@InProceedings{joshi-EtAl:2016:COLING,
  author    = {Joshi, Aditya  and  Prabhu, Ameya  and  Shrivastava, Manish  and  Varma, Vasudeva},
  title     = {Towards Sub-Word Level Compositions for Sentiment Analysis of Hindi-English Code Mixed Text},
  booktitle = {Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers},
  month     = {December},
  year      = {2016},
  address   = {Osaka, Japan},
  publisher = {The COLING 2016 Organizing Committee},
  pages     = {2482--2491},
  abstract  = {Sentiment analysis (SA) using code-mixed data from social media has several
	applications in opinion mining ranging from customer satisfaction to social
	campaign analysis in multilingual societies. Advances in this area are impeded
	by the lack of a suitable annotated dataset. We introduce a Hindi-English
	(Hi-En) code-mixed dataset for sentiment analysis and perform empirical
	analysis comparing the suitability and performance of various state-of-the-art
	SA methods in social media.  
	In this paper, we introduce learning sub-word level representations in our LSTM
	(Subword-LSTM) architecture instead of character-level or word-level
	representations. This linguistic prior in our architecture enables us to learn
	the information about sentiment value of important morphemes. This also seems
	to work well in highly noisy text containing misspellings as shown in our
	experiments which is demonstrated in morpheme-level feature maps learned by our
	model. Also, we hypothesize that encoding this linguistic prior in the
	Subword-LSTM architecture leads to the superior performance. Our system attains
	accuracy 4-5% greater than traditional approaches on our dataset, and also
	outperforms the available system for sentiment analysis in Hi-En code-mixed
	text by 18%.},
  url       = {http://aclweb.org/anthology/C16-1234}
}