Data and Information in Online Environments: Third EAI International Conference, DIONE 2022, Virtual Event, July 28-29, 2022, Proceedings (Lecture ... and Telecommunications Engineering)

This book constitutes the refereed post-conference proceedings of the Third EAI International Conference on Data and Information in Online Environments, DIONE 2022, held as virtual event, in July 28-29, 2022. Due to COVID-19 pandemic the conference was held virtually. DIONE 2022 aims to bring together academicians and practitioners willing to discuss topics around the intersection of Computer Science, Information Science, and Communication Science. The attractiveness of the scope and topics has brought relevant research results. This proceeding consists of chapters covering deep learning, data management, software design, social networks, natural language processing, and data processing in various contexts like scholarly publishing, health and medicine, higher education, innovation and research, energy and transportation, and organizations. The 18 full papers and 2 short papers were carefully reviewed and selected from 56 submissions. The papers are grouped in thematic sessions as follows: Informational challenges for the study of Science, Technology and Society relationships; and Advances in Artificial Intelligence for data processing and analysis in online social environments. Preface Organization Contents Informational Challenges for the Study of Science, Technology and Society Relationships Disinformation as a Social Phenomenon 1 Introduction 2 How is Information Selected? 3 Methodology 4 Results 5 Discussion 6 Conclusions References Overview of Citizen Science Projects Contemplated in the Civis Platform 1 Introduction 2 Citizen Science 2.1 Models of Citizen Participation 3 Methodology 4 Results 5 Discussion 6 Preliminary Conclusions References National Registry of Scientific Data Management Plans by IBICT 1 Introduction 2 Methodological Procedures 3 FAIR Data Management Plan 4 Results and Discussions 5 Final Considerations References Collection and Integration of Patent Data for Analysis and Validation of Brazilian Technical Production 1 Introduction 2 Related Works 3 Methodology 3.1 Data Acquisition 4 Results 5 Final Considerations References Publications in Scientific Events as a Data Source for Scientometric Analysis 1 Introduction 2 Development 3 Results 3.1 General Characterization 3.2 Temporal Analysis 3.3 Articles in Annals of Events by Large Area 3.4 Persistent Identifiers 3.5 Analysis by Countries 4 Final Considerations References Publications in Open Access Journals: A Bibliometric Analysis 1 Introduction 2 Methodology 3 Analysis and Results 4 Conclusions References Scientific Divulgation Before the Post-truth and the Crisis of Credibility of Science in the Context of Digital Humanities 1 Introduction 2 Methodology 3 Digital Humanities and the Scientific Environment 4 Scientific Divulgation and Scientific Communication: Necessary Distinctions 5 The Post-truth Phenomenon and the Crises of Science Credibility: The Problem 6 Results 7 Final Considerations References Workflow with Emphasis in Technologies for the Construction of an Aggregator and a Dashboard of Brazilian Museums Digital Collections 1 Introduction 2 Methodology 3 Technologies Workflow or the Construction of an Aggregator and a Dashboard 3.1 Tainacan: Mapping Origin Museums 3.2 Beats - Filebeat: Automated Collection of Items from Museums 3.3 Logstash: Aggregation of Collections and Data Transformation 3.4 Ruby Plugin in Logstash: Item Submission in Tainacan 3.5 Elasticsearch: Data Storage 3.6 Kibana: Dashboard 3.7 Tainacan: Final Repository 4 Discussions 5 Conclusions References Concept Maps as a Support for Learning: 1 Introduction 2 Concept Maps 3 General Law for Personal Data Protection 4 Methodology 5 Results and Discussion: Representative Concept Map of Data Life Cycle According to LGPD Rules 6 Conclusions References Effect of Network Embedding on the Performance of Chinese Venture Capital Institutions: Mediatory Role of Organizational Learning 1 Introduction 2 Theory and Research Hypothesis 2.1 Relationship of Network Embedding and Investment Performance 2.2 Mediatory Role of Organizational Learning 3 Research Design 3.1 Data Sample Matching 3.2 Mediating Effect