Book Description

Research on web personalization techniques for collecting and analysing web data in order to deliver personalized information to users is in an advanced state. Many metrics from the computational intelligence field have been developed to evaluate the algorithmic performance of Web Personalization Systems (WPSs). However, measuring the success of a WPS in terms of user acceptance is difficult until the WPS is deployed in practice. In summary, many techniques exist for delivering personalized information to a user, but a comprehensive measure of the success in WPSs in terms of human interaction and behaviour does not exist. This study aims to develop a framework for measuring user acceptance of WPSs from a user perspective. The proposed framework is based on the unified theory of acceptance and use of technology (UTAUT). The antecedents of user accep- tance are described by indicators based on four key constructs, i.e. performance expectancy (PE), effort expectancy (EE), social influence (SI), and facilitating conditions (FC). All these constructs are underpinned by Information Systems (IS) theories that determine the intention to use (BI) and the actual use (USE) of a technology. A user acceptance model was proposed and validated using structural equation modelling (SEM) via the partial least squares path modelling (PLS-PM). Four user characteristics (i.e. gender, age, skill and experience) have been chosen for testing the moderating effects of the four constructs. The relationship between the four constructs in regard to BI and USE has been validated through moderating effects, in order to present an overall view of the extent of user acceptance of a WPS. Results from response data analysis show that the acceptance of a WPS is deter- mined through PE, EE SI, and FC. The gender of a user was found to moderate the relationship between performance expectancy of a WPS and their behavioural intention in using a WPS. The effect of behavioural intention on the use of WPS is higher for a group of females than for males. Furthermore, the proposed model has been tested and validated for its explanation power of the model and effect size. The current study concluded that predictive relevance of intention to use a WPS is more effective than the actual WPS usage, which indicated that intention to use has more prediction power for describing a user acceptance of a WPS. The implications of these measures from the computational intelligent point of view are useful when a WPS is implemented. For example, the designer of a WPS should consider personalized design features that enable the delivery of relevant information, sharing to other users, and accessibility across many platforms, Such features create a better web experience and a complete security policy. These measures can be utilized to obtain a higher attention rate and continued use by a user; the features that define user acceptance of a WPS.