NNContextSentiment is a package for Sentiment Analysis using neural networks based on libary LibN3L.
This is the code of AAAI 2016 papers:
Yafeng Ren, Yue Zhang, Meishan Zhang, Donghong Ji. Improving Twitter Sentiment Classification Using Topic-Enriched Multi-Prototype Word Embeddings. In Proceedings of the AAAI 2016. 2016.02.
Yafeng Ren, Yue Zhang, Meishan Zhang, Donghong Ji. Context-Sensitive Twitter Sentiment Classification Using Neural Network. In Proceedings of the AAAI 2016. 2016.02.
Some issues:
- For the first paper, please ignore the contextual features (one line per example, of which the first column denotes the sentiment polarity and other columns denote sentential words; examples are seperated by an empty line.);
- For the second paper, you would better refer to another implementation by Da Pan, a student of mine. This version does not include the character embeddings.
I'll give more readable implementations soon.
Any questions, please email to meishan zhang