Pregled bibliografske jedinice broj: 861018
Analysis of Policy Agendas: Lessons Learned from Automatic Topic Classification of Croatian Political Texts.
Analysis of Policy Agendas: Lessons Learned from Automatic Topic Classification of Croatian Political Texts. // Annual meeting of the Association for Computational Linguistics, 10th SIGHUM Workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities. / Reiter, Niels ; Alex, Beatrice (ur.).
Berlin: Taberg Media Group AB za Association for Computational Linguistics (ACL), 2016. str. 12-22 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 861018 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Analysis of Policy Agendas: Lessons Learned
from Automatic Topic Classification of Croatian
Political Texts.
Autori
Karan, Mladen ; Šnajder, Jan ; Širinić, Daniela ; Glavaš, Goran
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
ISBN
978-1-945626-09-8
Skup
Annual meeting of the Association for Computational Linguistics, 10th SIGHUM Workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities.
Mjesto i datum
Berlin, Njemačka, 07.08.2016. - 12.08.2016
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
Policy agendas ; supervised topic classification ; accuracy-efficiency trade-off
Sažetak
Policy agenda research is concerned with measuring the policymaker activities. Topic classification has proven a valuable tool for policy agenda research. However, manual topic coding is extremely costly and time-consuming. Supervised topic classification offers a cost- effective and reliable alternative, yet it introduces new challenges, the most significant of which are the training set coding, classifier design, and accuracy-efficiency trade-off. In this work, we address these challenges in the context of the recently launched Croatian Policy Agendas project. We describe a new policy agenda dataset, explore the many system design choices, and report on the in- sights gained. Our best-performing model reaches 77% and 68% of F1- score for ma- jor topics and subtopics, respectively.
Izvorni jezik
Engleski
Znanstvena područja
Računarstvo, Politologija
POVEZANOST RADA
Projekti:
036-1300646-1986 - Otkrivanje znanja u tekstnim podacima (Dalbelo-Bašić, Bojana, MZO ) ( CroRIS)
Ustanove:
Fakultet političkih znanosti, Zagreb,
Fakultet elektrotehnike i računarstva, Zagreb
