Strengths and Weaknesses of Text Analysis

Chris Bail, Duke University
SICSS, Day 3

Qualitative Detail/Context

Big/Abundant

List of Interesting Text-Datasets for Social Scientists

There a vast amount of data out there that has already been compiled (e.g. The New York Times, Reuters, Google, Wikipedia)

Here is a crowd-sourced list that I curate.

Non-Reactive

Measuring Ideas/Ideology

WEAKENESSES OF AUTOMATED TEXT ANALYSIS

Unstructured/Dirty

"Publication"/Elite Bias

Polysemy/Hidden Meaning

Limits of Measurement

Non-Findings

TYPES OF QUANTITATIVE TEXT ANALYSIS

Grimmer and Stewart's Decision Tree