Modeli strojnog učenja za otkrivanje toksičnih komentara na Internetu

undergraduate thesis

• Title (english): Machine Learning Models for Toxic Comments Detection on the Internet
• Author: Martin Čolja
• Mentor: Jan Šnajder (mentor)
• Committee member: Jan Šnajder (predsjednik povjerenstva)
• Committee member: Domagoj Alagić (član povjerenstva)
• Committee member: Zoran Medić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2019-07-12, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Toksični komentari na internetu bespotrebno kradu pozornost svemu korisnome što nam internet pruža, stoga nije iznenađujuće da je njihovo rano otkrivanje postalo prioritet na mnogi društvenim mrežama. U ovom radu pokazano je kako se taj problem može riješiti pomoću klasifikacije koristeći metodu potpornih vektora. Navedene su do sad poznate metode klasifikacije te nekoliko situacija u kojima se klasifikacija koristila za potrebe slične potrebama ovog rada. Također proveden je i objašnjen eksperiment klasifikacije korištenjem SVM-a te su rezultati prikazani tablično. Dan je zaključak rada s osvrtom na postignute rezultate, te prijedlozima za daljnje unaprjeđenje rada.

Abstract (english)

Toxic comments on the Internet needlessly take attention away from all the benefits
that the Internet provides, so it’s not surprising that early detection of these comments
has become a priority on many social networks. This paper shows ways to solve this
problem by using classification, specifically the support vector machine method. Other
so far known methods of classification were listed alongside with the few situations
in which they were used similarly to the needs of this work. The experiment was
conducted using the SVM method as well as explained and analyzed with results shown
using tables. This work reaches a conclusion based on results in these tables and offers
suggestions on future work.

• Keywords: NLP; SVM; toksičnost; strojno učenje; umjetna inteligencija; govor mržnje
• Keywords (english): NLP; SVM; toxicity; machine learning; artificial intelligence; hate speach
• Language: croatian
• URN:NBN: urn:nbn:hr:168:721080
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2020-01-07 17:23:50