Analyzing Sentiments Regarding ChatGPT Using Novel BERT: A Machine Learning Approach

被引:14
|
作者
Sudheesh, R. [1 ]
Mujahid, Muhammad [2 ]
Rustam, Furqan [3 ]
Shafique, Rahman [4 ]
Chunduri, Venkata [5 ]
Villar, Monica Gracia [6 ,7 ,8 ]
Ballester, Julien Brito [6 ,9 ,10 ]
Diez, Isabel de la Torre [11 ]
Ashraf, Imran [4 ]
机构
[1] Kodiyattu Veedu, Kollam 691532, Valakom, India
[2] Khwaja Fareed Univ Engn & Informat Technol, Dept Comp Sci, Rahim Yar Khan 64200, Pakistan
[3] Univ Coll Dublin, Sch Comp Sci, Dublin D04 V1W8, Ireland
[4] Yeungnam Univ, Dept Informat & Commun Engn, Gyongsan 38541, South Korea
[5] Indiana State Univ, Terre Haute, IN 47809 USA
[6] Univ Europea Atlantico, Fac Social Sci & Humanities, Isabel Torres 21, Santander 39011, Spain
[7] Univ Int Iberoamer Arecibo, Dept Project Management, Arecibo, PR 00613 USA
[8] Univ Int Cuanza, Dept Extens, EN250, Cuito, Bie, Angola
[9] Univ Int Iberoamer, Campeche 24560, Mexico
[10] Univ Int Colombia, Bogota 11001, Colombia
[11] Univ Valladolid, Dept Signal Theory Commun & Telemat Engn, Paseo Belen 15, Valladolid 47011, Spain
关键词
ChatGPT; sentimental analysis; BERT; machine learning; LDA; app reviewers; deep learning; ALGORITHMS;
D O I
10.3390/info14090474
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Chatbots are AI-powered programs designed to replicate human conversation. They are capable of performing a wide range of tasks, including answering questions, offering directions, controlling smart home thermostats, and playing music, among other functions. ChatGPT is a popular AI-based chatbot that generates meaningful responses to queries, aiding people in learning. While some individuals support ChatGPT, others view it as a disruptive tool in the field of education. Discussions about this tool can be found across different social media platforms. Analyzing the sentiment of such social media data, which comprises people's opinions, is crucial for assessing public sentiment regarding the success and shortcomings of such tools. This study performs a sentiment analysis and topic modeling on ChatGPT-based tweets. ChatGPT-based tweets are the author's extracted tweets from Twitter using ChatGPT hashtags, where users share their reviews and opinions about ChatGPT, providing a reference to the thoughts expressed by users in their tweets. The Latent Dirichlet Allocation (LDA) approach is employed to identify the most frequently discussed topics in relation to ChatGPT tweets. For the sentiment analysis, a deep transformer-based Bidirectional Encoder Representations from Transformers (BERT) model with three dense layers of neural networks is proposed. Additionally, machine and deep learning models with fine-tuned parameters are utilized for a comparative analysis. Experimental results demonstrate the superior performance of the proposed BERT model, achieving an accuracy of 96.49%.
引用
收藏
页数:29
相关论文
共 50 条
  • [1] Analyzing the User's Sentiments of ChatGPT Using Twitter Data
    Korkmaz, Adem
    Aktürk, Cemal
    Talan, Tarık
    [J]. Iraqi Journal for Computer Science and Mathematics, 2023, 4 (02): : 202 - 214
  • [2] Analyzing Machine Learning Algorithms for Sentiments in Arabic Text
    Yafoz, Ayman
    Mouhoub, Malek
    [J]. 2020 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC), 2020, : 2150 - 2156
  • [3] A novel machine learning approach to analyzing geospatial vessel patterns using AIS data
    Ferreira, Martha Dais
    Campbell, Jessica N. A.
    Matwin, Stan
    [J]. GISCIENCE & REMOTE SENSING, 2022, 59 (01) : 1473 - 1490
  • [4] A novel approach for analyzing buffer overflow vulnerabilities in binary executables by using machine learning techniques
    Durmus, Gursoy
    Sogukpinar, Ibrahim
    [J]. JOURNAL OF THE FACULTY OF ENGINEERING AND ARCHITECTURE OF GAZI UNIVERSITY, 2019, 34 (04): : 1695 - 1704
  • [5] A Novel Approach in Analyzing Traffic Flow by Extreme Learning Machine Method
    Sonmez, Yasin
    Kutlu, Huseyin
    Avci, Engin
    [J]. TEHNICKI VJESNIK-TECHNICAL GAZETTE, 2019, 26 (01): : 107 - 113
  • [6] Unveiling metaverse sentiments using machine learning approaches
    Natarajan, Thamaraiselvan
    Pragha, P.
    Dhalmahapatra, Krantiraditya
    Raghavan, Deepak Ramanan Veera
    [J]. KYBERNETES, 2024,
  • [7] An approach for analyzing urban carbon emissions using machine learning models
    Gao, Peidao
    Zhu, Chaoyong
    Zhang, Yang
    Chen, Bo
    [J]. INDOOR AND BUILT ENVIRONMENT, 2023, 32 (08) : 1657 - 1667
  • [8] Forecasting and Analyzing Predictors of Inflation Rate: Using Machine Learning Approach
    Das, Pijush Kanti
    Das, Prabir Kumar
    [J]. JOURNAL OF QUANTITATIVE ECONOMICS, 2024, 22 (02) : 493 - 517
  • [9] Detecting the Use of ChatGPT in University Newspapers by Analyzing Stylistic Differences with Machine Learning
    Kim, Min-Gyu
    Desaire, Heather
    [J]. INFORMATION, 2024, 15 (06)
  • [10] A Novel Approach for IMU Denoising using Machine Learning
    Damagatla, Rohan Kumar Reddy
    Atia, Mohamed
    [J]. 2023 IEEE SENSORS APPLICATIONS SYMPOSIUM, SAS, 2023,