How to identify the trends of services: GTM-TT service map

• Published in: Expert systems with applications 2013-06, Vol.40 (8), p.2956-2965
• Main Authors: Son, Changho, Geum, Youngjung, Park, Yongtae
• Format: Article
• Language: English
• Subjects: Applied sciences; Clustering; Computer science; control theory; systems; Computer systems and distributed systems. User interface; Dynamic tests; Dynamics; Exact sciences and technology; Expert systems; Fundamental areas of phenomenology (including applications); Generative topographic mapping through time; Mobile application services; Physics; Preprocessing; Service map; Software; Solid mechanics; Structural and continuum mechanics; Topographic mapping; Trends; Vibration, mechanical wave, dynamic stability (aeroelasticity, vibration control...); Visualization
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2012.12.011

► Providing an approach for developing and utilizing GTM-TT service map. ► Employing text mining technique to extract meaningful information. ► Employing information visualization for identifying the trends of services. ► Analyzing and visualizing service trends and the dynamic change path of them. Recently, due to the explosive increase of services, firms have faced with challenges to analyze patterns and trends in services in an intuitive but objective ways. The notion of service map can be adapted to this end. Maps, in general, have been receiving a great deal of attention because of their potential as visualization tools that can allow people to visualize massive amounts of information. Specifically, the generative topographic mapping through time (GTM-TT) algorithm is suitable for dynamic analysis since GTM-TT provides a time-based clustering and change path. In response, this study proposes an approach for developing and using GTM-TT service maps consisting of a service clustering map and a service sequence map for analyzing service trends. The proposed approach, broadly, is comprised of four steps: (1) the construction of a database, (2) data preprocessing, (3) development of a GTM-TT service map, and (4) interpretation. The proposed approach is expected to aid in the identification of dynamic service trends.