Multilingual Subjectivity: Are More Languages Better?

Description:

This paper discusses multilingual subjectivity.

Creator(s):
Creation Date: August 2010
Partner(s):
UNT College of Engineering
Collection(s):
UNT Scholarly Works
Usage:
Total Uses: 67
Past 30 days: 2
Yesterday: 0
Creator (Author):
Banea, Carmen

University of North Texas

Creator (Author):
Mihalcea, Rada, 1974-

University of North Texas

Creator (Author):
Wiebe, Janyce M.

University of Pittsburgh

Date(s):
  • Creation: August 2010
Description:

This paper discusses multilingual subjectivity.

Degree:
Note:

Abstract: While subjectivity related research in other languages has increased, most of the work focuses on single languages. This paper explores the integration of features originating from multiple languages into a machine learning approach to subjectivity analysis, and aims to show that this enriched feature set provides for more effective modeling for the source as well as the target languages. We show not only that they are able to achieve over 75% macro accuracy in all of the six languages they experiment with, but also that by using features drawn from multiple languages they can construct high-precision meta-classifiers with a precision of over 83%.

Physical Description:

9 p.

Language(s):
Subject(s):
Keyword(s): subjectivity analysis | meta-classifiers | sentiment analysis | text-to-speech synthesis
Source: International Conference on Computational Linguistics (COLING), 2010, Beijing, China
Contributor(s):
Partner:
UNT College of Engineering
Collection:
UNT Scholarly Works
Identifier:
  • ARK: ark:/67531/metadc31025
Resource Type: Paper
Format: Text
Rights:
Access: Public