This repository contains code for paper "Sentiment Analysis of Sinhala News Comments using Sentence-State LSTM Networks"
Different types of deep learning based sentiment classification techniques have been introduced for sentiment analysis, and for Natural Language Processing, in general. However, Sinhala, which is a low resourced, yet morphologically rich language, has not experienced these recent advancements. In particular, for sentiment analysis, there is only one research that used deep learning techniques, and that also gave sub-optimal results. In this paper, we present the use of a novel state-of-the-art deep learning technique called sentence state long short-term memory network for Sinhala sentiment classification. On a binary sentiment classification task, this method outperforms both the previously reported statistical machine learning algorithms and deep learning algorithms.
[1] Y. Zhang, Q. Liu, and L. Song, Sentence-state LSTM for text representation ,arXiv preprint arXiv:1805.02474, 2018.