Preferences 4.1 Experimental Setup 4.2 Results 5 Early Prediction of Tendencies 5.1 Experimental Setup 5.2 Results 6 Conclusions and Future Work References Summarization of Twitter Events with Deep Neural Network Pre-trained Models 1 Introduction 2 Related Works 3 System Overview 3.1 Event Clustering 3.2 Event Summarization 4 Experiments 4.1 Dataset 4.2 Cluster Selection 4.3 Reference Summary Creation 5 Results and Analysis 5.1 Cluster Evaluation 5.2 Summary Evaluation 6 Conclusion References Multi-strategic Approach for Author Name Disambiguation in Bibliography Repositories 1 Introduction 2 Related Work 3 Social Network Disambiguation Approach 3.1 Preliminaries 3.2 Data Extraction and Storage 3.3 Multi-strategic Core 3.4 Social Network Graph Creation 4 Case Study 4.1 Baseline 4.2 Case Results and Analysis 5 Conclusion References Machine Learning Techniques for Speech Emotion Classification 1 Introduction 2 Related Work 3 Methodology 3.1 Database 3.2 Preprocessing 3.3 Modeling 3.4 Model Evaluation 3.5 Demo 4 Results 5 Conclusions References An Evaluation of Physiological Public Datasets for Emotion Recognition Systems 1 Introduction 2 Related Work 3 Materials and Method 3.1 The Datasets 3.2 The Requirements 3.3 The Evaluation 4 Results 5 Discussion 5.1 Threats to Validity 6 Conclusions and Future Work References Machine Learning YTTREX: Crowdsourced Analysis of YouTube's Recommender System During COVID-19 Pandemic 1 Introduction 1.1 Algorithmic Personalization 1.2 Methods for Algorithmic Personalization Analysis 2 Tool: YouTube Tracking Exposed 2.1 How It Works 3 Experiment 3.1 Experiment Design 3.2 Official API Comparison 4 Findings 4.1 Evidence of Filter Bubbles 4.2 Network Analysis 5 Conclusions References Parallel Social Spider Optimization Algorithms with Island Model for the Clustering Problem 1 Introduction 2 Background 2.1 Clustering 2.2 Social Spider Optimization (SSO) Algorithm 2.3 Island Models 3 Parallel SSO (P-SSO) 3.1 P-SSO with Static Topologies 3.2 P-SSO with Dynamic Topologies 4 Experiments and Results 5 Discussion 6 Conclusions and Future Work References Two-Class Fuzzy Clustering Ensemble Approach Based on a Constraint on Fuzzy Memberships 1 Introduction 2 Background 2.1 Partition Generation 2.2 Consensus Function 3 Proposed Ensemble Method 3.1 Generation 3.2 Consensus Scheme 4 Evaluation 4.1 Performance Analysis 4.2 Experiments and Results 5 Conclusion References Modeling and Predicting the Lima Stock Exchange General Index with Bayesian Networks and Information from Foreign Markets 1 Introduction 2 Materials and Methods 3 Experiments and Results 4 Conclusion References Comparative Study of Spatial Prediction Models for Estimating PM2.5 Concentration Level in Urban Areas 1 Introduction 2 Materials and Methods 3 Results and Discussions 4 Conclusions References Prediction of Solar Radiation Using Neural Networks Forecasting 1 Introduction 2 Low-Cost Automatic Weather Station 3 Raspberry Pi and Sensors for Measuring Meteorological Variables 4 Forecasting Using Neural Networks 5 Conclusion References COVID-19 Infection Prediction and Classification 1 Introduction 2 Literature Review 3 Machine Learning 3.1 Supervised Machine Learning 3.2 Decision Trees 4 The Learning Data 4.1 Initial Data Analysis 5 Experimentations 6 Conclusion References Image Processing Towards a Benchmark for Sedimentary Facies Classification: Applied to the Netherlands F3 Block 1 Introduction 2 Seismic Dataset 2.1 Dataset Preparation 3 Deep Network Architectures 3.1 U-Net 3.2 U-Net with Dilated Convolutions 3.3 Deep Residual U-Net 3.4 Danet FCN 3.5 DeepLabv3+ 4 Experiments 4.1 Training 4.2 Post-processing 5 Results 6 Conclusion References Mobile Application for Movement Recognition in the Rehabilitation of the Anterior Cruciate Ligament of the Knee 1 Introduction 2 Theoretical Framework 2.1 Anterior Cruciate Ligament 2.2 Injury of the Anterior Cruciate Ligament 2.3 Rehabilitation and Physiotherapy 2.4 Android, OpenCV and