Neural Network: An Improved FCM for Multimodal Cultural Data Analysis

With the development of cloud computing, big data, and artificial intelligence (AI) technology, there is a growing interest in “cultural analysis.” Cultural analysis requires different types of data such as texts, pictures, and videos. The richness and differences of resources in the cultural field lead to diverse modalities of cultural data. Traditional text analysis methods can no longer meet the data analysis needs of current multimedia cultural resources. This article starts from cultural data’s feature information to solve the heterogeneity problem faced by massive multimodal cultural data analysis. It analyzes it from geography, time, art, and thematic character, classified and aggregated to form a multimodal cultural feature information matrix. The corresponding correlation measurement methods for different matrices from the above dimensions are proposed, solved in turn, and substituted into the optimized training back propagation (BP) neural network to obtain the final correlation degree. The improved fuzzy C-means (FCM) clustering algorithm is used to aggregate the high correlation cultural data based on the degree. The algorithm proposed in this study is compared with the existing algorithm. The experimental results show that the optimized BP neural network is at least 58% more accurate than the current method for calculating different matrices’ correlation degrees. In terms of accuracy, the improved fuzzy C-means algorithm effectively reduces the random interference in the selection of the initial clustering center, which is significantly higher than other clustering algorithms.

Comparing a Binary Dependent Variable Across Cultural Groups Using Applied Logistic Regression

This chapter reviews the basic ideas of logistic regression involving a binary dependent regressed on independent variables, along with assumptions for analysis and interpretations of results. It provides strategies and practical guides for data analysis using Stata and explains the basic assumptions of logistic regression and its applications for cross-cultural data analysis. The chapter also provides examples of logistic regression models for cross-cultural comparison, and outlines the techniques for testing the equivalence of effects across groups. The text includes examples of charts and graphs that can be used to explain differences in effects across cultural groups.

Introduction to Applied Cross-Cultural Data Analysis

This chapter introduces applied cross-cultural data analysis and addresses the concepts of culture and how culture can be integrated into social work research. We review the definition of culture and how it has been understood and examined in research across various disciplines. We present an overview of the theories and frameworks of cross-cultural analysis, and provide the lens through which culture is examined by means of the techniques and approaches that are used in this book. Cross-cultural analysis can be viewed as comparisons based on key demographic variables such as countries of origin, race, ethnicity, language, sex, religion, and related cultural identifications. The assumption is that people who share the same cultural identification also share similar values and behaviors.

Applied Hierarchical Linear Modeling for Cross-Cultural Comparison

We explain and demonstrate the application of Hierarchical Linear Modeling (HLM) in cross-cultural research. This method of analysis has not been sufficiently explored in social work research, and it can be a highly useful and appropriate statistical approach for making cross-cultural comparisons. We explain the rationale for HLM or multilevel modeling for cross-cultural data analysis, and we provide an example in which we use Stata to test for neighborhood effects across race groups using survey data. We provide Stata commands and examples of testing for invariance of effects across groups while controlling for heteroscedasticity due to neighborhood level effects. Finally, we included geomaps based on the data to provide visualization of neighborhood effects.

Applied Cross-Cultural Data Analysis for Social Work

Applied Cross-Cultural Data Analysis for Social Work is a research guide which provides a hands-on approach for learning and understanding data analysis techniques for examining and interpreting data for the purpose of cultural group comparisons. This book aims to provide practical applications in statistical approaches of data analyses that are commonly used in cross-cultural research and evaluation. Readers are presented with step-by-step illustrations in the use of descriptive, bivariate, and multivariate statistics to compare cross-cultural populations using large-scale, population-based survey data. These techniques have important applications in health, mental health, and social science research relevant to social work and other helping professions, especially in providing a framework of evidence to examine health disparities using population-health data. For each statistical approach discussed in this book, we explain the underlying purpose, basic assumptions, types of variables, application of the Stata statistical package, the presentation of statistical findings, and the interpretation of results. Unlike previous guides on statistical approaches and data analysis in social work, this book explains and demonstrates the strategies of cross-cultural data analysis using descriptive and bivariate analysis, multiple regression, additive and multiplicative interaction, mediation, and SEM and HLM for subgroup analysis and cross-cultural comparisons. This book also includes sample syntax from Stata for social work researchers to conduct cross-cultural analysis with their own research.