دانلود مقاله درک پاسخ COVID-19 توسط کاربران توییتر
چکیده
مقدمه
استفاده از توییتر برای سنجش افکار عمومی
روش تحقیق
تصویر فیلترینگ داده برای مجموعه داده نهایی (تحلیل).
برچسب احساس برای هر توییت
نتایج
بحث
محدودیت ها و تحقیقات آتی
نتیجه
منابع
Abstract
Introduction
Using twitter to measure Public Opinion
Research methodology
Illustration of data filtering for final (analysis) dataset
Sentiment tag for each tweets
Results
Discussion
Limitations and future research
Conclusion
References
چکیده
شیوع کووید-19 باعث تعداد زیادی تلفات شده و یک اورژانس بهداشت عمومی بی سابقه است. توییتر به عنوان یک پلت فرم اصلی برای تعاملات عمومی ظاهر شده است و فرصتی را به محققان برای درک واکنش عمومی به شیوع بیماری می دهد. محققان 100000 توییت را با هشتگ #coronavirus، #coronavirusbreak، #coronaviruspandemic، #COVID19، #COVID-19، #epitwitter، #ihavecorona، #StayHomeStaySafe، #TestTraceIsolate تجزیه و تحلیل کردند. زبان های برنامه نویسی مانند Python، Google NLP و NVivo برای تحلیل احساسات و تحلیل موضوعی استفاده می شوند. نتیجه نشان داد که 29.61 درصد توییت ها به احساسات مثبت، 29.49 درصد احساسات مختلط، 23.23 درصد احساسات خنثی و 18.069 درصد احساسات منفی مرتبط هستند. کلمات کلیدی محبوب عبارتند از "موارد"، "خانه"، "مردم" و "کمک". ما «30» از این موضوعات را شناسایی کردیم و آنها را در «سه موضوع» دسته‌بندی کردیم: بهداشت عمومی، COVID-19 در سراسر جهان و تعداد موارد/مرگ. این مطالعه نشان می‌دهد که داده‌های توییتر و رویکرد NLP را می‌توان برای مطالعات مربوط به بحث‌های عمومی و احساسات در طول شیوع COVID-19 مورد استفاده قرار داد. تجزیه و تحلیل زمان واقعی می تواند به کاهش پیام های نادرست و افزایش کارایی در اثبات دستورالعمل های صحیح برای افراد کمک کند.
توجه! این متن ترجمه ماشینی بوده و توسط مترجمین ای ترجمه، ترجمه نشده است.
Abstract
COVID-19 outbreak has caused a high number of casualties and is an unprecedented public health emergency. Twitter has emerged as a major platform for public interactions, giving opportunity to researchers for understanding public response to the outbreak. The researchers analyzed 100,000 tweets with hashtags #coronavirus, #coronavirusoutbreak, #coronavirusPandemic, #COVID19, #COVID-19, #epitwitter, #ihavecorona, #StayHomeStaySafe, #TestTraceIsolate. Programming languages such as Python, Google NLP, and NVivo are used for sentiment analysis and thematic analysis. The result showed 29.61% tweets were attached to positive sentiments, 29.49% mixed sentiments, 23.23 % neutral sentiments and 18.069% negative sentiments. Popular keywords include “cases”, “home”, “people” and “help”. We identified “30” such topics and categorized them into “three” themes: Public Health, COVID-19 around the world and Number of Cases/Death. This study shows twitter data and NLP approach can be utilized for studies related to public discussion and sentiments during the COVID-19 outbreak. Real time analysis can help reduce the false messages and increase the efficiency in proving the right guidelines for people.
Introduction
On December 31, 2019, an unknown pneumonia-like disease was detected in Wuhan, China and was reported to WHO country-office in China. In Early January, it was declared as an International public health emergency. In February, WHO announced the name of the new coronavirus as COVID-19. Since then, people all around the world are fighting to find a vaccine for the virus and the authorities are taking measures to keep the public safe from the virus. These measures include easy and efficient access to testing and results, rigorous contact tracing, consistent science-based messaging, quarantines and a genuine commitment to clamping down on socializing. The recent COVID-19 or Coronavirus pandemic is one such topic that has been trending on twitter. Ever since the outbreak in China, the global situation is worsening. As of April 28, 2020, globally, there were 2,954,222 cases of COVID-19. The cases are increasing globally with 960,916, highest cases alone in the United States. The virus is primarily spread between people during close contact, often via small droplets produced by coughing, sneezing, or talking. To stop the spreading of the virus, authorities worldwide were implementing travel bans, lockdowns, quarantines, curfews, stay-at-home orders, sanitizations, and public facilities closures.
Conclusion
This proposed research, particularly attempting to analyse people's emotions and feelings throughout a COVID-19 outbreak, has been an accomplishment. Throughout this study, the Twitter posting interface was chosen to ensure the reliability of the findings as well as the ease of accessing individual Twitter posts. This study demonstrates how Twitter data may be used to measure public sentiment amid emergencies like COVID-19. Even throughout the study, it was revealed that nearly all states were tweeting about COVID-19 with positive views, showing that all of those people had already become accustomed to COVID-19 and, as a result, the survival rate had increased over time. The results of this analysis revealed that subjects such as "preventive methods to combat COVID-19," "public health," and "COVID-19 cases and mortality rate" were frequently discussed. The sentiment analysis suggested maximum users showed “positive” and “mixed” emotions. This type of analysis can be helpful for government and healthcare authorities to understand and react to public emergencies. It can also be utilized to ensure trust in the public.