Understanding Abuse: A Typology of Abusive Language Detection Subtasks

نویسندگان

  • Zeerak Waseem
  • Thomas Davidson
  • Dana Warmsley
  • Ingmar Weber
چکیده

As the body of research on abusive language detection and analysis grows, there is a need for critical consideration of the relationships between different subtasks that have been grouped under this label. Based on work on hate speech, cyberbullying, and online abuse we propose a typology that captures central similarities and differences between subtasks and we discuss its implications for data annotation and feature construction. We emphasize the practical actions that can be taken by researchers to best approach their abusive language detection subtask of interest.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Do Characters Abuse More Than Words?

Although word and character n-grams have been used as features in different NLP applications, no systematic comparison or analysis has shown the power of character-based features for detecting abusive language. In this study, we investigate the effectiveness of such features for abusive language detection in user-generated online comments, and show that such methods outperform previous state-of...

متن کامل

Sexting: a Typology

This bulletin presents a typology of sexting episodes based on a review of over 550 cases obtained from a national sur‐ vey of law enforcement agencies. The cases all involved " youth‐produced sexual images, " defined as images of minors created by minors that could qualify as child pornography under applicable criminal statutes. The episodes could be broadly divided into two categories, which ...

متن کامل

Improving Fraud and Abuse Detection in General Physician Claims: A Data Mining Study

Background We aimed to identify the indicators of healthcare fraud and abuse in general physicians’ drug prescription claims, and to identify a subset of general physicians that were more likely to have committed fraud and abuse.   Methods We applied data mining approach to a major health insurance organization dataset of private sector general physicians’ prescription claims. It involved 5 ste...

متن کامل

Abuse of people with dementia by family carers: representative cross sectional survey

OBJECTIVE To determine the prevalence of abusive behaviours by family carers of people with dementia. DESIGN Representative cross sectional survey SETTING Community mental health teams in Essex and London. PARTICIPANTS 220 family carers of people newly referred to secondary psychiatric services with dementia who were living at home. MAIN OUTCOME MEASURE Psychological and physical abuse ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:
  • CoRR

دوره abs/1705.09899  شماره 

صفحات  -

تاریخ انتشار 2017