Title: Potential and limitations of commercial sentiment detection tools
Authors : Cieliebak, Mark
Dürr, Oliver
Uzdilli, Fatih
Proceedings: Proceedings of the First International Workshop on Emotion and Sentiment in Social and Expressive Media: approaches and perspectives from AI (ESSEM 2013)
Pages : 47
Pages to: 58
Conference details: First International Workshop on Emotion and Sentiment in Social and Expressive Media (ESSEM 2013), Turin, Italy, December 3 2013
Publisher / Ed. Institution : RWTH Aachen
Issue Date: 2013
License (according to publishing contract) : Licence according to publishing contract
Series : CEUR workshop proceedings
Series volume: 1096
Type of review: Not specified
Language : English
Subjects : Corpus analytics; Machine learning; Sentiment detection
Subject (DDC) : 005: Computer programming, programs and data
Abstract: In this paper, we analyze the quality of several commercial tools for sentiment detection. All tools are tested on nearly 30,000 short texts from various sources, such as tweets, news, reviews etc. In addition to the quality analysis (measured by various metrics), we also investigate the effect of increasing text length on the performance. Finally, we show that combining all tools using machine learning techniques increases the overall performance significantly.
Departement: School of Engineering
Organisational Unit: Institute of Applied Information Technology (InIT)
Institute of Data Analysis and Process Design (IDP)
Publication type: Conference Paper
ISBN: 1613-0073
URI: http://ceur-ws.org/Vol-1096/paper4.pdf
Other identifiers : urn:nbn:de:0074-1096-7
Appears in Collections:Publikationen School of Engineering

Files in This Item:
There are no files associated with this item.

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