Towards Sub-Word Level Compositions for Sentiment Analysis of Hindi-English Code Mixed Text
This work addresses sentiment analysis for multilingual social media users, but it is incremental as it builds on existing LSTM methods with a linguistic prior.
The paper tackles sentiment analysis of Hindi-English code-mixed text by introducing a new dataset and a Subword-LSTM architecture that learns sub-word level representations, achieving 4-5% higher accuracy than traditional methods and outperforming an existing system by 18%.
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 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%.