#129 λλλ
Chapter 22 Facts
Number of paragraphs: 276
Number of sentences: 737
Number of tokens: 5,897
Number of unique tokens: 1,406
Number of speakers: 2
Grace : 902 tokens
Rocky : 540 tokens
Direct speech: 24.49% of tokens
Space: 4 sections; 100.00% of tokens
Words unusually frequent for Space sections:
generator, beetle, nose, power, tether.
Words unusually infrequent or lacking for Space sections:
thing, nitrogen, year, stuff.
For the sentences count, segmentation was performed using spaCy. Tokenization is just based on whitespace, em-dash, en-dash, and ellipsis delimiters. Unique tokens are case-insensitive.
Speaker identification was done manually.
Unusually frequent or infrequent words are based on log-likelihood of lemmas (lemmatization by spaCy).