運用文字探勘從網路新聞探討台灣COVID-19疫情期間民生物資與確診人數發展關係;Exploring the Relationship between the Development of Daily Necessities and Confirmed Cases during the COVID-19 Epidemic in Taiwan from Online News Based on Text Mining

NCUIR > School of Management at National Central University > Executive Master of Business Administration > Electronic Thesis & Dissertation > Item 987654321/92184

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/92184

Title:	運用文字探勘從網路新聞探討台灣COVID-19疫情期間民生物資與確診人數發展關係;Exploring the Relationship between the Development of Daily Necessities and Confirmed Cases during the COVID-19 Epidemic in Taiwan from Online News Based on Text Mining
Authors:	吳岱蓉;WU, TAI-JUNG
Contributors:	企業管理學系在職專班
Keywords:	COVID-19;文字探勘;Google Trends;民生物資;延遲分析;COVID-19;text mining;Google Trends;daily necessities;delay analysis
Date:	2023-01-12
Issue Date:	2024-09-19 15:21:05 (UTC+8)
Publisher:	國立中央大學
Abstract:	自2019年底起，新冠肺炎病毒COVID-19疫情開始爆發，在全世界範圍各方面都受到了巨大的影響與改變。在疫情期間，每當爆發大規模感染時，消費者都會產生恐慌性或預防性的大量消費和囤貨行為。因此本論文透過文字探勘方法，分析台灣疫情期間的新聞關鍵字，與使用Google Trends分析關鍵字熱度趨勢變化與確診人數之間的相關分析，並使用互相關分析不同物資關鍵字的熱度與確診人數間的延遲關係。透過延遲處理後，能發現民生物資與防疫物資在疫情不同發展階與確診人數間會有不同程度的延遲現象。與疫情相關新聞中的關鍵字和Google Trends上的關鍵字熱度趨勢有高度相關且同步的現象。本論文透過結合文字探勘方法與Google Trends關鍵字熱門度趨勢工具，能夠有效且快速的偵測到疫情期間不同物資需求的變化。;Since the outbreak of COVID-19 at the end of 2019, the world has been greatly affected and changed in all aspects. During the epidemic, whenever a large-scale infection breaks out, consumers will have panic or precautionary large-scale consumption and hoarding behaviors. Therefore, this paper uses text mining methods to analyze news keywords during the epidemic in Taiwan, and uses Google Trends to analyze the correlation between keywords popularity trends and the number of confirmed cases, and uses cross-correlation to analyze the delay between the trends of different keywords of daily necessities and the number of confirmed cases. After delayed processing, it can be found that there will be varying degrees of delays between the development stages of the epidemic and the number of confirmed cases between the people′s daily necessities and epidemic prevention supplies. The keywords in news related to the epidemic are highly correlated and synchronized with the keyword popularity trend on Google Trends. In this paper, by combining the text mining method and the Google Trends tool, it can effectively and quickly detect changes in the demand for different necessities and supplies during the epidemic.
Appears in Collections:	[Executive Master of Business Administration] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	16	View/Open

社群 sharing

Loading...