Test Model and Steps 3.3 Variable Measure 4 Descriptive Statistics and Correlation Analysis 5 Regression Results 6 Conclusion and Enlightenment References Advances in Artificial Intelligence for Data Processing and Analysis in Online Social Environments Contributions and Limitations About the Use of Deep Learning for Skin Diagnosis: A Review 1 Introduction 2 Literature Review 3 Methodology 4 Results and Discussion 5 Final Considerations References An Expanded Study of the Application of Deep Learning Models in Energy Consumption Prediction 1 Introduction 2 Related Works 3 Problem and Motivation 4 Proposed Model 4.1 Database 4.2 Load Seasonality 4.3 Consumption Prediction from Time Series 5 Implementation and Results 5.1 Variable Selection and Model Entry 5.2 Comparison of the Models Results 6 Conclusion References Application and Evaluation of a Taxonomy in the Context of Software Requirements Management 1 Introduction 2 Background 2.1 Requirements Engineering and the Activity of Software Requirements Management 2.2 Taxonomies in the Context of Information Management 2.3 Related Works 3 Research Stages 4 Analysis of Taxonomies’ Objectives in Relation to the Objectives of Requirements Management Activities 5 Application and Assessment of Taxonomies in the Context of Software Requirements Management 5.1 Taxonomy Application 5.2 Taxonomy Assessment 5.3 Analysis of Application Results and Assessment of the Taxonomy in the Context of Requirements Management 6 Conclusions References Assessment of Heart Patients Dataset Through Regression and Classification Algorithms 1 Introduction 2 Related Work 3 Methodology 3.1 Pre-processing 3.2 Regression Algorithms 3.3 Classification Algorithms 4 Exploratory Data Analysis 4.1 Dataset 4.2 Exploratory Analysis 5 Results and Discussion 5.1 Evaluating Algorithms with Other Resources 5.2 Conclusion 6 Future Work References Classification Model Based on Chatbot and Unsupervised Algorithms to Determine Psychological Intervention Programs in Peruvian University Students 1 Introduction 2 Materials and Methods 2.1 Unit of Analysis 2.2 Chatbot Construction and Data Extraction 2.3 Data Processing 3 Results 3.1 Chatbot Construction and Data Extraction 3.2 Data Processing 4 Conclusions References Comparison of Algorithms for Classification of Financial Intelligence Reports 1 Introduction 1.1 Financial Intelligence Report (FIR) 2 Background 2.1 Artificial Intelligence and Machine Learning 2.2 Decision Tree Algorithm 2.3 Random Forest Algorithm 2.4 K-Nearest Neighbors (KNN) Algorithm 3 Methodology 4 Development 4.1 Data Collection 4.2 Learning Table Pre-processing 4.3 Learning 4.4 Application 5 Results 6 Final Considerations References Natural Language Processing of Messages from a Social Network for Inflation Analysis 1 Introduction 2 Related Research 3 Method 3.1 Data Acquisition 3.2 Natural Language Processing 3.3 Network Analysis 4 Results Analysis 5 Final Remarks References Mining Association Rules in Commuter Feedback Comments from Facebook of Swiss National Railways (SBB) Using Apriori Algorithm 1 Introduction 2 Data Selection 3 Pre-processing 4 Data Transformation 5 Data Mining 5.1 Building Frequent Item Sets 5.2 Building Association Rules 6 Results (Association Rules) 6.1 Overall Impression and Corona 6.2 Overall Impression and Ticket 6.3 Overall Impression, Reliability, Time 7 Knowledge Interpretation 7.1 Reliability 7.2 Covid-19 7.3 Train Ticket 7.4 SBB APP 7.5 Timetable 8 Conclusion and Future Work References Enhancement of Voting Scores with Multiple Attributes Based on VoteRank++ to Identify Influential Nodes in Social Networks 1 Introduction 2 Backgrounds 2.1 Centrality Measures 2.2 Performances Metrics 3 Proposed Algorithm 4 Experimental Results 5 Conclusions and Future Work References Identification of the Relationships Between Data Provenance and Blockchain as a Contributing Factor for Health Information Systems 1 Introduction 2 Literature Review 2.1 Health Information Systems 2.2 Data Provenance 2.3 Blockchain 3 Methodology 4 Analysis 4.1 Identification of Relations Between the Main Applications of Data Provenance and Blockchain Features 4.2 Some of the Studies Which Verify the Relations Between Data Provenance and Blockchain Applied in HIS 5 Conclusions and Future Work References Author Index