1
2
3
4
5
6
7
8
9
10
11
12
13
|
- preprocessing:
- stopwords: ["check against delivery", "check delivery", "introduction", "video recording", "as delivered", "version as delivered", "distinguished", "mr", "mrs", "mr.", "mrs.", "ms.", "ms", "sir", "madam", "madame", "chairman", "chairmen", "chairwoman", "chairwomen", "chairperson", "chairpeople", "excellency", "excellencies", "majesty", "majesties", "highness", "highnesses", "royal", "honorable", "president", "king", "prince", "queen", "princess", "delegate", "delegates", "gentlemen", "ladies", "lady", "gentleman", "ministers", "'s", "also", "must", "would", "also", "refugee", "refugees", "unhcr", "united_nations", "united", "nations", "country", "year", "ha", "wa", "high_commissioner", "high", "commissioner", "de", "la", "un", "en", "los", "el", "que"]
- punctuation: [',', '.', ';', ':', '?', '!', '/', '-', '--', '(', ')', '–', '``' , ' ', '*']
- ngrams:
- min: 1
- max: 3
- df:
- min: 3
- max: 0.8
- lda:
- passes: 50
- iterations: 500
- num_topics: 10
|