We present a new feature type named rating-based feature and evaluate the contribution of this feature to the task of document-level sentiment analysis. We achieve state-of-the-art results on two publicly available standard polarity movie datasets: on the dataset consisting of 2000 reviews produced by Pang and Lee (2004) we obtain an accuracy of 91.6% while it is 89.87% evaluated on the dataset of 50000 reviews created by Maas et al. (2011). We also get a performance at 93.24% on our own dataset consisting of 233600 movie reviews, and we aim to share this dataset for further research in sentiment polarity analysis task.
|Title of host publication||ACL 2014|
|Subtitle of host publication||5th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis: proceedings of the workshop|
|Place of Publication||Pennsylvania|
|Publisher||Association for Computational Linguistics (ACL)|
|Number of pages||8|
|Publication status||Published - 1 Jun 2014|