A comparison of machine learning approaches for detecting misogynistic speech in urban dictionary

Theo Lynn; Patricia Takako Endo; Pierangelo Rosati; Ivanovitch Silva; Guto Leoni Santos; Debbie Ging

doi:10.1109/CyberSA.2019.8899669

A comparison of machine learning approaches for detecting misogynistic speech in urban dictionary

Theo Lynn
, Patricia Takako Endo
, Pierangelo Rosati
, Ivanovitch Silva
, Guto Leoni Santos
, Debbie Ging

Dublin City University
Federal University of Rio Grande do Norte
Universidade Federal de Pernambuco

Research output: Chapter in Book or Conference Publication/Proceeding › Conference Publication › peer-review

28 Citations (Scopus)

Abstract

Recent moves to consider misogyny as a hate crime have refocused efforts for owners of web properties to detect and remove misogynistic speech. This paper considers the use of deep learning techniques for detection of misogyny in Urban Dictionary, a crowdsourced online dictionary for slang words and phrases. We compare the performance of two deep learning techniques, Bi-LSTM and Bi-GRU, to detect misogynistic speech with the performance of more conventional machine learning techniques, logistic regression, Naive-Bayes classification, and Random Forest classification. We find that both deep learning techniques examined have greater accuracy in detecting misogyny in the Urban Dictionary than the other techniques examined.

Original language	English
Title of host publication	2019 International Conference on Cyber Situational Awareness, Data Analytics and Assessment, Cyber SA 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728102320
DOIs	https://doi.org/10.1109/CyberSA.2019.8899669
Publication status	Published - Jun 2019
Externally published	Yes
Event	2019 International Conference on Cyber Situational Awareness, Data Analytics and Assessment, Cyber SA 2019 - Oxford, United Kingdom Duration: 3 Jun 2019 → 4 Jun 2019

Publication series

Name	2019 International Conference on Cyber Situational Awareness, Data Analytics and Assessment, Cyber SA 2019

Conference

Conference	2019 International Conference on Cyber Situational Awareness, Data Analytics and Assessment, Cyber SA 2019
Country/Territory	United Kingdom
City	Oxford
Period	3/06/19 → 4/06/19

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 5 Gender Equality

Keywords

Deep learning
Hate speech
LSTM
Machine learning
Misogyny
Recurrent neural networks
Urban dictionary

Access to Document

10.1109/CyberSA.2019.8899669

Cite this

Lynn, T., Endo, P. T., Rosati, P., Silva, I., Santos, G. L., & Ging, D. (2019). A comparison of machine learning approaches for detecting misogynistic speech in urban dictionary. In 2019 International Conference on Cyber Situational Awareness, Data Analytics and Assessment, Cyber SA 2019 Article 8899669 (2019 International Conference on Cyber Situational Awareness, Data Analytics and Assessment, Cyber SA 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CyberSA.2019.8899669

Lynn, Theo ; Endo, Patricia Takako ; Rosati, Pierangelo et al. / A comparison of machine learning approaches for detecting misogynistic speech in urban dictionary. 2019 International Conference on Cyber Situational Awareness, Data Analytics and Assessment, Cyber SA 2019. Institute of Electrical and Electronics Engineers Inc., 2019. (2019 International Conference on Cyber Situational Awareness, Data Analytics and Assessment, Cyber SA 2019).

@inproceedings{55b9770ac9604f4c97bc627ae3a9fdbe,

title = "A comparison of machine learning approaches for detecting misogynistic speech in urban dictionary",

abstract = "Recent moves to consider misogyny as a hate crime have refocused efforts for owners of web properties to detect and remove misogynistic speech. This paper considers the use of deep learning techniques for detection of misogyny in Urban Dictionary, a crowdsourced online dictionary for slang words and phrases. We compare the performance of two deep learning techniques, Bi-LSTM and Bi-GRU, to detect misogynistic speech with the performance of more conventional machine learning techniques, logistic regression, Naive-Bayes classification, and Random Forest classification. We find that both deep learning techniques examined have greater accuracy in detecting misogyny in the Urban Dictionary than the other techniques examined.",

keywords = "Deep learning, Hate speech, LSTM, Machine learning, Misogyny, Recurrent neural networks, Urban dictionary",

author = "Theo Lynn and Endo, \{Patricia Takako\} and Pierangelo Rosati and Ivanovitch Silva and Santos, \{Guto Leoni\} and Debbie Ging",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 2019 International Conference on Cyber Situational Awareness, Data Analytics and Assessment, Cyber SA 2019 ; Conference date: 03-06-2019 Through 04-06-2019",

year = "2019",

month = jun,

doi = "10.1109/CyberSA.2019.8899669",

language = "English",

series = "2019 International Conference on Cyber Situational Awareness, Data Analytics and Assessment, Cyber SA 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2019 International Conference on Cyber Situational Awareness, Data Analytics and Assessment, Cyber SA 2019",

