• Journal of the Korea Society of Computer and Information
• /
• v.25 no.12
• /
• pp.165-172
• /
• 2020

Recently, due to exponential growth of access information on the web, the importance of predicting a user's next web page use has been increasing. One of the methods that can be used for predicting user's next web page is deep learning. To predict next web page, web logs are analyzed by data preprocessing and then a user's next web page is predicted on the output of the analyzed web logs using a deep learning algorithm. In this paper, we propose a framework for web page prediction that includes methods for web log preprocessing followed by deep learning techniques for web prediction. To increase the speed of preprocessing of large web log, a Hadoop based MapReduce programming model is used. In addition, we present a web prediction system that uses an efficient deep learning technique on the output of web log preprocessing for training and prediction. Through experiment, we show the performance improvement of our proposed method over traditional methods. We also show the accuracy of our prediction.

• Journal of KIISE:Databases
• /
• v.34 no.5
• /
• pp.437-447
• /
• 2007

A variety of similarity metrics have been used to measure the degree of web page changes. In this paper, we first define criteria for web page changes to evaluate the effectiveness of the similarity metrics in terms of six important types of web page changes. Second, we propose a new similarity metric appropriate for measuring the degree of web page changes. Using real web pages and synthesized pages, we analyze the five existing metrics (i.e., the byte-wise comparison, the TF IDF cosine distance, the word distance, the edit distance, and the shingling) and ours under the proposed criteria. The analysis result shows that our metric represents the changes more effectively than other metrics. We expect that our study can help users select an appropriate metric for particular web applications.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.12 no.2
• /
• pp.181-186
• /
• 2012

This paper proposes a method for evaluating web pages by considering implicit user reaction on web pages. Usually users spend more time and make more reactions, such as clicking, dragging and scrolling, while reading interesting pages. Based on this observation, a web page evaluation method by observing implicit user reaction is proposed. The system is designed with Ajax for observing user reactions, and neural networks for learning correlation between user reactions and usefulness of pages. The amounts of each type of user reactions are inputted to neural networks. Also the numbers of characters and images of pages are used as inputs because the amount of users' behaviors has a tendency to increase as the length of pages increase. The experiment is conducted with 113 people and 74 pages. Each page is ranked by users with a questionnaire. The proposed method shows more close ranking results to the user ranks than Google. That is, our system evaluates web pages more closely to users' viewpoint than Google. Although our experiment is limited, our result shows powerful potential of new element for web page evaluation. Some approaches evaluate web pages with their contents and some evaluate web pages with structural attributes, particularly links, of pages. Web page evaluation is for users, so the best evaluation can be done by users themselves. So, user feedback is one of the most important factors for web page evaluation. This paper proposes a new method which reflects user feedbacks on web pages.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.142-145
• /
• 2003

When we search information on the Web using search engines, they only analyze the text information collected from the source files of Web pages. However, there is a limit to analyze the layout of a Web page only from its source file, although Web page design is the most important factor for a user to estimate a page. In particular it often happens on the Web that the pages of similar design ofter similar information. We propose a method to analyze layout for comparing the design of pages by treating the displayed page as image.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.29 no.2
• /
• pp.104-109
• /
• 2006

We can offer suitable information to users analyzing the pattern of users. An association rule is one of data mining techniques which can discover the pattern. We use an association rule which considers the web page visiting time and we should the pattern analyse of users. The offered method puts the weights in Web page visiting time of the user and produces an association rule. Weight is web page visiting time unit divide to total of web page visiting time. We offer rather meaningful result the association rule by Apriori algorithm. This method that proposes in the paper offers rather meaningful result Apriori algorithm

• Proceedings of the Korean Society for Language and Information Conference
• /
• 2007.11a
• /
• pp.285-292
• /
• 2007

The parallel corpus is an important resource in the research field of data-driven natural language processing, but there are only a few parallel corpora publicly available nowadays, mostly due to the high labor force needed to construct this kind of resource. A novel strategy is brought out to automatically fetch parallel text from the web in this paper, which may help to solve the problem of the lack of parallel corpora with high quality. The system we develop first downloads the web pages from certain hosts. Then candidate parallel page pairs are prepared from the page set based on the outer features of the web pages. The candidate page pairs are evaluated in the last step in which the sentences in the candidate web page pairs are extracted and aligned first, and then the similarity of the two web pages is evaluate based on the similarities of the aligned sentences. The experiments towards a multilingual web site show the satisfactory performance of the system.

• Journal of The Korean Association of Information Education
• /
• v.22 no.4
• /
• pp.409-417
• /
• 2018

There are unplugged computer science activities for elementary school students to learn the concept of the Internet. However, these activities are not enough to teach the concept of the Web because they focus on teaching how the Internet works. Since the Web is the core technology of the Third Industrial Revolution, it needs to be understood as a basic common sense. In this paper, we developed an unplugged activity to understand the PageRank algorithm which is closely related to the web. The experimental results show that our unplugged activities behave similarly to the PageRank algorithm.

• The KIPS Transactions:PartC
• /
• v.8C no.6
• /
• pp.847-854
• /
• 2001

The Web continues to grow fast rate in both a large aclae volume of traffic and the size and complexity of Web sites. Along with growth, the complexity of tasks such as Web site design Web server design and of navigating simply through a Web site have increased. An important input to these design tasks is the analysis of how a web site is being used. The is paper proposes a Page logging System(PLS) identifying reliably user sessions required in Web mining system PLS consists of Page Logger acquiring all the page accesses of the user Log processor producing user session from these data, and statements to incorporate a call to page logger applet. Proposed PLS abbreviates several preprocessing tasks which spends a log of time and efforts that must be performed in Web mining systems. In particular, it simplifies the complexity of transaction identification phase through acquiring directly the amount of time a user stays on a page. Also PLS solves local cache hits and proxy IPs that create problems with identifying user sessions from Web sever log.

• Journal of KIISE:Databases
• /
• v.37 no.2
• /
• pp.104-112
• /
• 2010

Social bookmarking is one of the most interesting trends in the current web environment. In a social bookmarking system, users annotate a web page with tags, which describe the contents of the page. Numerous studies have been done using this information, mostly on enhancing the quality of web search. In this paper, we use this information to measure the semantic similarity between two web pages. Since web pages consist of various types of multimedia data, it is quite difficult to compare the semantics of two web pages by comparing the actual data contained in the pages. With the help of social bookmarks, this comparison can be performed very effectively. In this paper, we propose a new similarity measure between web pages, called Web Page Similarity Based on Entire Tags (WSET), based on social bookmarks. The experimental results show that the proposed measure yields more satisfactory results than the previous ones.

• Proceedings of the Korea Contents Association Conference
• /
• 2006.11a
• /
• pp.478-482
• /
• 2006

This paper implemented speech-library and the Web Services that conversion the Web page for the speech recognition. The system is consisted of Web services consumer and Web services providers. The Web services consumer has libraries that Speech-library and proxy-library. The Speech -library has functions as follows from the user's speech extracted speech-data and searching the URL in link-table that is mapped with user's speech. The proxy-library calls two web services and is received the returning result. The Web services provider consisted of Parsing Web Services and Speech-Recognition Web Services. Parsing Web Services adds ActiveX control and reconstructs web page using the speech recognition. The speech recognizer is the web service providers that implemented in the previous study. As the result of experiment, we show that reconstructs web page and creates link-Table. Also searching the URL in link-table that is mapped with user's speech. Also confirmed returning the web page to user by searching URL in link-table that is mapped with the result of speech recognition web services.