Syllabus - LEGALST 123, Spring 2020

1 Week 01

Jan 22: data, prediction, law; Lab Lab 1: Anaconda setup; Lab Lab 2: Intro to Jupyter Notebooks

2 Week 02

Jan 27: data structures; Lab Lab 3: Dataframe Operations & Simple Visualizations
Jan 29: summary stats (mean, s.d., distributions…), collection and cleaning of traditional survey data; Lab Lab 4: Probability Distributions, Bootstrap, and Confidence Intervals

3 Week 03

Feb 3: estimation & uncertainty, large N hypothesis testing; Lab Lab 5: Large n and hypothesis testing
Feb 5: Guest: Rebecca Wexler, Berkeley Law; “litigating predictive models (COMPAS), correlation, OLS regression regression and causal inference”; Lab Lab 5: Large n and hypothesis testing

4 Week 04

Feb 10: Prediction in policing; Lab Lab 7: Introduction to Folium (mapping)
Feb 12: SFPD incident report data and its application, machine learning models; Lab Lab 8: Folium Choropleth Maps

5 Week 05

Feb 24: Guest: Stephanie Croft, HRC Investigations Lab; predictive instruments and the decision to punish; Lab Lab 10: Folium Plugins
Feb 26: predictive bias–COMPAS; Lab Lab 11: Math in Scipy

6 Week 06

Mar 2: Guest: Prof. Hany Farid; more on COMPAS; Lab Lab 12: Regression for Prediction, Data Splitting
Mar 4: modeling risk, machine versus human predictions; Lab Lab 13: Model Selection

7 Week 07

Mar 9: a new physiognomy? thinking about what models are actually doing; Lab Lab 14: Feature Selection
Mar 11: allocation of resources and models; Lab Lab 15: Text Preprocessing

08 Week 08

Mar 16: surveillance, selection, and the ratchet effect; Lab Lab 16: Intro to Text Analysis (BOW)
Mar 18: remaining questions and discussion on predictions from “big data”; Lab Lab 17: Parse XML (Beautiful Soup)

09 Week 09

Mar 30: Guest: Isaac Dalke, Sociology; selecting into a dataset: thinking critically about what data are collected; Lab Lab 18: Regular Expressions
Apr 1: understanding how Old Bailey Proceedings data got made, content analysis of cases, outline of computational text analysis techniques; selecting into a dataset: thinking critically about what data are collected; Lab Lab 19: TF-IDF and Classification

10 Week 10

Apr 6: Marx, history, and law as indicator or constitutive; Lab Lab 20: Exploratory Data Analysis (feature extraction, visualizations, principal components analysis)
Apr 8: Guest: Dr. Lon Troyer, H5; Lab TAR and the legal profession

11 Week 11

Apr 13: the Old Bailey in its legal-historical context; Lab Lab 21: Neural Nets
Apr 15: wrap up on Old Bailey in its historical context; Lab Lab 22: Word Embedding

12 Week 12

Apr 20: Guest: Aniket Kesari, JSP; “text as social science evidence”; Lab Lab 23: Topic Models
Apr 22: Guest: Matt Cannon, JSP; text as social science evidence 2; Lab Lab 24: Sentiment: Morality

13 Week 13

Apr 27: text as social science evidence; Lab Lab 25: Ensemble Methods

10 Week 14

Apr 6: Marx, history, and law as indicator or constitutive; Lab Lab 20: Exploratory Data Analysis (feature extraction, visualizations, principal components analysis)
Apr 8: Guest: Dr. Lon Troyer, H5; Lab TAR and the legal profession

11 Week 15

Apr 13: the Old Bailey in its legal-historical context; Lab Lab 21: Neural Nets
Apr 15: wrap up on Old Bailey in its historical context; Lab Lab 22: Word Embedding