1 - 1 of 1 results for: SOC128D

Data science and machine learning have rapidly gained recognition within the social sciences because they offer powerful new ways to ask questions about social and cultural issues. This course will examine how data science has revolutionized how social scientists study culture by providing new tools to analyze patterns in text data in different contexts and at different scales. More specifically, we will explore how these tools can be used to mine the meaning of text from sources such as posts on social media, transcripts of political debates, books, press releases, and more. This is a hands-on, interactive course culminating in a social data science project designed by the student or a team of up to four students. Most class sessions will be taught interactively using Jupyter Notebooks. Students will follow along with workshop-style lectures by using and modifying the provided Python code in real time to analyze data and visualize results. The course will cover such topics as gender and racial/ethnic stereotypes, workplace discrimination, climate change, and lifestyles. Students will learn to explore text data with techniques such as word embeddings, topic models, and sentiment analysis, to visualize their results, and to scrape the web (where and when appropriate). Students will gain experience with base Python and tools from libraries useful for data science such as Empath, Gensim, NumPy, Pandas, Scikit-learn, and spaCy.