}

Lynn, T, Endo, PT, Rosati, P, Silva, I, Santos, GL & Ging, D 2019, A comparison of machine learning approaches for detecting misogynistic speech in urban dictionary. in 2019 International Conference on Cyber Situational Awareness, Data Analytics and Assessment, Cyber SA 2019., 8899669, 2019 International Conference on Cyber Situational Awareness, Data Analytics and Assessment, Cyber SA 2019, Institute of Electrical and Electronics Engineers Inc., 2019 International Conference on Cyber Situational Awareness, Data Analytics and Assessment, Cyber SA 2019, Oxford, United Kingdom, 3/06/19. https://doi.org/10.1109/CyberSA.2019.8899669

A comparison of machine learning approaches for detecting misogynistic speech in urban dictionary. / Lynn, Theo; Endo, Patricia Takako; Rosati, Pierangelo et al.
2019 International Conference on Cyber Situational Awareness, Data Analytics and Assessment, Cyber SA 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 8899669 (2019 International Conference on Cyber Situational Awareness, Data Analytics and Assessment, Cyber SA 2019).

Research output: Chapter in Book or Conference Publication/Proceeding › Conference Publication › peer-review

TY - GEN

T1 - A comparison of machine learning approaches for detecting misogynistic speech in urban dictionary

AU - Lynn, Theo

AU - Endo, Patricia Takako

AU - Rosati, Pierangelo

AU - Silva, Ivanovitch

AU - Santos, Guto Leoni

AU - Ging, Debbie

PY - 2019/6

Y1 - 2019/6

N2 - Recent moves to consider misogyny as a hate crime have refocused efforts for owners of web properties to detect and remove misogynistic speech. This paper considers the use of deep learning techniques for detection of misogyny in Urban Dictionary, a crowdsourced online dictionary for slang words and phrases. We compare the performance of two deep learning techniques, Bi-LSTM and Bi-GRU, to detect misogynistic speech with the performance of more conventional machine learning techniques, logistic regression, Naive-Bayes classification, and Random Forest classification. We find that both deep learning techniques examined have greater accuracy in detecting misogyny in the Urban Dictionary than the other techniques examined.

AB - Recent moves to consider misogyny as a hate crime have refocused efforts for owners of web properties to detect and remove misogynistic speech. This paper considers the use of deep learning techniques for detection of misogyny in Urban Dictionary, a crowdsourced online dictionary for slang words and phrases. We compare the performance of two deep learning techniques, Bi-LSTM and Bi-GRU, to detect misogynistic speech with the performance of more conventional machine learning techniques, logistic regression, Naive-Bayes classification, and Random Forest classification. We find that both deep learning techniques examined have greater accuracy in detecting misogyny in the Urban Dictionary than the other techniques examined.

KW - Deep learning

KW - Hate speech

KW - LSTM

KW - Machine learning

KW - Misogyny

KW - Recurrent neural networks

KW - Urban dictionary

UR - https://www.scopus.com/pages/publications/85071578374

U2 - 10.1109/CyberSA.2019.8899669

DO - 10.1109/CyberSA.2019.8899669

M3 - Conference Publication

T3 - 2019 International Conference on Cyber Situational Awareness, Data Analytics and Assessment, Cyber SA 2019

BT - 2019 International Conference on Cyber Situational Awareness, Data Analytics and Assessment, Cyber SA 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2019 International Conference on Cyber Situational Awareness, Data Analytics and Assessment, Cyber SA 2019

Y2 - 3 June 2019 through 4 June 2019

ER -

Lynn T, Endo PT, Rosati P, Silva I, Santos GL, Ging D. A comparison of machine learning approaches for detecting misogynistic speech in urban dictionary. In 2019 International Conference on Cyber Situational Awareness, Data Analytics and Assessment, Cyber SA 2019. Institute of Electrical and Electronics Engineers Inc. 2019. 8899669. (2019 International Conference on Cyber Situational Awareness, Data Analytics and Assessment, Cyber SA 2019). doi: 10.1109/CyberSA.2019.8899669

A comparison of machine learning approaches for detecting misogynistic speech in urban dictionary

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this