Sentiment Extraction From Bangla Text : A Character Level Supervised Recurrent Neural Network Approach

摘要

Over the recent years, people are heavily getting involved in the virtual world to express their opinions and feelings. Each second, hundreds of thousands of data are being gathered in the social media sites. Extraction of information from these data and finding their sentiments is known as a sentiment analysis. Sentiment analysis (SA) is an autonomous text summarization and analysis system. It is one of the most active research areas in the field of NLP and also widely studied in data mining, web mining and text mining. The significance of sentiment analysis is picking up day by day due to its direct impact on various businesses. However, it is not so straightforward to extract the sentiments when it comes to the Bangla language because of its complex grammatical structure. In this paper, a deep learning model was developed to train with Bangla language and mine the underlying sentiments. A critical analysis was performed to compare with a different deep learning model across different representation of words. The main idea is to represent Bangla sentence based on characters and extract information from the characters using a Recurrent Neural Network (RNN). These extracted information are decoded as positive, negative and neutral sentiment.