Article Structure
Abstract
The translation of sentiment information is a task from which sentiment analysis systems can benefit.
Introduction
Sentiment analysis is an important topic in computational linguistics that is of theoretical interest but also implies many real-world applications.
Related Work
The translation of sentiment information has been the topic of multiple publications.
Bilingual Lexicon Induction
Typical approaches to the induction of bilingual lexicons involve gathering new information from a small set of known identities between the languages which is called a seed lexicon and incorporating intralingual sources of information (e.g.
Sentiment Transfer
Although unsupervised methods for the design of sentiment analysis systems exist, any approach can benefit from using resources that have been established in other languages.
Experiments
5.1 Baseline Method (SO-PMI)
Conclusion and Outlook
We presented a novel approach to the translation of sentiment information that outperforms SO-PMI, an established method.
Topics
sentiment analysis
- The translation of sentiment information is a task from which sentiment analysis systems can benefit.Page 1, “Abstract”
- Sentiment analysis is an important topic in computational linguistics that is of theoretical interest but also implies many real-world applications.Page 1, “Introduction”
- Usually, two aspects are of importance in sentiment analysis .Page 1, “Introduction”
- Work on sentiment analysis most often covers resources or analysis methods in a single language, usually English.Page 1, “Introduction”
- However, the transfer of sentiment analysis between languages can be advantageous by making use of resources for a source language to improve the analysis of the target language.Page 1, “Introduction”
- (2008) use machine translation for multilingual sentiment analysis .Page 1, “Related Work”
- Although unsupervised methods for the design of sentiment analysis systems exist, any approach can benefit from using resources that have been established in other languages.Page 2, “Sentiment Transfer”
- The automatic translation of this information could be beneficial for sentiment analysis in other languages.Page 6, “Conclusion and Outlook”
- Another important problem in sentiment analysis is the treatment of ambiguity.Page 6, “Conclusion and Outlook”
See all papers in Proc. ACL 2010 that mention sentiment analysis.
See all papers in Proc. ACL that mention sentiment analysis.
Back to top.
human judges
- To determine the sentiment of these adjectives, we asked 9 human judges , all native German speakers, to annotate them given the classes neutral, slightly negative, very negative, slightly positive, and very positive, reflecting the categories from the training data.Page 4, “Experiments”
- Since human judges tend to interpret scales differently, we examine their agreement using Kendall’s coefficient of concordance (W) including correction for ties (Legendre, 2005) which takes ranks into account.Page 4, “Experiments”
- Due to disagreements between the human judges there exists no clear threshold between these categories.Page 4, “Experiments”
- Auferstanden (resurrected) is perceived as a positive adjective by the human judges , however it is misclassified by SimRank as negative due to its occurrence with words like gestorben (deceased) and gekreuzigt (crucified) which have negative as-Page 5, “Experiments”
See all papers in Proc. ACL 2010 that mention human judges.
See all papers in Proc. ACL that mention human judges.
Back to top.
sentiment lexicon
- (2007) propose two methods for translating sentiment lexicons .Page 1, “Related Work”
- The first method simply uses bilingual dictionaries to translate an English sentiment lexicon .Page 1, “Related Work”
- The induction of a sentiment lexicon is the subject of early work by (Hatzivassiloglou and McKeown, 1997).Page 1, “Related Work”
- 5.3 Sentiment Lexicon InductionPage 4, “Experiments”
See all papers in Proc. ACL 2010 that mention sentiment lexicon.
See all papers in Proc. ACL that mention sentiment lexicon.
Back to top.
graph-based
- We present a novel, graph-based approach using SimRank, a well-established vertex similarity algorithm to transfer sentiment information between a source language and a target language graph.Page 1, “Abstract”
- Two examples of such methods are a graph-based approach by Dorow et al.Page 2, “Bilingual Lexicon Induction”
- In this paper, we will employ the graph-based method.Page 2, “Bilingual Lexicon Induction”
See all papers in Proc. ACL 2010 that mention graph-based.
See all papers in Proc. ACL that mention graph-based.
Back to top.
