State of the Union: Complete Presidential Transcripts from 1790 to Present

Housing transcripts of every United States State of the Union address, compiled by BrianWeinstein and last updated in July 2018. It serves as a longitudinal text corpus for analyzing presidential rhetoric and policy priorities across the history of the American presidency.

Use Cases

• Sentiment analysis of presidential transcripts to track rhetorical shifts over time
• Topic modeling on speech text to identify evolving legislative priorities
• Linguistic analysis of vocabulary complexity and word frequency across different presidential eras

Strengths

• Historical coverage of every SOTU address up to 2018
• Uniform text-based format for NLP tasks
• Longitudinal scope spanning over two centuries of political discourse

Limitations

• Lacks explicit metadata columns such as speaker name, party affiliation, or specific date in the provided schema
• No updates for addresses delivered between 2019 and the present
• Unknown file encoding and structure

Provenance

Source

BrianWeinstein (GitHub)

Time Range

1790-2018

Freshness

Stale; the repository has not been updated since 2018.

Geography

United States