Antisocial online behavior detection using deep learning

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F20%3A10423220" target="_blank" >RIV/00216208:11320/20:10423220 - isvavai.cz</a>

Výsledek na webu

<a href="https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=EdNDrUp~ng" target="_blank" >https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=EdNDrUp~ng</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.dss.2020.113362" target="_blank" >10.1016/j.dss.2020.113362</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Antisocial online behavior detection using deep learning

Popis výsledku v původním jazyce

Digitalization shifts human communication to online platforms, which has many benefits but also builds up a space for antisocial online behavior (AOB) such as harassment, insult and other forms of hateful textual content. Online platforms have good reasons to monitor and moderate such content. The paper examines the viability of automatic content monitoring using deep machine learning and natural language processing (NLP). More specifically, we consolidate prior work in the field of antisocial online behavior detection and compare relevant approaches to recent NLP models in an empirical study. Covering important methodological advancements in NLP including bidirectional encoding, attention, hierarchical text representations, and pre-trained transformer-based language models, and extending previous approaches by introducing a pseudo-sentence hierarchical attention network, the paper provides a comprehensive summary of the state-of-affairs in NLP-based AOB detection, clarifies the detection accuracy that is attainable with today&apos;s technology, discusses whether this degree is sufficient for deploying deep learning-based text screening systems, and approaches the interpretability topic.

Název v anglickém jazyce

Antisocial online behavior detection using deep learning

Popis výsledku anglicky

Digitalization shifts human communication to online platforms, which has many benefits but also builds up a space for antisocial online behavior (AOB) such as harassment, insult and other forms of hateful textual content. Online platforms have good reasons to monitor and moderate such content. The paper examines the viability of automatic content monitoring using deep machine learning and natural language processing (NLP). More specifically, we consolidate prior work in the field of antisocial online behavior detection and compare relevant approaches to recent NLP models in an empirical study. Covering important methodological advancements in NLP including bidirectional encoding, attention, hierarchical text representations, and pre-trained transformer-based language models, and extending previous approaches by introducing a pseudo-sentence hierarchical attention network, the paper provides a comprehensive summary of the state-of-affairs in NLP-based AOB detection, clarifies the detection accuracy that is attainable with today&apos;s technology, discusses whether this degree is sufficient for deploying deep learning-based text screening systems, and approaches the interpretability topic.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10103 - Statistics and probability

Projekt

<a href="/cs/project/GX19-28231X" target="_blank" >GX19-28231X: Dynamické modely pro digitální finance</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2020

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Decision Support Systems

ISSN

0167-9236

e-ISSN

—

Svazek periodika

138

Číslo periodika v rámci svazku

November 2020

Stát vydavatele periodika

NL - Nizozemsko

Počet stran výsledku

9

Strana od-do

113362

Kód UT WoS článku

000576663200004

EID výsledku v databázi Scopus

2-s2.0-85089579327