Modeling User’s Sentiment in User Segmentations: An Argumentation Approach for User Centered Design

摘要: User segmentation is a practice of clustering an audience based on mutually exclusive subsets individuals that are similar in specific ways. Nowadays user crucial not only for the industry but also field Centered Design, where achieving accurate understanding user’s behavior current e-scenario becoming complex task. The could be demographic issues, social-economical features, psychographic data, physical characteristics and psychological profiles, etc. This paper proposes novel strategy automatic detection critical factors divide users focused their feelings opinions towards particular topic. Given topic basis text-based posted at Web 2.0 services (such as social networks, microblogging platforms, online review systems, news media, etc.), our proposal introduces argument-oriented methodology integrates argumentation theory, sentiment analysis opinion mining including computational treatment incomplete, contradictory or potentially inconsistent information. process characterized terms dialectical (atomic more constructed by aggregation mechanism) according to preference criterion given feature specificity. As result, “opinion tree” rooted first original automatically visualized, which any node models segmentation, showing factor define well particularities group subset. way, traditional problems associated with subjective interpretation expressed natural language minimized. Besides, instead defining statistical sample, all available information considered possible, evident discovered, thus enhancing rational decision making process.