近年來，永續發展已經成為全球發展的一個重要目標，因此企業社會責任(CSR)的議題日趨重視，企業已不能像過去只重視自身的經濟利益與發展，更重要的是必須持續遵守道德規範，面對更多的責任與承諾，企業社會責任報告藉由全球報告倡議組織(GRI)所發布的報告書撰寫指引標準來認證、評比企業社會責任報告的完整性與可靠度，使企業社會責任報告書更具可靠性，讓利益相關者可以更容易瀏覽企業社會責任報告書。
企業社會責任為大量非結構資料，因此本研究利用文本探勘(text mining)方法分析、過濾大量的文字內容，萃取出重要的資料，並透過隱含狄克雷分布(LDA)得到每年企業社會責任報告的主題(topic)和字詞(word)分布，得知主題-字詞(Topic-Word)和文檔-主題(Document-Topic)之間的關係，運用隱含狄克雷分布得到的結果，利用社會網絡分析(SNA)視覺化呈現，繪出主題間的強烈關係、字詞的分布與其所對應主題的圖形，最後並利用各個詞語與其主題間的變化了解其每年化工相關產業的趨勢變化。
鑑於近期國內發生的氣爆事件，社會大眾對於化工相關產業越來越重視，也因為環境議題與大眾生活息息相關，因此本文將探討化工相關產業於環境議題的部分，本研究將採用坎貝爾獎得獎企業所發布的企業社會責任報告為標竿，探討企業社會責任報告中的環境構面，了解化工相關產業每年的議題分布、共通性、特定的主題和每年的趨勢變化，提供國內化工相關產業管理趨勢與撰寫報告之方向參考。

Sustainable development has been an important goal of global development so the issue of Corporate Social Responsibility (CSR) has received much attention in recent years. Enterprises cannot concern solely on their own economic interests and developments. It’s more important for them to comply with ethical norms when encountered more responsibilities and promises.
In this research, we use text mining to analyze the CSR reports and extract important data because CSR reports are comprised of a large number of unstructured data. Then we extract the topics from the annual CSR reports by using Latent Dirichlet allocation (LDA). After learning about the relationships of Topic-Word and Document-Topic, we use visualization method for Social Network Analysis (SNA) to acquire the graphic for representing the relationships between topics and words. Finally, we use the variation of words and topics to find out the trends in the chemical industry each year to let readers read the reports much easier.
In view of the recent domestic gas explosion incident, the public is increasingly concerned about the chemical industry. In this research will discuss the environmental issues because they are closely related to our life. We will use the Campbell Award winners’ CSR reports as the benchmark to realize the annual trends of the environmental issue to provide management trends and writing directions of CSR reports for domestic chemical industry.

Agarwal, S., Chen, V. Y. S., & Zhang, W. (2016). The Information Value of Credit Rating Action Reports: A Textual Analysis. Management Science, 62(8), 2218-2240.
Anzai, S., & Matsuzawa, C. (2013). Missions of the Japanese National University Corporations in the 21st Century: Content Analysis of Mission Statements. Academic Journal of Interdisciplinary Studies, 2(3), 197.
Blei, D., & Lafferty, J. (2006). Correlated topic models. Advances in neural information processing systems, 18, 147.
Blei, D. M. (2012). Probabilistic topic models. Communications of the ACM, 55(4), 77-84.
Blei, D. M., & Lafferty, J. D. (2006). Dynamic topic models. Paper presented at the Proceedings of the 23rd international conference on Machine learning. pp. 113-120.
Blei, D. M., Ng, A. Y., & Jordan, M. I. (2003). Latent dirichlet allocation. Journal of machine Learning research, 3(Jan), 993-1022.
Chang, D.-S., & Cheng, Y.-W. (2013). Explore the effects of industrial context and leaders' viewpoints on corporate sustainability in Taiwan by text mining. Paper presented at the 2013 10th International Conference on Service Systems and Service Management. pp. 670-673.
Chen, L., Hossain, K. T., Butler, P., Ramakrishnan, N., & Prakash, B. A. (2016). Syndromic surveillance of Flu on Twitter using weakly supervised temporal topic models. Data Mining and Knowledge Discovery, 30(3), 681-710.
Choi, H. S., Lee, W. S., & Sohn, S. Y. (2017). Analyzing research trends in personal information privacy using topic modeling. Computers & Security.
De Mauro, A., Greco, M., Grimaldi, M., & Nobili, G. (2016). Beyond Data Scientists: a Review of Big Data Skills and Job Families.
Gill, D. L., Dickinson, S. J., & Scharl, A. (2008). Communicating sustainability: A web content analysis of North American, Asian and European firms. Journal of Communication Management, 12(3), 243-262.
Girolami, M., & Kabán, A. (2003). On an equivalence between PLSI and LDA. Paper presented at the Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval. pp. 433-434.
Griffiths, T. L., & Steyvers, M. (2004). Finding scientific topics. Proceedings of the National academy of Sciences, 101(suppl 1), 5228-5235.
Heinrich, G. (2009). Parameter estimation for text analysis.
