A Study of Context Inference Algorithm on the Web-based Information Systems
Sangjun Kim, Euiho Suh, Keedong Yoo · Journal of the Association for Information Systems · 2005
Recently, context-awareness has been a hot topic in the ubiquitous computing field.Numerous methods for capturing, representing and inferring context have been developed and relevant projects have been performed.Existing research has tried to determine user's contextual information physically by using stereo type cameras, RFID, smart devices, etc. Especially, these are focusing on physical context such as location, temperature, light, etc.However, cognitive elements of the context are important and needs more study.Therefore, this paper confines its research domain to the web-based information system (IS) and proposes an algorithm for inferring cognitive context in the IS domain.First, a context inference algorithm aims at recognition of a user intention on the IS.To apply this algorithm, we use a text categorization technique to classify various text-based sources users are using such as web pages, pdf document, MS-word documents, etc.Second, the service inference algorithm is based on the similarity measurement between the user preference and the deliver-enabled services and tries to recommend a user-adaptive service to the user.The context and service inference algorithm that this paper proposes can help the IS user to work with a IS conveniently and enable an existing IS to deliver ubiquitous service.In this fashion, the paper shows the direction an existing IS heads and ultimately, shows the typical services of a ubiquitous computing-based IS.