RGB 3 Materials and Methods 3.1 Materials 3.2 Software 4 Application Development 4.1 Requirements 4.2 Design 4.3 Implementation 4.4 Testing 5 Results 6 Conclusions References Semantic Segmentation Using Convolutional Neural Networks for Volume Estimation of Native Potatoes at High Speed 1 Introduction 1.1 Related Work 2 Materials and Methods 2.1 Calibration Process 2.2 Approach Based on Classical Methods 2.3 Deep Learning Approach 2.4 Volume Estimation 3 Results 3.1 Experimentation Environment 3.2 Qualitative and Quantitative Comparison of Models 4 Discussion 5 Conclusions References Symbiotic Trackers' Ensemble with Trackers' Re-initialization for Face Tracking 1 Introduction 2 Symbiotic Tracker Ensemble 2.1 Relationships Between Tracking Estimates 2.2 Intra-tracker Correlation 2.3 Inter-tracker Correlation 2.4 Estimates Combination 3 SymTE with Trackers Re-initialization 3.1 Tracker's Re-initialization 4 Experimental Settings 4.1 TB-Face Dataset 4.2 Evaluation Metrics 4.3 Trackers 4.4 Symbiotic Tracker Ensemble Parameters 5 Results Analysis 6 Conclusions and Future Works References Multi-class Vehicle Detection and Automatic License Plate Recognition Based on YOLO in Latin American Context 1 Introduction 2 Related Work 3 Methods 3.1 Data Collection 3.2 Data Preparation 3.3 Data Processing, Detection and Classification 3.4 Character Segmentation 3.5 Character Recognition 3.6 Metrics 4 Results and Discussion 5 Conclusions 6 Future Work References Static Summarization Using Pearson's Coefficient and Transfer Learning for Anomaly Detection for Surveillance Videos 1 Introduction 2 Background 3 Main Contribution 3.1 Summarization 3.2 Classification 4 Related Work 4.1 Video Summarization 4.2 Classification of Anomalous Events 5 Experiments 5.1 Experimental Protocol 5.2 Results 6 Conclusion References Humpback Whale's Flukes Segmentation Algorithms 1 Introduction 2 Background 2.1 Otsu 2.2 Chan Vese 2.3 Fully Convolutional Neural Network 2.4 Pyramid Scene Parsing Network 3 Methodology 3.1 Dataset 3.2 Algorithms Implementations Details 3.3 Evaluation Metrics 4 Results Analysis 5 Conclusion References Improving Context-Aware Music Recommender Systems with a Dual Recurrent Neural Network 1 Introduction 2 Related Work 3 Proposed Work 4 Empirical Evaluation 4.1 Datasets 4.2 Context-Aware Recommender Systems 4.3 Evaluation Setup 4.4 Results 5 Conclusion and Future Work References Social Networks Classification of Cybercrime Indicators in Open Social Data 1 Introduction 2 Related Work 3 Proposed System 3.1 System Overview 3.2 Data Collection and Labeling 3.3 Preprocessing 4 Experimental Setup 4.1 Random Forest (RF) 4.2 Deep Neural Networks with Pyramid Structure 4.3 Evaluation Metrics 5 Results 5.1 Random Forest 5.2 2L-PCNN-BN 5.3 3L-PCNN-S 5.4 Comparison 5.5 Analysis over NYK-dataset 6 Conclusion References StrCoBSP: Relationship Strength-Aware Community-Based Social Profiling 1 Introduction 2 Related Work 3 Proposition: Strength-Aware Method to Construct Social Profiles 3.1 Notation 3.2 CoBSP: Community-Based Social Profile Process 3.3 StrCoBSP: Strength-Aware Community-Based Social Profile Process 4 Experiment 4.1 Relationship Strength Calculation 4.2 Evaluation 4.3 Results and Discussion 5 Conclusions References Identifying Differentiating Factors for Cyberbullying in Vine and Instagram 1 Introduction 2 Related Work 3 Data Set 4 Analysis of Unique Commenters 5 Temporal Analysis of Negative and Positive Sentiment Comments 6 Analysis of Comments 7 Analysis of Media Captions 8 Conclusions References Effect of Social Algorithms on Media Source Publishers in Social Media Ecosystems 1 Introduction 2 Related Work 3 Social Media Content Delivery Ecosystem 4 Data Set 5 Time Series of Publishing Contents 6 The Number of Participants 7 Response Time 8 Conclusion References The Identification of Framing Language in Business Leaders' Speech from the Mass Media 1 Introduction 2 Related Work 3 Proposed Technique 4 Evaluation 4.1 Results 