search

SvenElyes / Textanalytics

MIT License
1 stars 0 forks source link

Keywords - Processing - extract keywords for character #9

Open aileen-reichelt opened 3 years ago

aileen-reichelt commented 3 years ago

For the character in question, we want to extract keywords from those passages of text where to character is mentioned. For this, we need to

  1. find relevant text passages (see issue "assign character to text")
  2. determine size of context to be considered (e. g. 10 word before and after character name is mentioned)
  3. apply keyword extraction algorithm (YAKE) to this context

The pre-processing for YAKE is already included in the existing Python YAKE implementation.

aileen-reichelt commented 3 years ago

Partly solved with 40120848e9b0139a35acb26761fec279aa0c663c. Still to do: change context from verse to 20 words and tie in with other code