Please use this identifier to cite or link to this item:https://hdl.handle.net/20.500.12259/50967
Type of publication: research article
Type of publication (PDB): Straipsnis recenzuojamoje užsienio tarptautinės konferencijos medžiagoje / Article in peer-reviewed foreign international conference proceedings (P1d)
Field of Science: Informatika / Informatics (N009)
Author(s): Kapočiūtė-Dzikienė, Jurgita;Krupavičius, Algis;Krilavičius, Tomas
Title: A comparison of approaches for sentiment classification on Lithuanian internet comments
Is part of: ACL 2013 : proceedings of the 4th Biennial international workshop on Balto-Slavic natural language processing, August 8-9, 2013, Sofia, Bulgaria. Stroudsburg : Association for computational linguistics, 2013
Extent: p. 2-11
Date: 2013
Keywords: Komentarai internete;Klasifikavimas;Nuomonių analizė;Lietuvių kalba;Kalbos technologijos;Internet comments;Classification;Sentiment analysis;Lithuanian language;Language technologies
ISBN: 9781937284596
Abstract: Despite many methods that effectively solve sentiment classification task for such widely used languages as English, there is no clear answer which methods are the most suitable for the languages that are substantially different. In this paper we attempt to solve Internet comments sentiment classification task for Lithuanian, using two classification approaches - knowledge-based and supervised machine learning.[...]
Internet: https://hdl.handle.net/20.500.12259/50967
Affiliation(s): Baltijos pažangių technologijų institutas
Kauno technologijos universitetas
Appears in Collections:Universiteto mokslo publikacijos / University Research Publications

Files in This Item:
marc.xml6.12 kBXMLView/Open

MARC21 XML metadata

Show full item record
Export via OAI-PMH Interface in XML Formats
Export to Other Non-XML Formats


CORE Recommender

Page view(s)

81
checked on May 1, 2021

Download(s)

9
checked on May 1, 2021

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.