Evaluate the Tweet Analysis with Improved Accuracy Using Multi Channel N-gram Convolutional Neural Network Model over Naive Bayes Model

Chinthapalli Reddy, P. Sriramaya

2023

Abstract

The purpose of this study is to compare the accuracy of tweet analysis using a novel Multi Channel N-gram CNN model and Naive Bayes model. Materials and Methods: There are two groups in this study: Naive Bayes methods and Multi channel N gram CNN. The sample size for each group is 10, and the study’s parameters include an alpha value of 0.8 and a beta value of 0.2. Taking the G-Power value of 80% into account, the significance value of the dataset was predicted using SPSS. Results and Discussion:In the examination of tweets, the Multi Channel N gram CNN Algorithm’s accuracy was 97.84%, whereas the Naive Bayes algorithm’s accuracy was 79.69%; this means that the two algorithms are statistically different. Conclusion: When analyzing tweets, the Multi Channel N gram CNN algorithm performs noticeably better than the Naive Bayes algorithm.

Paper Citation

in Harvard Style

Reddy C. and Sriramaya P. (2023). Evaluate the Tweet Analysis with Improved Accuracy Using Multi Channel N-gram Convolutional Neural Network Model over Naive Bayes Model. In Proceedings of the 1st International Conference on Artificial Intelligence for Internet of Things: Accelerating Innovation in Industry and Consumer Electronics - Volume 1: AI4IoT; ISBN 978-989-758-661-3, SciTePress, pages 546-552. DOI: 10.5220/0012772600003739

in Bibtex Style

@conference{ai4iot23,
author={Chinthapalli Reddy and P. Sriramaya},
title={Evaluate the Tweet Analysis with Improved Accuracy Using Multi Channel N-gram Convolutional Neural Network Model over Naive Bayes Model},
booktitle={Proceedings of the 1st International Conference on Artificial Intelligence for Internet of Things: Accelerating Innovation in Industry and Consumer Electronics - Volume 1: AI4IoT},
year={2023},
pages={546-552},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012772600003739},
isbn={978-989-758-661-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Artificial Intelligence for Internet of Things: Accelerating Innovation in Industry and Consumer Electronics - Volume 1: AI4IoT
TI - Evaluate the Tweet Analysis with Improved Accuracy Using Multi Channel N-gram Convolutional Neural Network Model over Naive Bayes Model
SN - 978-989-758-661-3
AU - Reddy C.
AU - Sriramaya P.
PY - 2023
SP - 546
EP - 552
DO - 10.5220/0012772600003739
PB - SciTePress