Hofmann, T. (1999). Probabilistic latent semantic analysis. Paper presented at the Proceedings of the Fifteenth conference on Uncertainty in artificial intelligence. pp. 289-296.
Hofmann, T., Puzicha, J., & Jordan, M. I. (1999). Learning from dyadic data. Advances in neural information processing systems, 466-472.
Jiang, H., Qiang, M., & Lin, P. (2016). Finding academic concerns of the Three Gorges Project based on a topic modeling approach. Ecological Indicators, 60, 693-701.
Jordan, M. I., Ghahramani, Z., Jaakkola, T. S., & Saul, L. K. (1999). An introduction to variational methods for graphical models. Machine learning, 37(2), 183-233.
Liew, W. T., Adhitya, A., & Srinivasan, R. (2014). Sustainability trends in the process industries: A text mining-based analysis. Computers in Industry, 65(3), 393-400.
Maeda, T., Kawakami, N., Chujo, Y., & Park, E. (2016). Time Series Analysis on the Determinants of Environmental Costs Expenditure Using Text Mining Technique. Paper presented at the Proceedings of the International Conference on Parallel and Distributed Processing Techniques and Applications (PDPTA). pp. 375.
Miller, G., & Fellbaum, C. (1998). Wordnet: An electronic lexical database: MIT Press Cambridge.
Miller, G. A. (1995). WordNet: a lexical database for English. Communications of the ACM, 38(11), 39-41.
Minka, T., & Lafferty, J. (2002). Expectation-propagation for the generative aspect model. Paper presented at the Proceedings of the Eighteenth conference on Uncertainty in artificial intelligence. pp. 352-359.
Modapothala, J. R., & Issac, B. (2009). Evaluation of corporate environmental reports using data mining approach. Paper presented at the Computer Engineering and Technology, 2009. ICCET'09. International Conference on. pp. 543-547.
Modapothala, J. R., & Issac, B. (2009). Study of economic, environmental and social factors in sustainability reports using text mining and Bayesian analysis. Paper presented at the Industrial Electronics & Applications. pp. 209-214.
Modapothala, J. R., Issac, B., & Jayamani, E. (2010). Appraising the corporate sustainability reports–text mining and multi-discriminatory analysis Innovations in Computing Sciences and Software Engineering (pp. 489-494): Springer.
Moro, S., Cortez, P., & Rita, P. (2015). Business intelligence in banking: A literature analysis from 2002 to 2013 using text mining and latent Dirichlet allocation. Expert Systems with Applications, 42(3), 1314-1324.
Moro, S., Cortez, P., & Rita, P. (2016). An Automated Literature Analysis on Data Mining Applications to Credit Risk Assessment Artificial Intelligence in Financial Markets (pp. 161-177): Springer.
Mrva, D., & Woodland, P. C. (2006). Unsupervised language model adaptation for Mandarin broadcast conversation transcription. Paper presented at the INTERSPEECH.
Shahi, A. M., Issac, B., & Modapothala, J. R. (2014). Automatic Analysis of Corporate Sustainability Reports and Intelligent Scoring. International Journal of Computational Intelligence and Applications, 13(01), 1450006.
Stiglbauer, M., & Häußinger, C. (2013). Application of data mining techniques to stakeholder sentiment analysis towards corporate social responsibility in the social media: a case study on S&P 500 firms. International Journal of Web Science, 2(1-2), 27-43.
Tam, Y.-C., & Schultz, T. (2005). Dynamic language model adaptation using variational Bayes inference. Paper presented at the INTERSPEECH. pp. 5-8.
Tang, C., & Monteleoni, C. (2015). Can topic modeling shed light on climate extremes? Computing in Science & Engineering, 17(6), 43-52.
Tremblay, M. C., Parra, C., & Castellanos, A. (2015). Analyzing Corporate Social Responsibility Reports Using Unsupervised and Supervised Text Data Mining. 9073, 439-446.
Wang, H., Li, L., & Cao, J. (2012). Lexical features in corporate annual reports: a corpus-based study. European Journal of Business and Social Sciences, 1(9), 55-71.
Wang, J., Sun, X., She, M. F. H., Kouzani, A., & Nahavandi, S. (2013). Unsupervised mining of long time series based on latent topic model. Neurocomputing, 103, 93-103.
Wu, Q., Zhang, C., & An, X. (2013). Topic segmentation model based on ATNLDA and co-occurrence theory and its application in stem cell field. Journal of Information Science, 39(3), 319-332.
Wu, Q., Zhang, C., Hong, Q., & Chen, L. (2014). Topic evolution based on LDA and HMM and its application in stem cell research. Journal of Information Science, 40(5), 611-620.
Yeh, J.-L., & Liao, P.-C. (2015). Benchmarking Social Responsibility perceptions: A text-based approach. Paper presented at the Fuzzy Systems and Knowledge Discovery (FSKD), 2015 12th International Conference on. pp. 1377-1381.
杨慧, & 杨建林. (2016). 融合 LDA 模型的政策文本量化分析——基于国际气候领域的实证. 现代情报, 36(5), 71-81.
林頌堅. (2010). 以詞語共現網絡分析探勘資訊傳播學領域的研究主題與關係. 圖書資訊學研究, 4(2), 123-148.