• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.219-239
• /
• 2019

As the importance of providing customized services to individuals becomes important, researches on personalized recommendation systems are constantly being carried out. Collaborative filtering is one of the most popular systems in academia and industry. However, there exists limitation in a sense that recommendations were mostly based on quantitative information such as users' ratings, which made the accuracy be lowered. To solve these problems, many studies have been actively attempted to improve the performance of the recommendation system by using other information besides the quantitative information. Good examples are the usages of the sentiment analysis on customer review text data. Nevertheless, the existing research has not directly combined the results of the sentiment analysis and quantitative rating scores in the recommendation system. Therefore, this study aims to reflect the sentiments shown in the reviews into the rating scores. In other words, we propose a new algorithm that can directly convert the user 's own review into the empirically quantitative information and reflect it directly to the recommendation system. To do this, we needed to quantify users' reviews, which were originally qualitative information. In this study, sentiment score was calculated through sentiment analysis technique of text mining. The data was targeted for movie review. Based on the data, a domain specific sentiment dictionary is constructed for the movie reviews. Regression analysis was used as a method to construct sentiment dictionary. Each positive / negative dictionary was constructed using Lasso regression, Ridge regression, and ElasticNet methods. Based on this constructed sentiment dictionary, the accuracy was verified through confusion matrix. The accuracy of the Lasso based dictionary was 70%, the accuracy of the Ridge based dictionary was 79%, and that of the ElasticNet (${\alpha}=0.3$) was 83%. Therefore, in this study, the sentiment score of the review is calculated based on the dictionary of the ElasticNet method. It was combined with a rating to create a new rating. In this paper, we show that the collaborative filtering that reflects sentiment scores of user review is superior to the traditional method that only considers the existing rating. In order to show that the proposed algorithm is based on memory-based user collaboration filtering, item-based collaborative filtering and model based matrix factorization SVD, and SVD ++. Based on the above algorithm, the mean absolute error (MAE) and the root mean square error (RMSE) are calculated to evaluate the recommendation system with a score that combines sentiment scores with a system that only considers scores. When the evaluation index was MAE, it was improved by 0.059 for UBCF, 0.0862 for IBCF, 0.1012 for SVD and 0.188 for SVD ++. When the evaluation index is RMSE, UBCF is 0.0431, IBCF is 0.0882, SVD is 0.1103, and SVD ++ is 0.1756. As a result, it can be seen that the prediction performance of the evaluation point reflecting the sentiment score proposed in this paper is superior to that of the conventional evaluation method. In other words, in this paper, it is confirmed that the collaborative filtering that reflects the sentiment score of the user review shows superior accuracy as compared with the conventional type of collaborative filtering that only considers the quantitative score. We then attempted paired t-test validation to ensure that the proposed model was a better approach and concluded that the proposed model is better. In this study, to overcome limitations of previous researches that judge user's sentiment only by quantitative rating score, the review was numerically calculated and a user's opinion was more refined and considered into the recommendation system to improve the accuracy. The findings of this study have managerial implications to recommendation system developers who need to consider both quantitative information and qualitative information it is expect. The way of constructing the combined system in this paper might be directly used by the developers.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2001.10a
• /
• pp.19-25
• /
• 2001

At present the identification of vessels is still depending on the OOW (Officer Of Wateh) in VTS (Vessel Traffic Service), which is completed by radar, and also by the combination of VHF radio and VHF direction finder. However, with the development of port transportation and economic, this conventional way of identification can't satisfy more and more request for the information that the VTS needs from the vessels. In such a case, the AIS(Automatic Identification System) precept which is based on STDMA (Self-organized Time Division Multiple Access) technique is put forward by IMO (International Maritime Organization). AIS can automatically provide the information, including own ship's identification, type, position, course, speed, and other information to the appropriately equipped coast station and other ships. At the same time it can also automatically monitor and track the nearby ships similarly fitted with AIS. On the basis of describing the whole comprising and the format of transmission information of AIS, this paper mainly studies the key communication techniques in AIS, such as STDMA protocol, net synchronization and GMSK(Gaussian Minimum Shift Keying)technique, and so on. At last this paper briefly introduces the recommendation decided by IMO on forcing the sea-going ships to fixed with AIS equipments, and it continuos with the unexploited potential of AIS if it applies in VTS.

• The Korean Journal of Food And Nutrition
• /
• v.22 no.4
• /
• pp.687-695
• /
• 2009

The present study attempted to offer more insights into the foreign consumers' consumption decision structure of Korean restaurants located in foreign countries. A survey was designed based on the means-end chain theory, using the laddering interview technique. The qualitative data obtained from 10 Americans, 10 Japanese, and 10 Chinese were content analyzed and resulted in categories such as 'new experience', 'interest in Korea', 'recommendation', 'good food', 'easy to access', 'service', 'dining environment', and 'price' as perceived attributes of choice. The hierarchical value maps linking attributes, psychological consequences, and terminal values were presented. The most frequent consequences were 'experience new culture', 'be exposed to new experience', and 'learn more about Korea' which were related to 'happiness', 'pleasure', 'good relationship', 'desire fulfillment', and 'self-satisfaction' as personal values. Laddering interviews, which required laborious analysis, provided important information on the relationship between perceived attributes and the reasons for choosing Korean restaurants.

