Recommending Web Pages Using Item-Based Collaborative Filtering Approaches
Predicting the next page a user wants to see in a large website has gained importance along the last decade due to the fact that the Web has become the main communication media between a wide set of entities and users. This is true in particular for insti
- PDF / 321,998 Bytes
- 13 Pages / 439.37 x 666.142 pts Page_size
- 24 Downloads / 223 Views
tract. Predicting the next page a user wants to see in a large website has gained importance along the last decade due to the fact that the Web has become the main communication media between a wide set of entities and users. This is true in particular for institutional government and public organization websites, where for transparency reasons a lot of information has to be provided. The “long tail” phenomenon affects also this kind of websites and users need support for improving the effectiveness of their navigation. For this reason, complex models and approaches for recommending web pages that usually require to process personal user preferences have been proposed. In this paper, we propose three different approaches to leverage information embedded in the structure of web sites and their logs to improve the effectiveness of web page recommendation by considering the context of the users, i.e., their current sessions when surfing a specific web site. This proposal does not require either information about the personal preferences of the users to be stored and processed or complex structures to be created and maintained. So, it can be easily incorporated to current large websites to facilitate the users’ navigation experience. Experiments using a real-world website are described and analyzed to show the performance of the three approaches.
1
Introduction
A great amount of web sites, in particular the official web sites of Public Administrations and other Public Institution Bodies, are composed of a large number of web pages with a lot of information. These institutions are usually the creators of most of the content offered in their web pages (i.e., they are not simple information aggregators, but they are the providers of authoritative information). Therefore, a huge amount of visitors is interested in exploring and analyzing the information published on them. As an example, the ec.europa.eu and europa.eu c Springer International Publishing Switzerland 2015 J. Cardoso et al. (Eds.): KEYWORD 2015, LNCS 9398, pp. 17–29, 2015. DOI: 10.1007/978-3-319-27932-9 2
18
S. Cadegnani et al.
websites, managed by the European Commission, have been visited by more than 520M people in the last year1 . The websites of Governments and Public Institutions typically offer large amounts of data which are usually organized in thematic categories and nested sections that generally form large trees with high height. In particular, the way in which the information is organized (i.e., the conceptualization of the website) can differ from what users are expecting when they navigate the website. Some techniques and best practices have been proposed and experimented for the design of a website. In some websites, for example, the information is grouped according to the topic. In other websites, the users are explicitly asked to declare their roles with respect to the website (e.g., in a university website the users can be asked to declare if they are students, faculty members, or companies, and according to this and the information provided whe
Data Loading...
