Twitter hate aspect extraction using association analysis and dictionary-based approach

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F62690094%3A18450%2F17%3A50013660" target="_blank" >RIV/62690094:18450/17:50013660 - isvavai.cz</a>

Result on the web

<a href="http://dx.doi.org/10.3233/978-1-61499-800-6-641" target="_blank" >http://dx.doi.org/10.3233/978-1-61499-800-6-641</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.3233/978-1-61499-800-6-641" target="_blank" >10.3233/978-1-61499-800-6-641</a>

Result language

angličtina

Original language name

Twitter hate aspect extraction using association analysis and dictionary-based approach

Original language description

Recent research regarding hate speech is in the domain of social sciences and psychology. From these trends, the dissemination of hate speech and antagonistic content in social media has not been extensively studies from the perspective of sentiment analysis. In this paper, the main studies concerned about aspect-based sentiment analysis through twitter as the most popular social media communication in the world as they have 313 million active users worldwide. This paper initiate to address the shortcomings of implied aspects specific for hate crime domain. The expected beneficial hate aspects can be extracted from twitter based on combination of both analysis. The evaluation with researcher&apos;s own Hate Crime Twitter Sentiment (HCTS) dataset and also Hate Speech Twitter Datasoft (HSTD) was shown that the proposed approach is effective and produces significantly better results than baselines method.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

S - Specificky vyzkum na vysokych skolach

Publication year

2017

Confidentiality

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

Article name in the collection

Frontiers in Artificial Intelligence and Applications

ISBN

978-1-61499-799-3

ISSN

0922-6389

e-ISSN

neuvedeno

Number of pages

11

Pages from-to

641-651

Publisher name

IOS press

Place of publication

Amsterdam

Event location

Kitakyushu; Japan

Event date

Sep 26, 2017

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—