Article

Sentiment analysis of the burmese language using n-gram-based words

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

Abstract

Text analysis has been an important research area. Among text processing, opinion mining which is deciding the opinions and giving feelings of others is popular. The researchers have proposed different ways to give the opinions of people automatically. In this case, low resource languages are still difficult to treat due to the unavailability of annotated big corpora and basic natural language processing tools. This research proposes a new method to use a character-based variable-length n-gram word model, which makes n vary within the pre-set thresholds, and select frequent strings of each n as n-length words. We employed this method for words segmentation and the sentiment values are calculated based on variable-length of n-gram-based words. Finally, sentiment analysis of Burmese news articles is processed whether the news is positive or negative, and achieved a similar result with Conditional Random Field (CRF) based ordinary word segmentation with a small size of supervised data. This enables to treat low resource languages without focusing on language specific characteristics.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

ResearchGate has not been able to resolve any citations for this publication.
ResearchGate has not been able to resolve any references for this publication.