A Support System for The Requirement Extraction from BBS Using Topic Mapping Based on Structure of Conversation with a 3-dimensional Space

Abstract

This paper proposes a support system for the requirement extraction from BBS(Bulletin Board System). On BBS in EC (Electronic Commerce) sites, participants who are consumers easily write frank opinions, which produce active conversation as enormous text data and include unexpected opinions and consumers' requirements. In this system, opinions on BBS are classified by topics and arranged on a 3-dimensional space so that users (product designers) can easily grasp how topics are interwoven into conversations. Furthermore, a method using the feature of the conversation structure on BBS is proposed for correcting the recognition of opinions written in colloquial style.