[4P2-GS-6] Web mining (2)

[4P2-GS-6-02] Automatic Extraction of the Company Overview from Startup Company's Website

〇Naoki Shibata¹, Chiharu Sawai², Hiroto Shinoda¹, Aya Ishino³, Toshiyuki Takezawa¹ (1. Graduate School of Information Sciences, Hiroshima City University, 2. School of Information Sciences, Hiroshima City University, 3. Faculty of Media Business, Hiroshima University of Economics)

Keywords:venture company, company overview, automatic extraction

Recently, many startup companies using new technologies such as AI have been founded. Investing in these startup companies from venture capital and angel investors is increasing. However, unlike listed companies, it is difficult for us to collect corporate information of startup companies because such information is often unorganized and undisclosed. To solve this problem, we are conducting research to collect information on startup companies from the Web automatically and comprehensively. As a first step, we propose a method for extraction of the company overview from startup company's website automatically. To confirm the effectiveness of our method, we conducted several experiments on extraction of the company overview. From the experimental results, we obtained precision of 0.794 and recall of 0.452.