Cultural Data Science
Learning Outcomes:
- Analyze the paradigm shift from traditional Humanities Computing to Cultural Data Science, and demonstrate technical literacy in managing Culture at Scale and Wide Data where features exceed the number of cases.
- Implement data science pipelines to transform unstructured cultural artifacts (images, text, audio) into quantitative data representations using algorithmic feature extraction and multi-modal metadata integration
- Execute unsupervised learning, temporal analysis, and media visualization to uncover cultural patterns while critically evaluating algorithmic bias and the interpretability of “Black Box” models in cultural decision-making
Topics:
- Introduction: From Humanities Computing to CDS
- Culture at Scale: The “More Media” Era
- Data Representation and the Semantic Gap
- Representing Culture: Social & Professional Networks
- Feature Extraction (I): Visual Analytics & Computer Vision
- Feature Extraction (II): Textual & Sound Analytics
- Cultural Sampling and Bias
- Information vs. Media Visualization
- Unsupervised Learning: Cluster Analysis
- Media Analytics in Industry: Recommendations
Published at :
SOCIAL MEDIA
Let’s relentlessly connected and get caught up each other.
Looking for tweets ...