الفهرس Only 14 pages are availabe for public view
 |  | from | 94 |  |  |
| | | from | 94 | | |
Abstract
The World Wide Web (WWW) tends to become the main medium supporting access to
. iDformation and services to an expanding group of users. A web user can interact with a web lite in multiple ways, while his mental model about a particular subject is obviously different tom these of other users and web developers. Consequently, the improvement of the interaction between users and web sites is of great importance. The adaptation of the desired interaction could be considered from a two-dimensional point of view. The first axis concerns the adaptation that takes place by making recommendations 10 the user, while the appearance and the structure of the web site do not change. The second axis concerns the reorganization of lhe web site to be adapted to users’ needs [15].
”\1’-:” Clustering techniques are used as the basis of many existing approaches for developing ~ve web sites. However the used clustering techniques arc primitive which limit the
~ ...•. ,-
efficiency of these approaches. This thesis proposes the use of soft clustering as the underlying
technique for web adaptation with its two dimcnsional point of view. In particular, it proposcs the use of soft clustering to provide a more efficient solution to the index page synthesis problem and to provide a more efficient on-line recommendation system.
The performance of the proposed systems is evaluated using real data. The performance ’,:’evaluation experiments showed the effectiveness of the proposed systems. Also, the ~:~:cxpcriments showed the scalability of the proposed systems for an increasing number of users -’~’”
;’ 8Dd for an increasing size of web logs.