![]() | Only 14 pages are availabe for public view |
Abstract Objectives: The current study aims at: 1.Identify the most important modern trends in the field of web mining. 2.Determine the foundations of the design and constructing web mining system. 3.Identify the quality of data from which user’s patterns can be extracted. 4.Classify user’s patterns according to the user’s interests. 5.Use web usage mining techniques to predict the requirements of web users. 6.Provide an efficient system to facilitate web personalization and improve websites performance. Tools: 1.The proposed system for User’s Patterns Recognition and predicts their requirements to improve the performance of websites. 2.A questionnaire of expert’s opinion in the educational materials related to the requirements of users. Results: 1.The performance of the experimental system is evaluated in terms of three performance measures namely, precision, recall and F-measure. The learning materials generated by our system were evaluated by trying to determine the efficiency of the results. Using the performance measures by a test set of queries and results. Results are labeled by human judges as (relevant or not relevant). Regarding the size of test set, the performance measures resulted in approximate values. This resulted in high levels in the system’s ability to meet the needs of users in access to educational materials that verify their requirements by an average of more than 90%. These results demonstrate the ability of the system to meet user’s needs of the user with high efficiency scale. The current study came in seven chapters: Chapter1”Introduction”, Chapter2 “Literature Review”, Chapter3 ”Knowledge Extraction from Database”, Chapter4 “Knowledge Discovery Techniques for Web Mining”, Chapter5”The proposed System Description”. Chapter 6” Application and Results”. Chapter 7 ”Conclusions and Future Work”. |