Online roadshow is a relatively new concept that has higher flexibility and scalability compared to the physical roadshow. This is because online roadshow is accessible through digital devices anywhere and anytime. In a physical roadshow, organizations can measure the effectiveness of the roadshow by interacting with the customers. However, organizations cannot monitor the effectiveness of the online roadshow by using the same method. A good user experience is important to increase the advertising effects on the online roadshow website. In web usage mining, clustering can discover user access patterns from the weblog. By applying a clustering technique, the online roadshow website can be further improved to provide a better user experience. This paper presents a review of clustering techniques used in web usage mining, namely the partition-based, hierarchical, density-based, and fuzzy clustering techniques. These clustering techniques are analyzed from three perspectives: their similarity measures, the evaluation metrics used to determine the optimality of the clusters, and the functional purpose of applying the techniques to improve the user experience of the website. By applying clustering techniques in different stages of the user activities in the online roadshow website, the advertising effectiveness of the website can be enhanced in terms of its affordance, flow, and interactivity.

Clustering technique is one of the mining techniques in web usage mining to discover user navigational behaviour of similar patterns from a weblog. A weblog is preprocessed to retrieve the web sessions that can be assigned to the clustering techniques. Clustering will group similar user access patterns from web sessions. The main purpose of web session clustering is to evaluate how engaged the users are with the website. Therefore, there are two important parts presented in this paper, which are the performance analysis of different clustering techniques and the utilization of user engagement metrics to describe the user behaviour of each cluster. The clustering techniques, namely k-means, k-medoids, bisecting k-means, and fuzzy c-means are applied on two different weblogs. The clustering qualities of the techniques are then compared using cluster validity indices. Two engagement metrics, which are the number of clicks and the number of sessions are calculated for each cluster to discover its user behaviour.

User engagement is a part of user experience that measures how attracted the users are in using a certain product or services. The level of user attention while navigating a website is a key factor in determining its effectiveness. Web usage mining can be performed on the weblog of a website to extract user navigational behavior and gain valuable insights into the useful activities of the users. The user navigational behavior can then be further evaluated to measure the user engagement of the website. This paper presents a new framework that uses user navigational behavior extracted from web usage mining to measure the engagement level of the users on the website. In this proposed framework, web session clustering is first performed on the pre-processed weblog to group similar user access patterns from web sessions. After that, four proposed engagement metrics, which are the hourly activeness, the hourly traffic, the daily activeness, and the daily traffic are calculated for each cluster to determine the engagement level of the users on the website. According to the engagement level determined by the user engagement metrics, an attention score is formulated to show how attracted the users in the session cluster are to the website. In this paper, two weblogs from different websites are used to measure their user engagement with the Cluster-N-Engage framework. The framework shows that attention score can assess the website’s effectiveness in achieving its objectives.