""" Keywords used by Program2_YouTube_API_Search_and_Classify.py This module defines: * Incident classification keyword lists * CATEGORY_MAP * CATEGORY_WEIGHTS The keyword lists are used to classify YouTube videos after retrieval. """ #=========================================================== # Keyword lists #=========================================================== BLASPHEMY_TERMS = [ "blasphemy", "blasphemous", "alleged blasphemy", "prophet muhammad", "holy prophet", "alleged prophet", "pbuh", "offensive islam remark", "offensive remark", "facebook post", "facebook status", "facebook comment", "facebook profile", "facebook account", "social media post", "religious post", "religious sentiments", "religious feelings", "quran", "quran desecration", "desecration", "desecrated", "alleged 'offensive' islam remark", "religious insult", "religious incitement", "false allegations of anti-Islam comments", "posted inflammatory content", "allegedly insulting the Prophet", "insulted islam", "insulting islam", "kaaba sharif insult on facebook", "insult the prophet", "insulted the prophet" ] #=========================================================== # Killings #=========================================================== KILLING_TERMS = [ "shot dead", "shot to death", "shot and killed", "kill", "killed", "killing", "murder", "murdered", "slain", "gunned down", "decomposed", "body found", "dead body", "recovered body", "recovered the body", "body recovered", "bodies recovered", "found dead", "behead", "beheaded", "hacked", "hacked to death", "chopped to death", "beat to death", "beaten to death", "strangled", "strangled to death", "died en route to the hospital", "custodial deaths", "throat slit", "hanging body", "hung himself", "hung herself", "fatal", "lynched", "butchered", "burned alive", "burnt alive" ] #=========================================================== # Missing / Abduction #=========================================================== MISSING_ABDUCTED_TERMS = [ # Missing "missing", "went missing", "reported missing", "has been missing", "still missing", "missing since", "disappeared", "disappearance", "untraceable", "not found", "whereabouts unknown", "never returned", "never arrived", "last seen", "lost contact", # Abduction "abduction", "abducted", "abducting", "kidnapped", "kidnapping", "kidnap", "forcibly taken", "forcefully taken", "taken away", "taken from", "dragged away", "picked up", "held captive", "held hostage", "confined", "detained against", "unlawfully detained", # Recovery "rescued", "recovered safely", "returned home" ] #=========================================================== # Rape #=========================================================== RAPE_TERMS = [ "gang rape", "gang-rape", "attempted gang rape", "attempted rape", "attempt to rape", "rape attempt", "raped", "raping", "rape" ] #=========================================================== # General Violence #=========================================================== GENERAL_VIOLENCE_TERMS = [ # General violence "attack", "attacked", "assault", "assaulted", "beaten", "beating", "stabbed", "stabbing", "injured", "injury", "harass", "harassed", "harassment", "threat", "threatened", "intimidated", "intimidation", "mob attack", "communal attack", "communal violence", "communal", "riot", "rioting", "false case", "false cases", "extortion", "extortionists", "forced conversion", "forced to convert", "boycott", "outrage among minorities", "removed from government service", "hurt over renaming Hindu luminaries' names", "obstructed a century-old indigenous cemetery burial", "forced Hindu school headmaster", "cultural outrage", "threatening forced removal", "police obstruction", "fascist ally", "bullets hit", "sexual assault", "sexual abuse", "sexual harassment", "sexual violence", "sexual exploitation", "sexual torture", "sexual misconduct", "indecent assault", "indecent behavior", "indecent proposal", "molest", "molested", "molestation", "eve teasing", "harassed sexually", "forced marriage", "forced to marry", "attempted forced marriage", "abducted for marriage", "kidnapped for marriage", "forced conversion and marriage", "outraging modesty" ] #=========================================================== # Religious Violence #=========================================================== RELIGIOUS_VIOLENCE_TERMS = [ # Religious institutions "temple", "mandir", "church", "monastery", "ashram", "pagoda", "cremation ground", "graveyard", "priest", "monk", "pastor", "purohit", "idol", "idols", "deity", "deities", "iskcon", "attempting to seize", "Cocktail explosions targeted St. Mary's Cathedral", # Common phrases "religious discrimination", "without a show-cause notice", "religious persecution", "religious intolerance", "religious hatred", "demanding release", "leave the village", "forced to flee" ] #=========================================================== # Property Damage #=========================================================== PROPERTY_DAMAGE_TERMS = [ # Fire / Arson "arson", "set fire", "burn", "burned", "burnt", "burning", "torched", "torch", "house burned", "shop burned", "temple burned", "business burned", "burned alive", # Theft / Robbery "theft", "stolen", "steal", "stole", "robbery", "robbed", "loot", "looted", "looting", "dacoity", "burglary", "burglarized", "extorting large sums and harassing", "property dispute", "throttled grocer", "Opponents harvested", "Hindu land via fake deeds", # Vandalism / Damage "vandal", "vandalized", "vandalism", "defaced", "destroy", "destroyed", "damage", "damaged", "demolish", "demolished", "ransack", "ransacked", "raided", "broken", "broke", "armed attacks and home demolitions", # Property-related phrases "house damaged", "shop damaged", "business establishment", "business premises", "house looted", "shop looted", "temple vandalized", "idol vandalized", "idol broken", "crops destroyed", "fish enclosure", "orchard", "fruit trees", "cash stolen", "gold ornaments", "valuable documents", "motorcycle stolen", "vehicle damaged", "vehicle burned", "boundary wall", "furniture destroyed" ] #=========================================================== # Land Grabbing #=========================================================== LAND_GRABBING_TERMS = [ # General "land grabbing", "land grab", "land grabber", "Land grabbers", "grabbed land", "grab land", "grabbed", "grabbing", "grab", # Possession / Occupation "occupied", "occupation", "occupied land", "illegal occupation", "illegal possession", "forcibly occupied", "forcefully occupied", "encroach", "encroached", "encroachment", "seized land", # Eviction "evict", "evicted", "eviction", "eviction notice", # Land disputes "land dispute", "disputed land", "ancestral land", "family land", "homestead", "homestead land", "agricultural land", # Lease-related "leased land", "lease cancellation", "lease cancelled", "lease canceled", "land protection committee", # Legal / Administrative "land office", "land registry", "registry office", "land record", "mutation", "deed", "forged deed", "fake deed", "land document", "property document", # Government land "khas land", "hill district council", "rubber plantation", "rubber cultivation", # Miscellaneous "boundary wall", "fence removed", "fencing", "land owner", "land ownership", "property ownership" ] EXCLUDE_TERMS = [ "committed suicide", "suicide", "suicidal" ] #=========================================================== # Category map #=========================================================== CATEGORY_MAP = { "Killings": KILLING_TERMS, "Rape": RAPE_TERMS, "Property Damage": PROPERTY_DAMAGE_TERMS, "Land Grabbing": LAND_GRABBING_TERMS, "Religious Violence": RELIGIOUS_VIOLENCE_TERMS, "General Violence": GENERAL_VIOLENCE_TERMS, "Blasphemy": BLASPHEMY_TERMS, "Missing/Abduction": MISSING_ABDUCTED_TERMS, } #=========================================================== # Category weights #=========================================================== CATEGORY_WEIGHTS = { "Killings": 10, "Rape": 10, "Property Damage": 8, "Land Grabbing": 8, "Religious Violence": 6, "General Violence": 5, "Blasphemy": 5, "Missing/Abduction": 6, }