Sentiment Analysis with a Multilingual Pipeline, paper at Wise 2011
- Details
- Aangemaakt op vrijdag, 26 augustus 2011 14:44
- Geschreven door Arthur
In a previous post we mentioned the research from our interns on pitfalls in sentiment analysis in a multilingual environment, done last spring. We can now compliment them on having their research published at WISE'11 as a full paper. Congratulations Malissa and Daniella!
For readers traveling to Australia this October, as a teaser, hereby the abstract of the paper:
"Sentiment analysis refers to retrieving an author’s sentiment from a text. We analyze the differences that occur in sentiment scoring across languages. We present our experiments for the Dutch and English language based on forum, blog, news and social media texts available on the Web, where we focus on the differences in the use of a language and the effect of the grammar of a language on sentiment analysis. We propose a multilingual pipeline for evaluating how an author’s sentiment is conveyed in different languages. We succeed in correctly classifying positive and negative texts with an accuracy of approximately 71% for English and 79% for Dutch. The evaluation of the results shows however that usage of common expressions, emoticons, slang language, irony, sarcasm, and cynicism, acronyms and different ways of negation in English prevent the underlying sentiment scores from being directly comparable."
For readers not going, but interested in this area of crawling and sentiment analysis, contact us for more details.
