• Asia pacific journal of information systems
• /
• v.14 no.4
• /
• pp.99-122
• /
• 2004

In the past days, most of studies about website behavior and website advertisement have been mainly focused on the effectiveness of website advertisement and advertisement attitude. But the generic model of website click behavior via website advertisement has not been made and the leading theory of that has not been existed. This purpose of this research is to explore the effects of internet advertisement in website click behavior. Specially, I deal with the influence of advertisement attributes(informativeness, entertainment, attentiveness, uneasiness, website attitude and advertising attitude) which is gradually being increased or decreased to attract the website click behavior of internet users. Added to this, it is to examine the influence of two attitudes(advertisement attitude and website attitude) as mediating variables on website click behavior. Major findings of this research are summarized as follows: First, mediating effects of website attitude and advertisement attitude were tested significantly in affecting the website click behavior by website advertisement attributes(informativeness, entertainment, attentiveness, uneasiness). Second, the website attitude was affected by website advertisement attributes(informativeness, entertainment, attentiveness, uneasiness). And the advertisement attribute(except of entertainment and attentiveness) such as informativeness and uneasiness did significantly affected in the website click behavior. Also, the website click behavior was not affected but the website advertisement attitude, however the mediating effect was tested significantly.

• Journal of the Korean Society for Library and Information Science
• /
• v.45 no.1
• /
• pp.377-393
• /
• 2011

This study aims to investigate trends of internet searching behavior of users of NAVER, a major Korean search portal. In particular, this study analyzed trends of query submission behaviors, behaviors related to typos, multimedia searching behaviors, and click behaviors. In conducting this study, query logs and click logs of unified search service were analyzed. The results of this study show that there were little changes in the topic and length of queries, the pattern of typos, and multimedia seeking behavior over a year's period. However, click counts of documents have gradually increased over time. The results of this study can be implemented to increase the portal's effective development of internet contents and searching algorithms.

• Journal of Digital Contents Society
• /
• v.19 no.2
• /
• pp.301-307
• /
• 2018

Generally, search engine summarizes the main contents of the search results so that user can click the site providing the information of the contents to search first. In this study, we demonstrated whether the user clicks on the search results based on the summary content provided by the search engine or on the order of the search result placement through empirical studies through the presentation of search results. By using the API provided by the search engine company, a search site that presents the search results in a regular and inverse order is created, and the click action of each user's search result is displayed in the order of actual click order, click position, and the user's search type such as the route of movement. As a result of the analysis, most users account for more than 60% of users who click on the first and second exposed search results regardless of the search results. It is confirmed that the search priority of users is determined according to the order of search results regardless of the summary of search results.

• Journal of Information Technology Applications and Management
• /
• v.13 no.1
• /
• pp.1-16
• /
• 2006

This paper empirically analyzed consumer price search behavior using Web log data of a Korean web site for price comparison. Consumer click-stream data of the site was used to test the effects of price level, product category, third party certification, reputation of retailers on click behavior. According to the descriptive statistics, 67.4% of shopbot users clicked the offer which was the lowest price returned in a search. We found that third party certification and reputation of retailers were significant determinants of clicking the lowest priced offer from legit analysis. We also applied Tobit regression analysis to estimate the price premium of the two determinants, but only reputation of retailers was found to have price premium of 4.9%.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2005.05a
• /
• pp.324-331
• /
• 2005

In this paper, we propose a new customer profile model based on customer behavior in Internet shopping mall. The proposed technique defines customer profile model based on customer behavior information such as click data, buy data, and interest categories. We also implement CBCPM(Customer Behavior-based Customer Profile Model) and perform extensive experiments. The experimental results show that CBCPM has higher precision, recall, and F1 than the existing customer profile model.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.25 no.1
• /
• pp.19-37
• /
• 2014

Server transaction logs containing complete click-through data from a digital library of primarily image-based documents were analyzed to better understand user search session behavior. One month of data was analyzed using descriptive statistics and network analysis methods. The findings reveal iterative search behaviors centered on result views and evaluation and topical areas of focus for the search sessions. The study is novel in its combined analytical techniques and use of click-through data for image collections.

