pastatimes / Master-Thesis-HateSpeech-Twitter

A comparison of hatespeech in political tweets from June 2015 to March 2020
0 stars 0 forks source link

### **Guidelines for hate speech detection** #5

Closed pastatimes closed 4 years ago

pastatimes commented 4 years ago

Guidelines for hate speech detection

Below are some instructions on the questions you have to answer for this job.

Target groups (X):

  1. (ILLEGAL) IMMIGRANTS, REFUGEES AND MIGRANTS
  2. NATIONALITIES, ETHNICITIES AND COUNTRIES
  3. RELIGIONS

Hate Speech

While answering the question "Is this tweet hateful?", you must take into account the following aspects:

A. the tweet content MUST have X as main TARGET, or even a single individual, but considered for his/her membership in that category (and NOT for the individual characteristics) B. we must deal with a message that spreads, incites, promotes or justifies HATRED OR VIOLENCE TOWARDS THE TARGET, or a message that aims at dehumanizing, hurting or intimidating the target. A tweet can be considered hateful if both of these conditions are true AND/OR at least one of the following statements is true:

• it implies or legitimates discriminating attitudes or policies against the given target • there is an allusion to a potential threat posed by the presence of the target, or its alleged outnumbering with respect to the native population • there is a sense of dissatisfaction and frustration, which may also result in overt hostility, due to the (perceived) privileged treatment granted to the target group by the government • there is the reference (whether explicit or just implied) to violent actions of any kind perpetrated against the given target of the message

Examples of tweets that are NOT hate speech

NOT HATEFUL tweet: A. It does not incite hatred: Hundreds of Syrian refugees started crossing the border from Lebanon on Saturday. B. It does not have X as main target: @campaignforleo Ireland is a neutral and independent country which is NOT part of any military alliance. Please do not forget that and act like Ireland is a vassal state of the UK or the EU. PLEASE DO NOT ENGAGE IN STUPID and DAMAGING ACTIONS AGAINST RUSSIA. Keep good relations with Russia!

Offensive Language

While answering the question "Is this tweet offensive?", you must take into account the following aspects:

A. the tweet content MUST have X as main TARGET, or even a single individual, but considered for his/her membership in that category (and NOT for the individual characteristics) B. we must deal with a message that focuses on the potentially HURTFUL EFFECT of the tweet content on a given target

A tweet can be considered offensive if both of these conditions are true AND/OR at least one of the following statements is true: • the given target is associated with typical human flaws, or in general negative characteristics • the status of the target group is questioned • the members of the target group are described, or just considered, unpleasant people, or just the kind of people you better have nothing to do with • there is derisive intent • the target group is addressed to by means of outrageous or degrading expressions • An overtly insulting language is used

Neutral language

If none of these previous conditions apply, then your answer will be 'Neutral'

Originally posted by @pastatimes in https://github.com/pastatimes/Master-Thesis-Trump-tweets/issues/1#issuecomment-626390710