Twitter sentiment analysis: An Arabic text mining approach based on COVID-19

被引:8
作者
Albahli, Saleh [1 ]
机构
[1] Qassim Univ, Coll Comp, Dept Informat Technol, Buraydah, Saudi Arabia
关键词
public health; sentiment analysis (SA); natural language processing; machine learning; ML; Synthetic Minority Over-sampling Technique (SMOTE);
D O I
10.3389/fpubh.2022.966779
中图分类号
R1 [预防医学、卫生学];
学科分类号
1004 ; 120402 ;
摘要
The 21st century has seen a lot of innovations, among which included the advancement of social media platforms. These platforms brought about interactions between people and changed how news is transmitted, with people now able to voice their opinion as opposed to before where only the reporters were speaking. Social media has become the most influential source of speech freedom and emotions on their platforms. Anyone can express emotions using social media platforms like Facebook, Twitter, Instagram, and YouTube. The raw data is increasing daily for every culture and field of life, so there is a need to process this raw data to get meaningful information. If any nation or country wants to know their people's needs, there should be mined data showing the actual meaning of the people's emotions. The COVID-19 pandemic came with many problems going beyond the virus itself, as there was mass hysteria and the spread of wrong information on social media. This problem put the whole world into turmoil and research was done to find a way to mitigate the spread of incorrect news. In this research study, we have proposed a model of detecting genuine news related to the COVID-19 pandemic in Arabic Text using sentiment-based data from Twitter for Gulf countries. The proposed sentiment analysis model uses Machine Learning and SMOTE for imbalanced dataset handling. The result showed the people in Gulf countries had a negative sentiment during COVID-19 pandemic. This work was done so government authorities can easily learn directly from people all across the world about the spread of COVID-19 and take appropriate actions in efforts to control it.
引用
收藏
页数:13
相关论文
共 29 条
[1]   Social Networking Security during COVID-19: A Systematic Literature Review [J].
Abid, Rabia ;
Rizwan, Muhammad ;
Vesely, Peter ;
Basharat, Asma ;
Tariq, Usman ;
Javed, Abdul Rehman .
WIRELESS COMMUNICATIONS & MOBILE COMPUTING, 2022, 2022
[2]   A comprehensive survey of arabic sentiment analysis [J].
Al-Ayyoub, Mahmoud ;
Khamaiseh, Abed Allah ;
Jararweh, Yaser ;
Al-Kabi, Mohammed N. .
INFORMATION PROCESSING & MANAGEMENT, 2019, 56 (02) :320-342
[3]   Using Word Embedding and Ensemble Learning for Highly Imbalanced Data Sentiment Analysis in Short Arabic Text [J].
Al-Azani, Sadam ;
El-Alfy, El-Sayed M. .
8TH INTERNATIONAL CONFERENCE ON AMBIENT SYSTEMS, NETWORKS AND TECHNOLOGIES (ANT-2017) AND THE 7TH INTERNATIONAL CONFERENCE ON SUSTAINABLE ENERGY INFORMATION TECHNOLOGY (SEIT 2017), 2017, 109 :359-366
[4]   Ensemble Classifiers for Arabic Sentiment Analysis of Social Network (Twitter Data) towards COVID-19-Related Conspiracy Theories [J].
Al-Hashedi, Abdullah ;
Al-Fuhaidi, Belal ;
Mohsen, Abdulqader M. ;
Ali, Yousef ;
Gamal Al-Kaf, Hasan Ali ;
Al-Sorori, Wedad ;
Maqtary, Naseebah .
APPLIED COMPUTATIONAL INTELLIGENCE AND SOFT COMPUTING, 2022, 2022
[5]   Enhancing Aspect-Based Sentiment Analysis of Arabic Hotels' reviews using morphological, syntactic and semantic features [J].
Al-Smadi, Mohammad ;
Al-Ayyoub, Mahmoud ;
Jararweh, Yaser ;
Qawasmeh, Omar .
INFORMATION PROCESSING & MANAGEMENT, 2019, 56 (02) :308-319
[6]   Arabic sentiment analysis about online learning to mitigate covid-19 [J].
Ali, Manal Mostafa .
JOURNAL OF INTELLIGENT SYSTEMS, 2021, 30 (01) :524-540
[7]  
[Anonymous], 2020, ARXIV, DOI DOI 10.48550/ARXIV.CS/0205028
[8]  
[Anonymous], 2016, GSTF J COMPUT, DOI [DOI 10.7603/S40601-016-0016-9, 10.7603/s40601-016-0016-9]
[9]  
Bhatia Surbhi, 2022, 2022 12th International Conference on Cloud Computing, Data Science & Engineering (Confluence), P559, DOI 10.1109/Confluence52989.2022.9734188
[10]   Information processing under stress: A study of Mumbai Police first responders [J].
Chakraborty, Rajarshi ;
Agrawal, Manish ;
Rao, H. .
IIMB MANAGEMENT REVIEW, 2014, 26 (02) :91-104