• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제14권3호
• /
• pp.306-310
• /
• 2008

정보추천 서비스를 위한 선호도는 상황에 따라 달라질 수 있으므로, 정보추천 서비스를 제공하기 위해서는 먼저 사용자의 컨덱스트 정보를 알아야 한다. 본 논문은 모바일 환경에서 다수 사용자의 선호도를 고려한 추천 시스템을 제안하며, 음식점 추천에 이를 적용하고자 한다. 모바일 환경에서 개별 사용자의 선호도를 모델링하기 위해 베이지안 네트워크를 사용하였으며, 음식점 추천은 많은 경우 개별 사용자가 아닌 다수 사용자의 선호도를 고려해야 하므로, 본 논문에서는 개별 사용자의 선호도를 바탕으로 다수의 선호도를 획득하기 위해 다기준 의사결정방법인 AHP를 이용하였다. 실험을 위해서 10가지 서로 다른 상황에서 추천을 수행하였으며, 마지막으로 SUS 사용성 평가를 통해 제안하는 시스템의 사용성이 높게 평가되었음을 확인하였다.

• Journal of Information Processing Systems
• /
• 제8권4호
• /
• pp.721-738
• /
• 2012

The Internet has become an increasingly important source for finding the right employees, so more and more companies post their job openings on the Web. The large amount and dynamic nature of career recruiting information causes information overload problems for job seekers. To assist Internet users in searching for the right job, a range of research and commercial systems were developed over the past 10 years. Surprisingly, the majority of existing job search systems support just one, rarely two ways of information access. In contrast, our work focused on exploring a value of comprehensive access to job information in a single system (i.e., a system which supports multiple ways). We designed Proactive, a recommendation system providing comprehensive and personalized information access. To assist the varied needs of users, Proactive has four information retrieval methods - a navigable list of jobs, keyword-based search, implicit preference-based recommendations, and explicit preference-based recommendations. This paper introduces the Proactive and reports the results of a study focusing on the experimental evaluation of these methods. The goal of the study was to assess whether all of the methods are necessary for users to find relevant jobs and to what extent different methods can meet different users' information requirements.

• Journal of the Korean Data and Information Science Society
• /
• 제20권5호
• /
• pp.809-818
• /
• 2009

협력적 필터링 기법은 전자상거래에서 거래되는 아이템에 대하여 고객들이 평가한 선호 정보를 이용하여 특정 상품에 대한 선호도 예측 대상 고객의 선호도를 예측하는 기법이다. 협력적 필터링 기법을 통한 예측 정확도를 향상시키기 위해서는 예측에 이용할 수 있는 고객들의 선호 정보를 충분히 확보하여야 한다. 그러나 과도한 이웃 고객의 선호 정보는 오히려 예측 정확도에 부정적 영향을 미치며 또한 과소 정보 역시 예측 정확도 감소에 영향을 미칠 수 있다. 본 연구에서는 협력적 필터링 알고리즘 적용에 있어 k명의 근접 이웃을 결정하는 이웃 선정방법을 개선하였으며 개별 고객의 선호도 평가 정보를 이용하여 적정 이웃 수를 결정할 수 있는 방법을 제시한다. 본 연구의 결과는 근접 이웃 수 결정을 위한 기존 방법인 탐색적 방법을 개선함과 동시에 선호도 예측 정확도를 향상시키는데 유용한 방법을 제공할 수 있다.

• 한국멀티미디어학회논문지
• /
• 제17권11호
• /
• pp.1286-1295
• /
• 2014

This paper suggests the way that it could improve the reliability about preference of user's feedback by adding weighting factor on sentiment analysis, and efficiently make a sentiment analysis of users' emotional perspective on the big data massively generated on twitter. To solve errors on earlier studies, this paper has improved recall and precision of sensibility determination by using sensibility dictionary subdivided sentiment polarity based on the level of sensibility and given impotance to sensibility determination by populating slang, new words, emoticons and idiomatic expressions not in the system dictionary. It has considered the context through conjunctive adverbs fixed in korean characteristics which are free to the word order. It also recognize sensibility words such as TF(Term Frequency), RT(Retweet), Follower which are weighting factors of preference and has increased reliability of preference analysis considering weight on 'a very emotional tweet', 'a recognised tweet from users' and 'a tweeter influencer'

• Journal of Information Processing Systems
• /
• 제15권3호
• /
• pp.645-654
• /
• 2019

The purpose of this study was to collect and analyze personal bio data and social network services (SNS) data, derive user preference and user life pattern, and propose intuitive and precise user modeling. This study not only tried to conduct eye tracking experiments using various smart devices to be the ground of the recommendation system considering the attribute of smart devices, but also derived classification preference by analyzing eye tracking data of collected bio data and SNS data. In addition, this study intended to combine and analyze preference of the common classification of the two types of data, derive final preference by each smart device, and based on user life pattern extracted from final preference and collected bio data (amount of activity, sleep), draw the similarity between users using Pearson correlation coefficient. Through derivation of preference considering the attribute of smart devices, it could be found that users would be influenced by smart devices. With user modeling using user behavior pattern, eye tracking, and user preference, this study tried to contribute to the research on the recommendation system that should precisely reflect user tendency.

