| 摘要: | 近年來，由於全球氣候社會變遷，評斷企業除了透過傳統會計指標之外，Environmental, Social, Governance (ESG)也成為一項評估企業發展的重要指標。ESG透過永續發展的角度來評估企業未來的發展性，其中Environmental主要檢視企業對於自然環境相關議題的評估，包含針對綠色能源、廢氣排放、環境汙染等議題做的努力。Social主要檢視企業對於社會相關責任的議題進行評估，包含員工、產品、供應鏈等議題的管理成果。Governance主要檢視企業對於內部管理相關議題的評估，包含董事會、股東、企業倫理等相關議題進行評估。許多研究都發現ESG Rating與企業的股價呈現正相關，並且較高ESG Rating企業其投資風險也較低，因此需多投資者將ESG Rating作為其投資決策的依據，由此可知企業的ESG Rating對其發展將有十分顯著的影響。
隨著自然語言處理的技術越來越成熟，其相關的應用也變得更加多元，本次研究針對Morgan Stanley Capital International (MSCI)所評估的ESG Rating作為研究的目標。本研究將使用BERT自然語言處理技術來對企業的公開報告進行ESG分析，藉此來了解企業與MSCI定義的各Key Issue之間的相關性。最後嘗試透過機器學習與深度學習模型方法來預測企業的MSCI ESG Rating。
;In recent years, due to global climate and social changes, in addition to traditional accounting indicators, Environmental, Social, Governance (ESG) has also become an important indicator for evaluating enterprise development. ESG evaluates the sustainable development of a company from the perspective of sustainable development. Environmental mainly examines the company′s assessment of issues related to the natural environment, including efforts to address issues such as green energy, exhaust emissions, and environmental pollution. Social mainly examines the company′s assessment of social-related responsibilities, including management results on issues such as employees, products, and supply chains. Governance mainly reviews the company′s evaluation of internal management-related issues, including the board of directors, shareholders, corporate ethics and other related issues. Many studies have found that ESG Rating is positively correlated with the stock price of companies, and companies with higher ESG Ratings have lower investment risks. Therefore, many investors used ESG Rating as the basis for their investment decisions. It can be seen that the ESG Rating of a company will have a very significant impact on its development.
As the technology of natural language processing becomes more and more mature, its related applications become more diverse. This research aims at the ESG Rating assessed by Morgan Stanley Capital International (MSCI). This study will use BERT natural language processing technology to conduct ESG analysis on the company′s public reports, so as to understand the correlation between the company and each Key Issue defined by MSCI. Finally, try to predict the MSCI ESG Rating of enterprises through machine learning and deep learning model methods. |
