Tracking User Interaction with Web and Assisting in Targeted Communication

Today, we spend most of our time online using some form of digital technology (such as search engines, news portals, or social media sites). Our online presence keeps us involved most of the time and provides a lot of information to Internet customers. The development of the web is excellent because every day about a million pages are added. Due to the massive use of the network, the log files of the network increase at a faster rate and the scope becomes enormous. Web Usage Mining uses mining technology on log data to extract user performance, which is used in different applications such as support design, e-commerce, service modification, prefetch, etc. In this paper, we propose a tool that users can use to collect data on their website, and then use this web log data to track user interactions on your website, which helps in targeted communication.

An Efficient Mining Approach for Handling Web Access Sequences

The World Wide Web (WWW) becomes an important source for collecting, storing, and sharing the information. Based on the users query the traditional web page search approximately retrieves the related link and some of the search engines are Alta, Vista, Google, etc. The process of web mining defines to determine the unknown and useful information from web data. Web mining contains the two approaches such as data-based approach and process-based approach. Now a day the data-based approach is the widely used approach. It is used to extract the knowledge from web data in the form of hyper link, and web log data. In this study, the modern technique is presented for mining web access utility-based tree construction under Modified Genetic Algorithm (MGA). MGA tree are newly created to deploy the tree construction. In the web access sequences tree construction for the most part relies upon internal and external utility values. The performance of the proposed technique provides an efficient Web access sequences for both static and incremental data. Furthermore, this research work is helpful for both forward references and backward references of web access sequences.

Recommender System for Multiple Databases Based on Web Log Mining

Finding information from a large collection of resources is a tedious and time-consuming process. Due to information overload, searchers often need help and assistance to search and find the information. Recommender system is one of the innovative solutions to the problem related to information searching and retrieval. It helps and assist searchers by recommending the possible solution based on the previous search activities. These activities can be obtained from the web log, which requires a web log mining approach to extract all the keywords. In this study, keywords obtained from the library web log were analysed and the search keyword patterns were obtained. These keyword patterns were from several databases or resources that were subscribed by the library. The finding revealed some of the popular keywords and the most searchable databases among the searchers. This information was used to design and develop the recommender system that can be used to assist other searchers. The usability test of the recommender system showed that it is beneficial and useful to the searchers. These findings will also benefit the management in planning and managing the subscription of online databases at the university’s library.

Mutual Information Pre-processing Based Broken-stick Linear Regression Technique for Web User Behaviour Pattern Mining

Web usage behaviour mining is a substantial research problem to be resolved as it identifies different user’s behaviour pattern by analysing web log files. But, accuracy of finding the usage behaviour of users frequently accessed web patterns was limited and also it requires more time. Mutual Information Pre-processing based Broken-Stick Linear Regression (MIP-BSLR) technique is proposed for refining the performance of web user behaviour pattern mining with higher accuracy. Initially, web log files from Apache web log dataset and NASA dataset are considered as input. Then, Mutual Information based Pre-processing (MI-P) method is applied to compute mutual dependence between the two web patterns. Based on the computed value, web access patterns which relevant are taken for further processing and irrelevant patterns are removed. After that, Broken-Stick Linear Regression analysis (BLRA) is performed in MIPBSLR for Web User Behaviour analysis. By applying the BLRA, the frequently visited web patterns are identified. With the identification of frequently visited web patterns, MIP-BSLR technique exactly predicts the usage behaviour of web users, and also increases the performance of web usage behaviour mining. Experimental evaluation of MIPBSLR method is conducted on factors such as pattern mining accuracy, false positives, time requirements and space requirements with respect to number of web patterns. Outcomes show that the proposed technique improves the pattern mining accuracy by 14%, and reduces the false positive rate by 52%, time requirement by 19% and space complexity by 21% using Apache web log dataset as compared to conventional methods. Similarly, the pattern mining accuracy of NASA dataset is increased by 16% with the reduction of false positive rate by 47%, time requirement by 20% and space complexity by 22% as compared to conventional methods.