Measuring the Impact of Language Models in Sentiment Analysis for Mexico's COVID-19 Pandemic

被引:1
作者
Leon-Sandoval, Edgar [1 ]
Zareei, Mahdi [1 ]
Barbosa-Santillan, Liliana Ibeth [1 ]
Morales, Luis Eduardo Falcon [1 ]
机构
[1] Tecnol Monterrey, Sch Engn & Sci, Zapopan 45201, Mexico
关键词
sentiment analysis; language model evaluation; big data; COVID-19; machine learning; Mexico; twitter; TWITTER;
D O I
10.3390/electronics11162483
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The world has been facing the COVID-19 pandemic, which has come with an unprecedented impact on general physical health and financial and social repercussions. The adopted mitigation measures also present significant challenges to the population's mental health and health-related programs. It is complex for public organizations to measure the population's mental health to incorporate its feedback into their decision-making process. A significant portion of the population has turned to social media to express the details of their daily life, making these public data a rich field for understanding emotional and mental well-being. To this end, by using open sentiment analysis tools, we analyzed 760,064,879 public domain tweets collected from a public access repository to examine the collective shifts in the general mood about the pandemic evolution, news cycles, and governmental policies. Several modern language models were evaluated and compared using intrinsic and extrinsic tasks, that is, the sentiment analysis evaluation of public domain tweets related to the COVID-19 pandemic in Mexico. This study provides a fair evaluation of state-of-the-art language models, such as BERT and VADER, showcasing their metrics and comparing their performance against a real-world task. Results show the importance of selecting the correct language model for large projects such as this one, for there is a need to balance costs with the model's performance.
引用
收藏
页数:19
相关论文
共 32 条
[1]   Top Concerns of Tweeters During the COVID-19 Pandemic: Infoveillance Study [J].
Abd-Alrazaq, Alaa ;
Alhuwail, Dari ;
Househ, Mowafa ;
Hamdi, Mounir ;
Shah, Zubair .
JOURNAL OF MEDICAL INTERNET RESEARCH, 2020, 22 (04)
[2]   Emotions of COVID-19: Content Analysis of Self-Reported Information Using Artificial Intelligence [J].
Adikari, Achini ;
Nawaratne, Rashmika ;
De Silva, Daswin ;
Ranasinghe, Sajani ;
Alahakoon, Oshadi ;
Alahakoon, Damminda .
JOURNAL OF MEDICAL INTERNET RESEARCH, 2021, 23 (04)
[3]   RETRACTED: Deep Learning-Based Sentiment Analysis of COVID-19 Vaccination Responses from Twitter Data (Retracted Article) [J].
Alam, Kazi Nabiul ;
Khan, Md Shakib ;
Dhruba, Abdur Rab ;
Khan, Mohammad Monirujjaman ;
Al-Amri, Jehad F. ;
Masud, Mehedi ;
Rawashdeh, Majdi .
COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE, 2021, 2021
[4]   A Large-Scale COVID-19 Twitter Chatter Dataset for Open Scientific Research-An International Collaboration [J].
Banda, Juan M. ;
Tekumalla, Ramya ;
Wang, Guanyu ;
Yu, Jingyuan ;
Liu, Tuo ;
Ding, Yuning ;
Artemova, Ekaterina ;
Tutubalina, Elena ;
Chowell, Gerardo .
EPIDEMIOLOGIA, 2021, 2 (03) :315-324
[5]  
Barbieri Francesco, 2020, FINDINGS ASS COMPUTA
[6]  
Boon-Itt S, 2020, JMIR PUBLIC HLTH SUR, V6, P245, DOI 10.2196/21978
[7]  
Cenni D, 2017, 2017 IEEE SMARTWORLD, UBIQUITOUS INTELLIGENCE & COMPUTING, ADVANCED & TRUSTED COMPUTED, SCALABLE COMPUTING & COMMUNICATIONS, CLOUD & BIG DATA COMPUTING, INTERNET OF PEOPLE AND SMART CITY INNOVATION (SMARTWORLD/SCALCOM/UIC/ATC/CBDCOM/IOP/SCI)
[8]   COVID-19 sentiment analysis via deep learning during the rise of novel cases [J].
Chandra, Rohitash ;
Krishna, Aswin .
PLOS ONE, 2021, 16 (08)
[9]   Surveilling COVID-19 Emotional Contagion on Twitter by Sentiment Analysis [J].
Crocamo, Cristina ;
Viviani, Marco ;
Famiglini, Lorenzo ;
Bartoli, Francesco ;
Pasi, Gabriella ;
Carra, Giuseppe .
EUROPEAN PSYCHIATRY, 2021, 64 (01)
[10]  
Nguyen DQ, 2020, PROCEEDINGS OF THE 2020 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING: SYSTEM DEMONSTRATIONS, P9