Please use this identifier to cite or link to this item:
Title: Potential and limitations of cross-domain sentiment classification
Authors : von Grünigen, Dirk
Weilenmann, Martin
Deriu, Jan Milan
Cieliebak, Mark
Proceedings: Proceedings of the Fifth International Workshop on Natural Language Processing for Social Media
Pages : 17
Pages to: 24
Conference details: Fifth International Workshop on Natural Language Processing for Social Media, Valencia, Spain, April 3-7, 2017
Publisher / Ed. Institution : Association for Computational Linguistics
Publisher / Ed. Institution: Stroudsburg PA, USA
Issue Date: Apr-2017
License (according to publishing contract) : Licence according to publishing contract
Type of review: Peer review (Publication)
Language : English
Subjects : Sentiment Analysis
Subject (DDC) : 004: Computer science
005: Computer programming, programs and data
Abstract: In this paper we investigate the cross-domain performance of sentiment analysis systems. For this purpose we train a con-volutional neural network (CNN) on data from different domains and evaluate its performance on other domains. Furthermore , we evaluate the usefulness of combining a large amount of different smaller annotated corpora to a large corpus. Our results show that more sophisticated approaches are required to train a system that works equally well on various domains.
Departement: School of Engineering
Organisational Unit: Institute of Applied Information Technology (InIT)
Publication type: Conference Paper
DOI : 10.18653/v1/W17-1103
ISBN: 9781510838710
Appears in Collections:Publikationen School of Engineering

Files in This Item:
File Description SizeFormat 
W17-1103.pdf1.67 MBAdobe PDFThumbnail

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