Antisocial Behavior corpus for harmful language detection

Author

Munezero, Myriam ; Mozgovoy, Maxim ; Kakkonen, Tuomo ; Klyuev, Vitaly ; Sutinen, Erkki

Author_Institution

Sch. of Comput., Univ. of Eastern Finland, Joensuu, Finland

fYear

2013

fDate

8-11 Sept. 2013

Firstpage

261

Lastpage

265

Abstract

We report on experiments that demonstrate the relevance of our AntiSocial Behavior (ASB) corpus as a machine learning resource to detect antisocial behavior from text. We first describe the corpus and then, by using the corpus for training machine learning algorithms, we build a set of binary classifiers. Experimental evaluations revealed that classifiers built based on the ASB corpus produce reliable classification results with up to 98% accuracy. We believe that the dataset will be valuable to researchers and practitioners working in preventing, controlling and diagnosing antisocial behavior and related problems.

Keywords

behavioural sciences computing; learning (artificial intelligence); natural language processing; pattern classification; social sciences computing; text analysis; ASB corpus; antisocial behavior corpus; binary classifiers; harmful language detection; machine learning algorithm training; machine learning resource; text antisocial behavior detection; Accuracy; Educational institutions; Electronic publishing; Encyclopedias; Internet; Motion pictures;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Science and Information Systems (FedCSIS), 2013 Federated Conference on

Conference_Location

Krako??w

Type

conf

Filename

6644010