Social Big Data Analysis Using Python

This course introduces the analysis tool NetMiner and covers its basic usage. Through hands-on practice with opening and editing data files, importing external data, and performing visualization and analysis, it helps reduce the apprehension and difficulty experienced by those encountering NetMiner for the first time.

"A first step for beginners using NetMiner 5—from basic usage to analyzing research data, all in one!&quot

"How to Quickly Identify Social Opinion Trends! Training in News and Community Data Analysis" • News data contains important information such as the latest events, economic changes, political trends, and natural disasters, enabling companies or individuals to quickly identify and understand these changes. Online community data consists of text data containing users’ opinions and information on various topics, providing social and cultural insights. • News and community data, along with text analysis and text network analysis methods, can be used for various purposes, including market analysis, policy and decision-making, public response analysis, trend analysis, education and research, crisis response, and disaster management.

This course teaches how to collect, model, and analyze social media data using NetMiner. It covers how to collect and organize YouTube data using NetMiner’s SNS Data Collector, understand and model the types and structures of social media data, and analyze social media influence, topics, and trends through theory, case studies, and hands-on practice.

This course teaches how to identify research trends through social network analysis by directly collecting and preprocessing paper data. Through hands-on practice, you will learn how to collect data using the Bibliographic Information Collector (Biblio Data Collector), transform a two-mode relationship connecting “papers” and “authors” into a one-mode network connecting “authors” and “authors,” and extract words from unstructured text data such as abstracts, followed by keyword network analysis and visualization.

This course covers methods for analyzing unstructured text data, such as news articles, tweets, and speeches, using NetMiner’s text network analysis features. You will build a theoretical foundation in the entire text network analysis process, from extracting words from unstructured text data and discovering topics to constructing and visualizing word networks and selecting key keywords. You will also practice applying these analytical methods to real-world news article and Twitter data using NetMiner.

Although the majority of real-world data consists of '2-mode' relationships—such as buyer–product, user–content, and word–document relationships—have you encountered distorted metrics or limitations in data transformation from blindly applying conventional 1-mode analysis methods? We present clear solutions ranging from the core principles of 2-mode networks to data conversion and direct analysis (Direct/Bipartite) approaches, as well as hands-on practice in user profiling and association analysis using NetMiner. Spend less time struggling with data conversion and metric calculation, and take your research and professional insights to the next level with unparalleled 2-mode network analysis capabilities spanning text, bibliographic, and SNS data.

• This course introduces methodologies for analyzing roles and positions within networks—topics that have been extensively studied in SNA—and helps participants understand the underlying principles through hands-on exercises using NetMiner, while also exploring practical applications. • Through this course, participants can measure brokerage roles from various perspectives, determine actors’ roles and positions within a network based on relationship patterns, and summarize the entire network through the relationships among role groups, thereby uncovering the key structures that comprise complex networks.

This course covers how to statistically interpret the results of network data analysis and how to test the significance of statistical measures. When applying traditional statistical methods such as cross-tabulation, analysis of variance, correlation analysis, and regression analysis, researchers need to understand how the characteristics of network data and network indices affect significance testing and use appropriate methods. The course consists of examples covering analytical topics frequently encountered by researchers—such as analyzing associations between variables, testing the significance of network indices, and analyzing associations among multiple networks—along with hands-on exercises using NetMiner.

A group in which entities are densely connected within a network is called a cohesive group. This course explores in detail the frequently used analysis methods for identifying cohesive groups with many connections, including cliques, k-cores, components, and communities. Through this course, discover key groups in network data or identify closely connected clusters.

Network centrality refers to the importance of a particular node within a network. There are various ways to measure it, and this course provides an in-depth look at seven representative and widely used centrality indices, along with analyses using real-world data. Through the course, learn how to select and apply centrality indices suited to various types of network data.

The most basic approach in network data analysis is to analyze network characteristics. Starting with the frequencies of nodes and links, this course explores in detail the principles and meanings of various indices that describe structural features of networks, including the distribution of the number of connections, density, shortest distance, clustering coefficient, and more. If the structure of a network can be measured numerically, it becomes possible to compare it with other networks. Through this course, define the characteristics of your network data from various perspectives.

To visually inspect network data, explore its structure, and effectively present analytical results, you need to understand and apply a variety of visualization methods. NetMiner provides features that effectively represent network data and analysis results. Through this course, learn how to present your network analysis results aesthetically and communicate the key points effectively.

To obtain accurate and meaningful results and insights through network analysis, data must be processed appropriately according to the direction and methods of the analysis. This course explains the essential preprocessing methods you need to know when preparing and entering network data, and provides hands-on practice with various data cleaning, extraction, and transformation methods using NetMiner and real-world data.

Starting with the question “What are social networks and social network analysis (SNA)?,” this course explains the key theories and analytical methods related to them, the specific process of understanding network data and constructing it from observed phenomena, and the research design process. As the first step in social network analysis, data modeling is highly important. Through this course, gain a thorough understanding of “network data,” which may be unfamiliar, and try designing a process for creating or collecting network data directly from a topic of interest.

How can you analyze data in research papers and identify research trends? This course covers quantitative research trend analysis, from collecting bibliographic information to network analysis and topic modeling, using NetMiner 5 and Biblio Data Collector. By developing bibliographic data processing skills and network analysis techniques, you can identify research trends objectively and efficiently.

"Social Network Analysis Training for Immediate Use in Practice and Research" Would you like to analyze the “relationships” within organizations, society, and content as data? Social network analysis (SNA) is a powerful analytical technique for structurally understanding relationships among people, information, and systems and uncovering hidden insights. From the core theories of social network analysis to hands-on practice, use NetMiner 5 and apply what you learn directly to your work and research.

Have you felt daunted by the unfamiliar coding barriers when trying to apply text analysis to various real-world settings? This course concisely covers the key theories behind the latest topic analysis methods frequently used in actual academic papers and research reports (LDA, BERTopic, and BERTrend), while helping you build practical analysis skills through hands-on analysis of real data using NetMiner 5—without any programming.