• Asian Journal of Business Environment
• /
• v.8 no.3
• /
• pp.5-12
• /
• 2018

Purpose - The purpose of current paper is to identify features of advertisements at social media that generate the ad-click and to further identify if these advertisements lead to purchase. If no purchase is made, then reasons for not making purchase are identified. Users' purchase experience after users clicked at advertisements are also studied. Research design, data, and methodology - Research design followed is exploratory research, where various factors leading to ad-clicks and generating purchase at social media platform were explored. Raw data was gathered by means of survey among a sample of 185 respondents in India using online structured questionnaire. GLM model and multinomial regression were used to analyze the data. Results - Several factors including endorsement by friends, advertisement aesthetics, product reviews, and aggressive pricing played major role in generating ad-clicks. Major impediment to purchase on were product misrepresentation in advertisement, false discounts, and site security. Female users clicked more on social media advertisements and made more purchases compared to their male counterpart. Conclusions - Social media advertisements have significant positive effect on buying behavior of online customers. Transactions culminating from social media ad-click generated significant positive experience for social media users. Thus, social media can be effective marketing tool.

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.369-384
• /
• 2021

In a personalized product recommendation system, when the amount of log data is large or sparse, the accuracy of model recommendation will be greatly affected. To solve this problem, a personalized product recommendation method using deep factorization machine (DeepFM) to analyze user behavior is proposed. Firstly, the K-means clustering algorithm is used to cluster the original log data from the perspective of similarity to reduce the data dimension. Then, through the DeepFM parameter sharing strategy, the relationship between low- and high-order feature combinations is learned from log data, and the click rate prediction model is constructed. Finally, based on the predicted click-through rate, products are recommended to users in sequence and fed back. The area under the curve (AUC) and Logloss of the proposed method are 0.8834 and 0.0253, respectively, on the Criteo dataset, and 0.7836 and 0.0348 on the KDD2012 Cup dataset, respectively. Compared with other newer recommendation methods, the proposed method can achieve better recommendation effect.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.37 no.3
• /
• pp.189-195
• /
• 2001

The characteristics of echolocation signals of the Common Dolphin, Delphinus Delphis was observed by the hydrophone in order to detect exactly distribution and migration on whales and dolphins in Korean Coastal waters. It's observation was carried out at the position of 13 mm off Gam-Po of Korean east-southern sea at 3rd-5th. April and 13th-15th. October, 1999. The results obtained are summarized as follows: (1) The frequency range of ship's noise and ambient noise in the observed station was 0.5-0.3 kHz, that ones could be influenced to the behavior of common dolphins which carry out echolocation using low-frequency. (2) The common dolphin was radiated single click of 8.6 ms and double click of 4.8 ms pulse width during these observation (3) The high click frequencies of common dolphin were 5.10 kHz, 7.22 kHz, 10.60 kHz with the click pulse width of 4.0 ms, 2.6 ms, 1.0 ms, respectively. In case of low-frequency 1-2 kHz, that is, 1.12 kHz, 1.38 kHz, 1.82 kHz, pulse width were 22.4 ms, 2.05 ms, 11.9 ms, respectively and they showed a tendency using triple click signal. (4) The pulse width, pulse recurrence interval and frequency range of the observed echolocation signals were 2.4-8.4 ms, 9.0-40.0 ms, 0.60-10.63 kHz respectively, and frequency spectrum level was 100-125 dB for single, double, triple click signals.

• Korean Management Science Review
• /
• v.23 no.3
• /
• pp.183-194
• /
• 2006

In this paper, we propose a customer profiling technique based on customer behavior for personalized products recommendation in Internet shopping mall. The proposed technique defines customer profile model based on customer behavior Information such as click data, buying data, market basket data, and interest categories. We also implement CBCPT(customer behavior based customer profiling technique) and perform extensive experiments. The experimental results show that CBCPT has higher MAE, precision, recall, and F1 than the existing other customer profiling technique.