Eşref ADALI, Şule GÜNDÜZ

Web kullanıcılarının davranışları için örüntü bulma ve modelleme

İnternetin yaygınlaşması ve her alanda bilgi sağlaması günlük yaşantımıza hızla girmesine neden olmuştur. Haber, ekonomi, kültür, eğitim, sağlık hizmetleri ve reklam gibi bir çok alanda bilgi kaynağı olan internet ortamında, kullanıcı kendisi için gerekli bilgileri bulmakta çoğu zaman zorlanmaktadır. Bunun nedeni sorgulama araçlarının kısıtlı olması ve bilgilerin fazlalığı olarak görülmektedir. Bu çalışmada kullanıcının bir sonraki istek yapacağı sayfayı öngörerek hızlı ve yüksek oranda doğru öneri yapabilen bir yöntem önerilmiştir. Model tabanlı demetleme yönteminden yaralanarak, kullanıcı oturumları aynı demette bulunan oturumlardaki ortak sayfalarda benzer süreler geçirilmesine göre demetlenmiştir. Ortaya çıkan demetler yeni kullanıcılar için öneri kümesi oluşturmak için kullanılmıştır.

Pattern extraction and modelling of the behavior of web users

Making recommendation requires predicting what is of interest to a user at a specific time. Even the same user may have different desires at different times. It is important to extract the aggregate interest of a user from his or her navigational path through the site in a session. In this paper, we present a new model that uses only the visiting time and visiting frequencies of pages without considering the access order of page requests in user sessions. The resulting model has lower run-time computation and memory requirements, while providing predictions that are at least as precise as previous proposals. Our objective in this paper is to assess the effectiveness of non-sequentially ordered pages in predicting navigation patterns. The key idea behind this work is that user sessions can be clustered according to the similar amount of time that is spent on similar pages within a session. We first partition user sessions into clusters such that only sessions which represent similar aggregate interest of users are placed in the same cluster. We employ a model-based clustering approach and partition user sessions according to similar amount of time in similar pages. In particular, we cluster sessions by learning a mixture of Poisson odels using Expectation Maximization algorithm. The resulting clusters are then used to recommend pages to a user that are most likely contain the information which is of interest to that user at that time.

PDF

___

Cooley, R., Mobasher, B., Srivastava, J., (1999). Data Preparation for Mining World Wide Web Browsing Patterns, Journal of Knowledge and Information Systems, 1, 1, 5-32.
Dempster, A. P., Laird, N. M., Rubin, D. B., (1977). Maximum Likelihood from Incomplete Data via the EM Algorithm, Journal of Royal Statistical Society, 39, 1, 1-38.
Deshpande, M., Karypis, G., (2001). Selective Markov Models for Predicting Web-Page Accesses. In Proceedings of 1st SIAM International Conference on Data Mining (SDM'2001).
Etzioni, O., (1996). The World Wide Web: Quagmire or Gold Mine, Communications of the ACM, 39, 11,65-68.
Madria, S. K., Bhowmick, S. S., Ng, W. K., Lim, E. P., (1999). Research Issues in Web Data Mining. In Proceedings of Data Warehousing and Knowledge Discovery, First International Conference, DaWaK '99, 303-312.
Mobasher, B., Dai, H., Luo, T., Nakagawa M., (2000). Discovery of Aggregate Usage Profiles for Web Personalization, In Proceedings of International {WEBKDD} Workshop - Web Mining for E-Commerce: Challenges and Opportunities.
Mobasher, B., Dai, H., Luo, T., Nakagawa, M., (2001). Effective Personalization Based on Association Rule Discovery from Web Usage Data. In Proceedings of 3rd ACM Workhop on Web Information and Data Management.
Nasraoui, O., Frigui, H., Joshi, A., Krishnapuram, R., (1999). Mining Web Access Logs Using a Fuzzy Relational Clustering Algorithm Based on a Robust Estimator, In Proceedings of the Eighth International Fuzzy Systems Association Congress.
Pitkow, J., Pirolli, P., (1999). Mining Longest Repeating Subsequences to Predict World Wide Web Surfing. In Proceedings of USENIX Symposium on Internet Technologies and Systems (USITS'99)
Sarukkai, R. R., (2000). Link Prediction and Path Analysis Using Markov Chains. In Proceedings of 9th International World Wide Web Conference, 377-386.
Shahabi, C, Zarkesh, A., Adibi, J., Shah, V., (1997). Knowledge Discovery from, Users Web-Page Navigation, In Proceedings of 7th Int. Workshop on Research Issues in Data Engineering.