現今文字探勘的技術成熟，作為新穎的管理學工具，文字探勘為定性研究帶 來了更多的見解。不同於過往定性研究倚賴研究者的背景知識及主觀判斷，文字 探勘有大量的資料作為研究對象，可作為質化研究與量化研究的橋樑為管理學提 供了不同面向的見解及成果。 本文採用主題模型對網路上關於電動車的新聞資料進行分析，我們對新聞網 站進行爬蟲擷取近十年有關電動車的資料，並搜集了電動車的銷售數量。我們透 過隱含迪利克雷分佈(LDA)對爬取的新聞資料進行建模並取得文件的主題分佈, 並比較兩個地區的隨時間推移的主題分佈，我們同時也對主題的分佈及電動車新 車比例進行斯皮爾曼等級相關係數的分析，找出潛在的主題中與電動車銷量之間 的關係。 實驗結果顯示政策、充電與自動駕駛相關議題的主題分佈與電動車新車比例 呈現顯著的負相關，同時我們也在實驗中捕捉到疫情與電動車的發展並無顯著的 關係、半導體與電動車新車比例呈現高度的正相關，顯示台灣半導體在電動車產 業中將扮演不可忽視的角色。;The text mining technique is mature and widely applied on management nowadays. As an advanced tool of management, text mining brings us more insight. Different from the previous qualitative research that relies on the background knowledge and subjective judgment of researchers, text mining has a large amount of data as the research object, which can be used as a bridge between qualitative research and quantitative research to provide management with different perspectives and results. We use topic modeling to analysis the news about electric vehicle on the website. We crawl the news about EVs in recent ten years. We model the texture data and obtain the topic distribution of the document through the Latent Dirichlet Distribution (LDA), and compare the topic distribution over time in Taiwan and USA. We also analyze the topic distribution and the number of EV sales. Spearman’s rank correlation coefficient analysis was performed to find the relationship between potential themes and EV sales. The results show that the correlation between three topic frames and the proportion of electric vehicle is negative significantly, they are policy, autonomous and charging issue. Meanwhile we find other topic related to the industry of EV; the impact of Covid -19 doesn’t affect the EV sales and the topics of semiconductor are highly positive correlated to proportion of EV sales.
