hasadna / knesset-data-pipelines

Main repository for Open Knesset project - contains the knesset data scrapers and processing pipelines
https://oknesset.org/
MIT License
14 stars 26 forks source link

classify committee sessions related to law process #177

Closed OriHoch closed 4 years ago

OriHoch commented 4 years ago

classify committee sessions with boolean values - related / not related to law processes

following classifications should be exposed:

  1. related_to_bill: if sessions is related to a bill item (according to committees_kns_cmtsessionitem item type 2)
  2. has_bill_keywords: kns_committeesession Note or Topics fields contain the following keywords: `חוק' / 'תקנות' / 'צו'
  3. ml_bill_classified: use the protocols machine learning project done in Bar Ilan University to get additional keywords / algorithm for this classification TBD
OriHoch commented 4 years ago
  1. done in the detailed speaker stats package show notebook
  2. handled in #182
  3. handled in #183