RESUMEN
The outbreak of Corona Virus Disease 2019 (COVID-19) makes people more concerned about the validity and timeliness of emergency decision making. When an emergency occurs, it is difficult for decision makers (DMs) to give accurate assessment information in the early stage due to the urgency of time, the incompleteness of information, and the limitations of DMs' cognition and knowledge. Hence, we use interval-valued intuitionistic hesitant fuzzy sets rather than exact numbers to better characterize the fuzziness and uncertainty of emergencies. In addition, the Internet has become a major platform for the public to express their opinions or concerns, so we can collect the user-generated content on social media to help DMs determine appropriate emergency decision-making criteria which are the premise and basis of scientific decisions. However, there is likely to be some correlation between the obtained criteria. To this end, we first extend the Bonferroni mean (BM) operator to the interval-valued intuitionistic hesitant fuzzy environment, and propose three interval-valued intuitionistic hesitant fuzzy BM operators to capture the interrelation of fuzzy input variables, including an interval-valued intuitionistic hesitant fuzzy BM operator, a simplified interval-valued intuitionistic hesitant fuzzy BM operator, and a simplified interval-valued intuitionistic hesitant fuzzy weighted BM (SIVIHFWBM) operator. Then, a new group emergency decision-making method based on the SIVIHFWBM operator and social media data is proposed, and the specific steps of ranking all emergency plans are put forward. Moreover, our method is applied to evaluate emergency plans for the prevention and control of COVID-19. Finally, the effectiveness and feasibility of the method are verified by the sensitivity analysis, validity test, and comparative analysis.
RESUMEN
Recent studies on the COVID-19 pandemic indicated an increase in the level of anxiety, stress, and depression among people of all ages. The World Health Organization (WHO) recently warned that even with the approval of vaccines by the Food and Drug Administration (FDA), population immunity is highly unlikely to be achieved this year. This paper aims to analyze people's sentiments during the pandemic by combining sentiment analysis and natural language processing algorithms to classify texts and extract the polarity, emotion, or consensus on COVID-19 vaccines based on tweets. The method used is based on the collection of tweets under the hashtag #COVIDVaccine while the nltk toolkit parses the texts, and the tf-idf algorithm generates the keywords. Both n-gram keywords and hashtags mentioned in the tweets are collected and counted. The results indicate that the sentiments are divided into positive and negative emotions, with the negative ones dominating.