Predviđanje vijestodostojnosti novinskih članaka pomoću strojnog učenja

undergraduate thesis

• Title (english): Predicting Newsworthiness of News Stories Using Machine Learning
• Author: Antonio Šajatović
• Mentor: Jan Šnajder (mentor)
• Committee member: Jan Šnajder (predsjednik povjerenstva)
• Committee member: Domagoj Alagić (član povjerenstva)
• Committee member: Martin Tutek (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2017-07-10, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Računalno predviđanje vijestodostojnosti nov je smjer istraživanja s primjenama
u praćenju događaja te sažimanju dokumenata, a potencijalnu primjenu ima u društvenim znanostima. Tema rada jest predviđanje vijestodostojnosti i emocija novinskih
članaka na engleskome jeziku temeljeno na strojnom učenju. Razvijena su dva generativna i jedan diskriminativni model za klasifikaciju vijestodostojnosti i emocija
na temelju naslova članaka u kategorije vijestodostojnosti koje su predložili Harcup
i O’Neill (2011) i šest osnovnih emocija. Na prikupljenoj zbirci naslova novinskih
članaka ručno označenih kategorijama vijestodostojnosti je provedeno učenje i vrednovanje modela te usporedbe s referentnim modelom.

Abstract (english)

The automatic prediction of newsworthiness is a new research direction with applications in event tracking and document summarization, and has potential applications
in social sciences. The topic of this thesis is the prediction of newsworthiness of news
stories and emotions in English using machine learning. Two generative and one discriminative model were developed for classifying newsworthiness and emotions into
newsworthiness categories proposed by Harcup and O’Neill (2011) and six basic emotions, based on the article headline. An experimental evaluation of the models and
comparisons against a baseline model were carried out on a compiled collection of
articles, manually labeled for newsworthiness.

• Keywords: obrada prirodnog jezika; strojno učenje; vijestodostojnost; emocije; stroj potpornih vektora; Bayesova mreža
• Keywords (english): natural language processing; machine learning; newsworthiness; emotions; support vector machine; Bayesian network
• Language: croatian
• URN:NBN: urn:nbn:hr:168:117198
• 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: 2019-03-14 01:03:42