Home WakeSpace Scholarship › Open Access Fund Publications

Classifying Hate Speech Using a Two-Layer Model

Open Access Fund Publications

Item Files

Item Details

abstract
Social media and other online sites are being increasingly scrutinized as platforms for cyberbullying and hate speech. Many machine learning algorithms, such as support vector machines, have been adopted to create classification tools to identify and potentially filter patterns of negative speech. While effective for prediction, these methodologies yield models that are difficult to interpret. In addition, many studies focus on classifying comments as either negative or neutral, rather than further separating negative comments into subcategories. To address both of these concerns, we introduce a two-stage model for classifying text. With this model, we illustrate the use of internal lexicons, collections of words generated from a pre-classified training dataset of comments that are specific to several subcategories of negative comments. In the first stage, a machine learning algorithm classifies each comment as negative or neutral, or more generally target or nontarget. The second stage of model building leverages the internal lexicons (called L2CLs) to create features specific to each subcategory. These features, along with others, are then used in a random forest model to classify the comments into the subcategories of interest. We demonstrate our approach using two sets of data.
subject
Hate speech
Lexicon
Sentiment analysis
contributor
Tang, Y. (author)
Dalzell, N. (author)
date
2020-03-23T18:35:25Z (accessioned)
2020-03-23T18:35:25Z (available)
10/1/19 (issued)
identifier
Tang, Y., & Dalzell, N. (2019). Classifying Hate Speech Using a Two-Layer Model. Statistics and Public Policy, 6(1), 80-86. (citation)
https://doi.org/10.1080/2330443X.2019.1660285 (doi)
http://hdl.handle.net/10339/96606 (uri)
language
en (iso)
publisher
Taylor and Francis
rights
https://creativecommons.org/licenses/by/4.0/ (uri)
source
Statistics and Public Policy
title
Classifying Hate Speech Using a Two-Layer Model
type
Article

Usage Statistics