Creating sentiment dictionaries via triangulation

Creating sentiment dictionaries via triangulation

The paper presents a semi-automatic approach to creating sentiment dictionaries in many languages. We firstproduced high-level gold-standard sentiment dictionaries for two languages and then translated themautomatically into third languages. Those words that can be found in both target language word lists are likelyto be useful because their word senses are likely to be similar to that of the two source languages. Thesedictionaries can be further corrected, extended and improved. In this paper, we present results that verifyour triangulation hypothesis, by evaluating triangulated lists and comparing them to non-triangulatedmachine-translated word lists.

Keywords: Sentiment analysis, dictionary creation, multilingual

Year: 2012

Journal ISSN: 0167-9236
Download: download Full text 
View record in Web of Science®

Authors of this publication:

Josef Steinberger


Josef is an associated professor at the Department of computer science and engineering at the University of West Bohemia in Pilsen, Czech Republic. He is interested in media monitoring and analysis, mainly automatic text summarisation, sentiment analysis and coreference resolution.

Related Projects:


Multilingual Sentiment Analysis

Authors:  Josef Steinberger
Desc.:Sentiment analysis of news and social media in multiple languages.