Sustav za analizu te analiza komentara novinskih članaka

master's thesis

• Title (english): System for analysis, and analysis of news articles comments
• Author: Silvana Bakula
• Mentor: Stjepan Groš (mentor)
• Committee member: Stjepan Groš (predsjednik povjerenstva)
• Committee member: Jan Šnajder (član povjerenstva)
• Committee member: Dejan Škvorc (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2022-09-30, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Internet je omogućio nastanak mnogih portala i društvenih mreža preko kojih se prenose vijesti iz svih domena. Određene teme pobuđuju visok interes javnosti i pokreću lavinu komentara. Porast računalne snage i memorijskih kapaciteta je omogućio pohranjivanje i analiziranje tih komentara. Cilj ovog rada je pokušati odgovoriti na pitanje je li moguće prepoznati i kvantificirati stil pisanja koji jedinstveno pripada svakom čovjeku i na taj način povezati komentar sa stvarnim autorom. Korištene su metode iz domene stilometrije u kombinaciji s algoritmima nadziranog strojnog učenja. Potrebno je pronaći način kako poboljšati robusnost modela da može rukovati s kratkim komentarima jer prema predloženoj shemi mali skup kratkih komentara nije dovoljan za prepoznavanje univerzalnog jezičnog obrasca.

Abstract (english)

The flow of news is growing every day on social media. Some topics arouse high interest in the public and trigger an avalanche of comments. Processors and memory capacity improvements have made it possible to save and process these comments. The main goal of this thesis is to answer if it is possible to extract and quantify linguistic features by which it is possible to distinguish different authors. Authorship attribution is implemented using stylometric techniques and supervised machine learning algorithms. It is necessary to improve the robustness of the model to be able to handle short comments because according to the proposed scheme a small set of short comments is not enough to recognise a universal writing style.

• Keywords: pripisivanje autorstva; stilometrija; strojno učenje; obrada prirodnog jezika
• Keywords (english): authorship attribution; stylometry; machine learning; natural language processing
• Language: croatian
• URN:NBN: urn:nbn:hr:168:060231
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-14 20:02:48