Internet Articles Classification by Industry Types Based on TF-IDF

Abstract

In order to understand a specific industry field, people usually look at the financial statements of the companies relevant to the industry field. Financial statements have diverse and numerical information but have past financial states of companies because those are usually quarterly reported. So, needs to timely obtain the current states of an industry field is increasing. Proposed method is focusing on internet articles because they are easy to obtain and updated with new information every day. As a preliminary study of extracting information on industries from internet articles, this paper proposes a method to classify internet articles by industry types. The proposed method in this paper computes importance values of nouns in internet articles based on TF-IDF. Using calculated importance values, proposed method classifies articles by industry types. Through experiments, it is proven that proposed method can achieve high accuracy in industry article classification.

This research was supported by Next-Generation Information Computing Development Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Science, ICT & Future Planning (NRF-2014M3C4A7030503). This work was also supported by Institute for Information & communications Technology Promotion (IITP) grant funded by the Korea government (MSIP) (R7120-17-1016, Development of Industry Evaluation Analysis SW based on Convergence of Structured and Unstructured Big Data to provide industry analysis information in a timely manner).