4.2 Ranked Quotes 5 Reproducibility 6 Conclusion References Clustering Analysis of Website Usage on Twitter During the COVID-19 Pandemic 1 Introduction 2 Related Research 3 Methodology 3.1 Multi-view Clustering of URLs 3.2 Data Processing and View Graph Creation 4 Results 4.1 Multi-view Clustering Statistics 4.2 Comparison of Clusters to Domain Labels 4.3 Content of Clusters of Interest 5 Discussion References Data-Driven Software Engineering Calibrated Viewability Prediction for Premium Inventory Expansion 1 Introduction 2 Related Work 3 Cascading Gradient Boosting Trees 4 Evaluation and Results 5 Discussion and Future Work 1 Appendix 1 - Additional Tables and Graphs References Data Driven Policy Making: The Peruvian Water Resources Observatory 1 Introduction 2 Related Works 3 Background 4 Water Resources Observatory Platform 5 Case Study: Water Distribution in Lima 6 Conclusions and Recommendations References Graph Mining Complex Networks to Differentiate Elderly and Young People 1 Introduction 1.1 Methods for Comparing Time Series 2 Techniques 3 Network Measure 3.1 Mean Jump Length 3.2 Betweenness Centrality 3.3 Clustering Coefficient 4 Database Information 5 Results 6 Conclusions References Analysis of the Health Network of Metropolitan Lima Against Large-Scale Earthquakes 1 Introduction 2 Related Works 3 Methodology 4 Results 5 Conclusions References Quasiquadratic Time Algorithms for Square and Pentagon Counting in Real-World Networks 1 Introduction 2 Proposed Method 2.1 Proposed Algorithms 3 Counting Squares and Pentagons 3.1 Squares 3.2 Pentagons 4 Experiments 5 Conclusions References Identifying Covid-19 Impact on Peruvian Mental Health During Lockdown Using Social Network 1 Introduction 2 Related Work 3 Methodology 3.1 Select Relevant Terms 3.2 Build the Query and Collect Data 3.3 Preprocessing Data 3.4 Visualization 4 Results and Discussion 4.1 Dataset Description 4.2 What Is the Covid-19 Impact on Peruvian Mental Health? 5 Conclusions 6 Future Work References Diagnosis of SARS-CoV-2 Based on Patient Symptoms and Fuzzy Classifiers 1 Introduction 2 Materials and Method 2.1 Fuzziness Interface 2.2 Knowledge Rules 2.3 Fuzzy Inference Engine 2.4 Defuzzification Interface 3 Results 4 Conclusions References Semantic Web, Repositories, and Visualization Distributed Identity Management for Semantic Entities 1 Introduction 2 Related Work 3 Distributed Industrial Engineering and Manufacturing Scenario: The LEGO Train Project 4 Requirements 5 Novel Concept of semDIM 6 Knowledge Representation in DIM Using Ontology Design Patterns 7 Evaluation: Application of semDIM Patterns 8 Conclusion References Telegram: Data Collection, Opportunities and Challenges 1 Introduction 2 Literature Review 3 Methodology 3.1 Setting up Data Collection Scripts 3.2 Discovery of Relevant Channels and Groups 3.3 Data Processing and Storage 4 Analysis and Findings 4.1 Group Analysis 4.2 Channel Analysis 5 Discussion and Conclusions References Graph Theory Applied to International Code of Diseases (ICD) in a Hospital 1 Introduction 2 Data Description and First Order Statistics 3 Applying Graph Theory 3.1 Self-ties Analysis 3.2 Cutting Edges: 10% 3.3 The Top 5% 4 Discussions 5 Conclusions References CovidStream: Interactive Visualization of Emotions Evolution Associated with Covid-19 1 Introduction 2 Related Work 3 Proposal 4 Implementation 4.1 Classification Model Construction 4.2 Data Acquisition 4.3 Data Preprocessing 4.4 Data Processing 4.5 Data Visualization Generation 4.6 Building Tool Visualization 5 Results 5.1 Q1: How is the Evolution of the Emotional Perception of Peruvians Regarding the Covid-19, Over Time? 5.2 Q2: Who are the Persons, Places, and Organizations that Influence the Emotional Perception of Peruvians, Regarding Covid-19, Over Time? 5.3 Q3: What is the Time Evolution of Persons, Places, and Organizations that Intervene in the Emotions of Peruvians, Regarding Covid-19, Over Time? 6 Conclusions References Author Index