keyword_text.py

keywords = {
    "online": ['online', 'technology', 'internet', 'web','social media', 
               'Facebook', 'chat', 'chatroom',  'digital', 'webcam', 'cyber'], 
    "children": ['children', 'child', 'minor', 'minors', 'infant', 'infants',
                 'underage', 'under-age', 'kid', 'teenager', 'teenagers', 'adolescent', 
                 'adolescents', 'girl', 'girls', 'boy', 'boys'], 
    "abuse":  ['abuse', 'abusive', 'exploiting', 'exploitation', 'harrassment', 
               'prostitution', 'groom', 'grooming', 'predator', 'predators', 
               'pedophile', 'paedophile', 'maltreatment', 'trafficking', 'violence'],
    "sexual": ['sex', 'sexual', 'pornography', 'pornographic']
    }

# Check text for search terms
def search_terms(text):
  searched = []
  for each in keywords:
    terms = keywords[each]

    if any(term in text for term in terms):
      searched.append(1)
    else:
      searched.append(0)
  return(1 if searched == [1, 1, 1, 1] else 0)

core_df['term_positive'] = core_df['cleaned_text'].map(lambda x: search_terms(x))

# Remove rows that don't meet search criteria
core_df = core_df[core_df['term_positive'] == 1]