• International Journal of Computer Science & Network Security
• /
• 제21권12호
• /
• pp.131-136
• /
• 2021

This research aims to analyse the practices adopted by social media users in the Kingdom of Saudi Arabia (KSA), specifically users of Facebook and Snapchat. To collect data from participants, a questionnaire was used, generating 915 responses. The analysis of the data shows a clear preference for Snapchat over Facebook in the KSA, where 89% of the participants have accounts on Snapchat compared to 66% of them with accounts on Facebook. Moreover, the preference for Snapchat over Facebook has been clearly shown in the daily usage of participants, where 83% of those with Snapchat accounts can be described as very active users. They have accessed their Snapchat accounts at least once a day compared to only 15% of Facebook users. Different reasons were provided by the participants explaining the practices they adopted. We believe that such research could help social media applications' designers and policy makers to understand the behaviour of users in the KSA when using social media applications and the rationale behind their behaviour and preferences. This understanding could help improve the performance of current applications and new ones.

• 한국지능시스템학회논문지
• /
• 제16권6호
• /
• pp.716-720
• /
• 2006

퍼지 이론을 이용하면 여러 정보를 통합 요약하기에 수월하여, 웹 상에서 사용자에게 제공할 정보를 가공하는 방법으로 많이 사용되고 있다. 하지만 퍼지의 애매모호한 특성 때문에 사용자에게 맞게 퍼지 집합으로 표현된 같은 정보라 하여도 사용자마다 자신의 퍼지값 선호도에 따라 다른 선택을 할 수 있다. 따라서 애매한 퍼지값을 선택함에 있어 사용자의 퍼지값에 대한 선호도를 반영할 필요가 있다. 그러나 기존의 방법들은 정해진 기준을 획일적으로 적용하여, 사용자의 개인적인 선택 기준을 반영하지 못하는 문제가 있다. 본 논문에서는 사용자의 선호도를 학습하여, 사용자의 선호도에 맞는 정보를 선택하는 방법을 제안한다. 사용자의 선호도를 학습하기 위해서 학습 데이터가 필요한데, 이 데이터는 사용자에게 직접 물어 사용자의 선호도론 얻는데 사용된다. 이때, 사용자에게 너무 많은 데이터로 질문을 한다면, 사용자에게 부담을 줄 수 있고, 또 너무 적은 데이터를 사용한다면, 학습을 잘 못하는 경향이 생길 수 있다. 이러한 문제에 대처하기 위해서 10개 정도의 데이터를 이용하여 사용자의 선호도를 학습하는 방법을 제안한다. 제안하는 방법은 먼저 두 퍼지값이 서로 겹칠 수 있는 모든 경우의 상대적 위치를 조사한 후 클러스터링을 이용하여 몇 가지 그룹으로 나누고, 나누어진 그룹을 이용하여 학습하였다. 이렇게 학습된 모델은 새로운 애매하게 겹치는 퍼지값에 대해 사용자를 대신해 어느 것을 어느 정도 선호하는지 추론하게 된다.

• 한국환경과학회지
• /
• 제30권3호
• /
• pp.267-277
• /
• 2021

This study investigates sound, scenery, and soundscape preferences, which are sensory factors that users feel in a healing forest, comparing the difference in recovery by the soundscape. In the barrier-free, wooden walking path of the National Daegwallyeong Healing Forest, a survey site with five different conditions was selected. Users prefer water sounds the most and places with open views for scenery. For the complex sensation of soundscapes, the most preferred is a space where water sounds can be heard, and either a waterfall or an open view can be seen. A profile of mood states test was use to compare users' psychological recovery by the soundscape. It was found that users felt the most positive mood with water sounds and open views. In addition, users' preference for artificial sounds, scenery, and soundscape was the lowest. In the mood state test, it was found that the artificial soundscape incited the most negative emotions.

• 한국주거학회:학술대회논문집
• /
• 한국주거학회 2006년도 추계학술발표대회 논문집
• /
• pp.346-351
• /
• 2006

Community facilities in apartment complex was developed through combination with residents' needs about housing environmental amenity, marketing competition among construction companies and social trend 'Well-being' . But community facilities and fitness center which are situated in the beginning are alienated by residents because the designers plan community facilities without considering about residents' life-style and preference. In this paper, the study includes present status of fitness center and residents' preference for proper fitness center design. The result presents that fitness center users in apartment complex want a resting space which is already located in fitness center of mixed-use residential building. A resting space provides conditions that users can make up with the community each other as well as they can rest after exercise. And the fitness center users prefer wood as interior finish material of floor and wall in exercising space and resting space because they have a feeling comfortable and splendid.

• 한국실내디자인학회논문집
• /
• 제22권6호
• /
• pp.88-97
• /
• 2013

This study aims to find out various users' diverse interior design needs for their housing and interior design through the personality, which is intrinsic and consistent traits of the individual. The survey research followed the literature reviews including personality studies and interior design assessments. 176 undergraduate and graduate students as controlled by age, sex, and major answered the questionnaire. Their housing and interior design attitudes, the semiotic assessment of interior design styles, and interior design preference were compared in accordance with four pairs of preference dichotomy of MBTI (Myers-Briggs Type Indicator): Extraversion -Introversion, Sensing-iNtuition, Thinking-Feeling, Judging-Perceiving. As a result, the framework of housing and interior design needs by the users' personality types are proposed. It shows specific needs for 16 types of personality based on eight preference dichotomy: extroversion-open, introversion-closed, sensing-functional, intuition-emotional, thinking-restricted, feeling-receptive, judging-simple, and perceiving-creative.