Constructing a Course on Classification Methods for Undergraduate Non-STEM Students: Striving to Reach Knowledge Discovery

Abstract

Classification, a fundamental data analytics task, has widespread applications across various academic disciplines, such as marketing, finance, sociology, psychology, education, and public health. Its versatility enables researchers to explore diverse research questions and extract valuable insights from data. Therefore, it is crucial to extend familiarity with classification methods to non-STEM students, who will encounter such problems in their professional careers. To address this need, this article presents a data science course for non-STEM students on classification methods. The course’s difficulty level is influenced by factors such as students’ backgrounds and the prerequisites and requirements set by the offering department. The suggested course framework begins with data preparation and provides students with a comprehensive toolbox comprising methodical techniques and software tools for classification. This course guides students toward discovering new knowledge and insights about classification and interpretation. The teaching approach emphasizes the dynamic process involved in classification, encompassing grasping the analytical task, understanding terms and concepts, visualizing the classification, analyzing data, interpreting results, and drawing conclusions. This course also combines project-based learning, open discussions, and even competitions among class participants. Incorporating practical projects that involve interaction and decision-making within a quantitative course can be highly beneficial. Supplementary materials for this article are available online.

Keywords

• Classification
• Data science education
• Decision-making
• Interpretation
• Knowledge discovery
• Supervised learning