Multilingual Corpus Development for Opinion Mining
Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC 2010)
Abstract
Opinion Mining is a discipline that has attracted some attention lately. Most of the research in this field has been done for English or Asian languages, due to the lack of resources in other languages. In this paper we describe an approach of building a manually annotated multilingual corpus for the domain of product reviews, which can be used as a basis for fine-grained opinion analysis also considering direct and indirect opinion targets. For each sentence in a review, the mentioned product features with their respective opinion polarity and strength on a scale from 0 to 3 are labelled manually by two annotators. The languages represented in the corpus are English, German and Spanish and the corpus consists of about 500 product reviews per language. After a short introduction and a description of related work, we illustrate the annotation process, including a description of the annotation methodology and the developed tool for the annotation process. Then first results on the inter-annotator agreement for opinions and product features are presented. We conclude the paper with an outlook on future work.