Data mining for analysing kiosk usage behavior patterns

This main purpose of this study is to understand the self-seeking behavior of participants in developed kiosks that provides interactive service at Huashan Creative Park in Taipei City. To understand user self-seeking patterns, log data from actual cases of interactive kiosk service were collected and analysed by web usage mining. This study analysed 5724 sessions of 8 kiosks for the month of December, 2013. Sequential profiles for user self-seeking behavior patterns were captured by applying sequence-based representation schemes in association with Markov models and enhanced K-mean clustering algorithms for sequence behavior mining cluster patterns. Self-seeking use cycle, time, function numbers, and the depth and extent (range) of services were statistically analysed. The analysis results can be used improved the public´s acceptance of interactive kiosks and help generate potential recommendations for achieving an intelligent kiosk service.