| Issue |
E3S Web Conf.
Volume 391, 2023
4th International Conference on Design and Manufacturing Aspects for Sustainable Energy (ICMED-ICMPC 2023)
|
|
|---|---|---|
| Article Number | 01037 | |
| Number of page(s) | 11 | |
| DOI | https://doi.org/10.1051/e3sconf/202339101037 | |
| Published online | 05 June 2023 | |
A Sentence Level Classification of Telugu News Document using Sentiment Analysis
1 Assistant Professor, Department of Computer Science Engineering, International School of Technology and Sciences for Women, Rajahmundry
2 Computer Science Engineering, Kakinada Institute of Technological Sciences, Ramachandra Puram, Andhra Pradesh
3 Department of Computer Science Engineering, University College of Engineering, JNT University, Kakinada, Andhra Pradesh
* Corresponding author: byganijalaja@gmail.com
In recent years, sentiment analysis-based categorization in low-resource languages and regional languages has become a hot topic in natural language processing. Researchers are more interested in categorizing sentiment in Indian languages such as Hindi, Telugu, Tamil, Bengali, Malayalam, and others. To the best of our knowledge, no microscopic study on Indian languages has been published to yet due to a lack of annotated data. Using Telugu sentiment analysis, we presented a two-phase classification technique for Telugu news phrases in this work. It first recognizes subjectivity categorization, which categorizes statements as Positive, Negative, or Neutral. Sentiment Classification is the next step, which divides subjective statements into positive and negative categories. We get an accuracy of 81 percent for sentiment analysis categorization using this method.
© The Authors, published by EDP Sciences, 2023
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.