A Pilot Study on Applying Text Mining Tools to Analyzing Steel Industry Trends : A Case Study of the Steel Industry for the Company “P”

Ki Young Min, Hoon Tae Kim, Yong Gu Ji


It becomes more and more important for business survival to have the ability to predict the future with uncertainties increasing faster and faster. To predict the future, text mining tools are one of the main candidate other than traditional quantitative analyses, but those efforts are still at their infancy. This paper is to introduce one of those efforts using the case of company “P” in the steel industry. Even with only four month pilot studies, we found strong possibilities, if not testified robustly, to predict future industrial trends using text mining tools. For these text mining case studies, we categorized steel industry trend keywords into ten components (10 categories) to study ten different subjects for each category. Once found any meaningful changes in a trend, we had investigated in more detail what and how some trend happened so. To be more roust, firstly we need to define more cleary the purpose of text mining analyses. Then we need to categorize industry trend key words in a more systematic way using systems thinking models. With these improvements, we are quite sure that applying text mining tools to analyzing industry trends will contribute to predicting the future industry trends as well as to identifying the unseen trends otherwise.

Full Text:



Bae, J. H., Son, J. E., and Song, M., “Analysis of Twitter for 2012 South Korea Presidential Election by Text Mining Techniques,” J Intell Inform syst 2013 September, Vol. 19, No. 3, pp. 141- 156, 2013.

Bae, S. J. and Park, C. K., “Analysis of text mining techniques Feasibility Study Technical Information,” Korea Technology Innovation Society Conference 2003, pp. 75-88, 2003.

Cho, G. H., Lim, S. Y., and Hur, S., “An Analysis of the Research Methodologies and techniques in the Industrial Engineering Using Text Mining,” Journal of Korean institute of industrial engineers, Vol. 40, No. 1, pp. 52-59, 2014.

Galit, S., Data mining for business intelligence, Wiley, 2011.

He, Q., “Knowledge Discovery Through Co-Word Analysis,” Library Trends, Vol. 48, No. 1, pp. 133-159, 1999.

Jiawel, H., Data Mining Concepts and Techniques, Elsevier, 2011.

Jung, Y. C., Bing Data, Communication books, 2013.

Kim, B. H. and Hong, S. I., Principles of Economics, Chongmok Publisher, 2012.

Kim, D. H., System Thinking, Sunhaksa, 2004.

Kim, H. J. and Song, M., “A Study on the Research Trends in Domestic/International Information Science Articles by Co-word Analysis,” Journal of the Korean society for information management, Vol. 31, No. 1, pp. 99-118, 2014.

Kim, J. H. and Gong, M. G., “Structural Changes in the Global Steel Industry and Future Prospects,” Journal of the Economic Policy and Industrial Research, Vol. 174, pp. 85-114, Fall 2012.

Lee, S. J. and Kim, H. J., “Keyword Extraction from News Corpus using Modified TF-IDF,” The Journal of Society for e-Business Studies, Vol. 14, No. 4, pp. 59-73, 2009.

LG CNS Official Blog, Social analytics solutions using big data ‘SMART SMA’ intensive exploration, 2014, http://blog. lgcns.com/469.

Ulf, P., Trends und Szenarien als Werkzeuge zur Strategieentwicklung, Publicis, 2008.


  • There are currently no refbacks.