Sinhala Sentiment Anlaysis using Deep Learning

This repository contains code for paper "Sentiment Analysis for Sinhala Language using DeepLearning Techniques"

Abstract of the Paper

Due to the high impact of the fast-evolving fields of machine learning and deep learning, Natural Language Processing (NLP) tasks have further obtained comprehensive performances for highly resourced languages such as English and Chinese. However Sinhala, which is an under-resourced language with a rich morphology, has not experienced these advancements. For sentiment analysis, there exists only two previous research with deep learning approaches, which focused only on document-level sentiment analysis for the binary case. They experimented with only three types of deep learning models. In contrast, this paper presents a much comprehensive study on the use of standard sequence models such as RNN, LSTM, Bi-LSTM, as well as more recent state-of-the-art models such as hierarchical attention hybrid neural networks, and capsule networks. Classification is done at document-level but with more granularity by considering POSITIVE, NEGATIVE, NEUTRAL, and CONFLICT classes. A data set of 15059 Sinhala news comments, annotated with these four classes and a corpus consists of 9.48 million tokens are publicly released. This is the largest sentiment annotated data set for Sinhala so far.

Download Data Set and Word Embedding Models

Word embedding models:

• FastText 300

Data set:

• Lankadeepa data set
• GossipLanka data set

Authors

• Lahiru Senevirathne
• Piyumal Demotte
• Binod Karunarathne
• Udyogi Munasinghe
• Dr Surangika Ranathunga

For now, cite our following papers if the work find useful:

@article{senevirathne2020sentiment,
  title={Sentiment Analysis for Sinhala Language using Deep Learning Techniques},
  author={Senevirathne, Lahiru and Demotte, Piyumal and Karunanayake, Binod and Munasinghe, Udyogi and Ranathunga, Surangika},
  journal={arXiv preprint arXiv:2011.07280},
  year={2020}
}