Tools and data for syntactic analysis of the Sept. 26, 2016 debate between Hillary Clinton and Donald Trump
| File | Explanation |
|---|---|
| transcript_raw.txt | Raw transcript, copied from CBSNews.com |
| get_sentences_and_speakers.py | Python script used to list sentences and speakers, one sentence per line |
| transcript_formatted.txt | Formatted transcript, listing speaker and sentence; output of the Python script |
| transcript_analysis.txt | Output using the sentences option in mccawley-bulk |
| transcript_analysis.xslx | Same content as transcript_analysis.txt, formatted in Excel |
| USEFUL.sh | Template of handy CLI commands to extract useful numbers and data |
| english_stop_words.txt | List of English stopwords used for this analysis |
| get_words.clj | Clojure code useful for analyzing words and syllables |
| results.xlsx | Aggregate results, formatted in Excel |