저자 | Donghoon Lee, Jaekwang Kim, Hee-Hyong Lee |
---|---|
논문지 | International Journal of Fuzzy Logic and Intelligent Systems |
Vol. | 12 |
No. | 2 |
pp. | 181-186 |
게재일 | 2012-06-01 |
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.
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.
댓글 0
2016
An approach for multi-label classification by directed acyclic graph with label correlation maximization
2016.10.04
저자: Jaedong Lee, Heera Kim, Noo-ri Kim, Jee-Hyong Lee
논문지: Information Sciences
Vol.: 351
pp.: 101
게재일: 2016-01-12
2015
Latent Keyphrase Extraction Using Deep Belief Networks
2015.10.27
저자: Taemin Cho, Jee-Hyong Lee
논문지: International Journal of Fuzzy Logic and Intelligent Systems
Vol.: 15
No.: 3
pp.: 153-158
게재일: 2015-10-13
Electricity Customer Clustering Following Experts’ Principle for Demand Response Applications
2016.01.08
저자: Jimyeong Kang, Jee-Hyong Lee
논문지: Energies
Vol.: 8
No.: 5
pp.: 12242-12265
게재일: 2015-10-01
Performance Analysis of Group Recommendation Systems in TV Domains
2015.06.10
저자: Noo-ri Kim, Jee-Hyong Lee
논문지: International Journal of Fuzzy Logic and Intelligent Systems
Vol.: 15
No.: 1
pp.: 45-52
게재일: 2015-03-17
Noisy and incomplete fingerprint classification using local ridge distribution models
2015.04.27
저자: Hye-Wuk Jung, Jee-Hyong Lee
논문지: The Journal of the Pattern Recognition Society
Vol.: 48
No.: 2
pp.: 473-484
게재일: 2015-02-01
2014
Multi-Intention Web Pages Model Based on User Keywords of Interest
2014.04.30
저자: Taebok Yoon, Jungmin Park, Jee-Hyong Lee
논문지: Smart Computing Review
Vol.: 4
No.: 1
pp.: 67-78
게재일: 2014-02-28
2013
Game Bot Detection Approach Based on Behavior Analysis and Consideration of Various Play Styles
2013.11.27
저자: Yeounoh Chung, Chang-young Park, Noo-ri Kim, Hana Cho, Taebok Yoon, Hunjoo Lee, and Jee-Hyong Lee
논문지: ETRI Journal
Vol.: 35
No.: 6
pp.: 1059-1068
게재일: 2013-12-01
An Approach of Genetic Programming for Music Emotion Classification
2013.08.28
저자: Sung-Woo Bang, Jaekwang Kim, and Jee-Hyong Lee
논문지: International Journal of Control, Automation, and Systems
Vol.: 11
No.: 6
게재일: 2013-12-01
Keyword Extraction for Blogs Based on Content Richness
2013.10.31
저자: Jinhee Park, Jaekwang Kim, and Jee-Hyong Lee
논문지: Journal of Information Science
게재일: 2013-10-24
Personalized Expert-Based Recommender System: Training C-SVM for Personalized Expert Identification
2014.01.20
저자: Yeounoh Chung, Hye-Wuk Jung, Jaekwang Kim, Jee-Hyong Lee
논문지: Machine Learning and Data Mining in Pattern Recognition
Vol.: 7988
pp.: 434-441
게재일: 2013-07-01
An Error Minimizing Partitioning Method for the Nearest Neighbor Search
2013.03.27
저자: Seunghoon Lee, Jaekwang Kim, Jaedong Lee, Jee-Hyong Lee
논문지: Applied Mechanics and Materials
Vol.: Mechatronics and Industrial Informatics, Trans Tech Publications Inc
pp.: pp. 2165-p.2170
게재일: 2013-03-14
A Path Summarization and Prediction Method Based on Meaningful Locations
2013.03.27
저자: Jaekwang Kim, Seunghoon Lee, Hye-Wuk Jung, Jee-Hyong Lee
논문지: Applied Mechanics and Materials
Vol.: Mechatronics and Industrial Informatics
pp.: pp. 2047-2055
게재일: 2013-03-14
Size-Independent Caption Extraction for Korean Captions with Edge Connected Components
2013.05.27
저자: Jung, Je-Hee; Kim, Jaekwang; Lee, Jee-Hyong
논문지: International Journal of Fuzzy Logic and Intelligent Systems
Vol.: V.12
No.: No.4
pp.: pp.308-318
게재일: 2012-12-04
2012
Web Page Evaluation based on Implicit User Reactions and Neural Networks
2012.09.11
저자: Donghoon Lee, Jaekwang Kim, Hee-Hyong Lee
논문지: International Journal of Fuzzy Logic and Intelligent Systems
Vol.: 12
No.: 2
pp.: 181-186
게재일: 2012-06-01
An Approach for Music Recommendation using Content-Based Analysis and Collaborative Filtering
2012.03.19
저자: Jaekwang Kim, Kunsu Kim, Kwan-Ho You and Jee-Hyong Lee
논문지: Information
Vol.: 15
No.: 5
pp.: 1985-1996
게재일: 2012-05-05
An Approach to Extract Informative Rules for Web Page Recommendation by Genetic Programming
2012.05.10
저자: Jaekwang Kim, KwangHo Yoon, Jee-Hyong Lee
논문지: IEICE TRANSACTIONS on Communications
Vol.: E95-B
No.: 5
pp.: 1558-1565
게재일: 2012-05-01
A Framework of Spatial Co-location Pattern Mining for Ubiquitous GIS
2013.06.10
저자: Seung Kwan Kim, Jee Hyung Lee, Keun Ho Ryu, Ungmo Kim
논문지: Multimedia Tools and Applications
pp.: 1-20
게재일: 2012-02-21
Live-Scanned Fingerprint Classification with Markov Models Modified by GA
2012.03.19
저자: Hye-Wuk Jung, Jee-Hyong Lee
논문지: International Journal of Control, Automaton, and Systems
Vol.: 9
No.: 5
pp.: 933-940
게재일: 2011-10-01
Augmented sliding-mode control of an ultra-precision positioning system
2013.06.10
저자: W.R. Lee, J.H. Lee, K.H. You
논문지: Precision Engineering
Vol.: 35
No.: 3
pp.: 521-524
게재일: 2011-03-10
An Auto Playlist Generation System with One Seed Song
2012.03.19
저자: Sung-Woo Bang, Hye-Wuk Jung, Jaekwang Kim, and Jee-Hyong Lee
논문지: International Journal of Fuzzy Logic and Intelligent Systems
Vol.: 10
No.: 1
pp.: 19-24
게재일: 2010-03-01