Logistic Regression

A gpu parallel logistic regression learning algorithm written in cuda.

Dataset and testing

• Sentiment analysis results of 50000 movie reviews from IMDb (25000 for training, 25000 for testing).
• Each data row contains occurrences of top 10/50/200/1000 frequent words in each review and its sentiment result (Positive / Negative).

Terms of use

Andrew L. Maas, Raymond E. Daly, Peter T. Pham, Dan Huang, Andrew Y. Ng, and Christopher Potts. (2011).
Learning Word Vectors for Sentiment Analysis.
The 49th Annual Meeting of the Association for Computational Linguistics (ACL 2011).