• Journal of information and communication convergence engineering
• /
• v.15 no.1
• /
• pp.43-48
• /
• 2017

Movie ratings are crucial for recommendation engines that track the behavior of all users and utilize the information to suggest items the users might like. It is intuitively appealing that information about the viewing preferences in terms of movie genres is sufficient for predicting a genre of an unlabeled movie. In order to predict movie genres, we treat ratings as a feature vector, apply a Bernoulli event model to estimate the likelihood of a movie being assigned a certain genre, and evaluate the posterior probability of the genre of a given movie by using the Bayes rule. The goal of the proposed technique is to efficiently use movie ratings for the task of predicting movie genres. In our approach, we attempted to answer the question: "Given the set of users who watched a movie, is it possible to predict the genre of a movie on the basis of its ratings?" The simulation results with MovieLens 1M data demonstrated the efficiency and accuracy of the proposed technique, achieving an 83.8% prediction rate for exact prediction and 84.8% when including correlated genres.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.2
• /
• pp.232-236
• /
• 2010

Nowadays, mobile users have a huge amount of multimedia contents and can use these contents anytime, anywhere by advance in computer and network techniques. However, users spend too much time for searching and managing these contents in web and local file system. Expecially, small and uncomfortable user interfaces of mobile devices make it difficult to search and manage multimedia contents. Therefore, an intelligent multimedia contents management technique is needed to use these contents more efficiently. In this paper, we propose a Personalized Mobile Multimedia Contents Provider (PMMCP) System which provides personalized multimedia contents based on users' psychological patterns and situations.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.15 no.5
• /
• pp.51-60
• /
• 2015

As electronic commerce service became more popular, information equivalent to currency prevails in network. Accordingly, hacking into network often occurs and thus OTP (One-Time-Password) has emerged as an alternative secondary security system. However, weakness has been found in even existing One-Time Password that used to be considered 'perfect'. Therefore, it becomes very urgent to have an additional security countermeasure. As security recommendation is not considered as solution anymore, more specific plan becomes necessary. The present study proposes PKI coordinates technique-based OTP (One-Time-Pad) for a safe key transmission in E-commerce.

• Information Systems Review
• /
• v.9 no.3
• /
• pp.45-65
• /
• 2007

As digital economy era and knowledge society advent, division of the industry has been indistinctive and complex. This change of business environment has leaded todifficulty in operations of firms consisted of continuous decision making. To develop effective SDSS needs systematic strategic decision making process, efficient problem solving techniques, information of good quality, efficiently information system, and analysis ability of problem solver. This research develop SDSS framework combined strategic decision making process with various problem solving techniques for designing SDSS. Finally, this paper developed the technique recommendation system by selected the criterions of technique assortment.

• The Journal of Korean Association of Computer Education
• /
• v.21 no.5
• /
• pp.61-68
• /
• 2018

Collaborative filtering is a fundamental technique implemented in many commercial recommender systems and provides a successful service to online users. This technique recommends items by referring to other users who have similar rating records to the current user. Hence, similarity measures critically affect the system performance. This study addresses problems of previous similarity measures and suggests a new similarity measure. The proposed measure reflects the subjectivity or vagueness of user ratings and the users' rating behavior by using fuzzy logic. We conduct experimental studies for performance evaluation, whose results show that the proposed measure demonstrates outstanding performance improvements in terms of prediction accuracy and recommendation accuracy.

• Journal of Korea Multimedia Society
• /
• v.9 no.9
• /
• pp.1095-1106
• /
• 2006

Recently, many effort is demanded for appropriate operation and management of the Electronic commerce system. Electronic commerce system must provide information satisfying customers. To do this, many kinds of studies are being advanced about electronic commerce system using intelligent agent technology. In this paper, We propose a support system for goods based on Case-Based Reasoning(CBR) and multi-crossselling technology. The system can supply the information of goods that is suitable about customer need under specification condition with CBR technique and can search several goods approximate to customer pattern using Multi-crossselling technique.

• Journal of Technologic Dentistry
• /
• v.38 no.4
• /
• pp.305-311
• /
• 2016

Purpose: The purpose of this study were to analysis of marginal adaptation of metal cores fabricated by selective laser sintering. Methods: Main model was prepared and ten stone models were fabricated. Ten single metal cores were fabricated by selective laser sintering(SLS group) and another ten single metal cores using lost wax technique and casting method were manufactured(CAST group). The marginal adaptation of metal cores were analysis using by the silicone replica technique. Silicone replicas were sectioned two times. The marginal adaptations were measured using by digital microscope. Statistical analyses was performed with independent t-test(${\bullet}{\cdot}=0.05$). Results: Means of marginal adaptations were 90.3 ${\ss}{\uparrow}$ for SLS group and 65.1 ${\ss}{\uparrow}$ for CAST group. Two groups were statistically significant differences (p < 0.05). Conclusion: Marginal adaptation of metal cores fabricated by selective laser sintering were ranged within the clinical recommendation.