• Asia pacific journal of information systems
• /
• 제29권4호
• /
• pp.856-874
• /
• 2019

The performance of recommender systems (RS) has been measured mainly in terms of accuracy. However, there are other aspects of performance that are difficult to understand in terms of accuracy, such as coverage, serendipity, and satisfaction with recommended results. Moreover, particularly with RSs that suggest multiple items at a time, such as YouTube, user satisfaction with recommended results may vary not only depending on their accuracy, but also on their configuration, content, and design displayed to the user. This is true when classifying an RS as a single RS with one recommended result and as a multiple RS with diverse results. No empirical analysis has been conducted on the influence of the content and distribution of recommendation items on user satisfaction. In this study, we propose a research model representing the content and distribution of recommended items and how they affect user satisfaction with the RS. We focus on RSs that recommend multiple items. We performed an empirical analysis involving 149 YouTube users. The results suggest that user satisfaction with recommended results is significantly affected according to the HHI (Herfindahl-Hirschman Index). In addition, satisfaction significantly increased when the recommended item on the top of the list was the same category in terms of content that users were currently watching. Particularly when the purpose of using RS is hedonic, not utilitarian, the results showed greater satisfaction when the number of views of the recommended items was evenly distributed. However, other characteristics of selected content, such as view count and playback time, had relatively less impact on satisfaction with recommended items. To the best of our knowledge, this study is the first to show that the category concentration of items impacts user satisfaction on websites recommending diverse items in different categories using a content-based filtering system, such as YouTube. In addition, our use of the HHI index, which has been extensively used in economics research, to show the distributional characteristics of recommended items, is also unique. The HHI for categories of recommended items was useful in explaining user satisfaction.

• Journal of Information Technology Applications and Management
• /
• 제21권4호
• /
• pp.203-223
• /
• 2014

This study proposes a novel context-aware recommender system, which is designed to recommend the items according to the customer's responses to the previously recommended item. In specific, our proposed system predicts the user's emotional state from his or her responses (such as facial expressions and movements) to the previous recommended item, and then it recommends the items that are similar to the previous one when his or her emotional state is estimated as positive. If the customer's emotional state on the previously recommended item is regarded as negative, the system recommends the items that have characteristics opposite to the previous item. Our proposed system consists of two sub modules-(1) emotion prediction module, and (2) responsive recommendation module. Emotion prediction module contains the emotion prediction model that predicts a customer's arousal level-a physiological and psychological state of being awake or reactive to stimuli-using the customer's reaction data including facial expressions and body movements, which can be measured using Microsoft's Kinect Sensor. Responsive recommendation module generates a recommendation list by using the results from the first module-emotion prediction module. If a customer shows a high level of arousal on the previously recommended item, the module recommends the items that are most similar to the previous item. Otherwise, it recommends the items that are most dissimilar to the previous one. In order to validate the performance and usefulness of the proposed recommender system, we conducted empirical validation. In total, 30 undergraduate students participated in the experiment. We used 100 trailers of Korean movies that had been released from 2009 to 2012 as the items for recommendation. For the experiment, we manually constructed Korean movie trailer DB which contains the fields such as release date, genre, director, writer, and actors. In order to check if the recommendation using customers' responses outperforms the recommendation using their demographic information, we compared them. The performance of the recommendation was measured using two metrics-satisfaction and arousal levels. Experimental results showed that the recommendation using customers' responses (i.e. our proposed system) outperformed the recommendation using their demographic information with statistical significance.

• Journal of the Korean Data and Information Science Society
• /
• 제24권4호
• /
• pp.803-813
• /
• 2013

전자상거래에서 상품의 구입은 오프라인에서 구매하는 방식과는 차이가 있다. 오프라인에서 상품추천은 판매원의 추천에 의해 이루어지지만 온라인에서 상품 추천은 판매원이 상품 추천을 할 수가 없기 때문에 오프라인과는 다른 형태의 상품을 추천하게 된다. 추천시스템은 온라인 상거래에서 상품을 추천하는 방법으로 기존 상품을 구입한 고객의 선호도를 기반으로 상품을 구입하려는 고객의 선호도를 예측하여 추정된 선호도가 높은 상품을 고객에게 추천하는 방법이다. 협력적 필터링 알고리즘은 전자상거래의 상품추천 추천시스템에 사용되며 추정된 값들로 추천 상품 목록을 만들고 그 목록을 고객에게 추천을 하는 것이다. 이 논문에서 사용된 데이터집합은 Movielens 데이터집합인 100k 데이터집합과 1 million 데이터집합이며 일반화를 위해 2개의 데이터집합에서 유사한 결과를 도출하여 일반화시키고자 한다. 영화 추천시스템의 새로운 알고리즘을 제안하기 위해 기존의 알고리즘과 변형된 알고리즘에 의해 추정된 추정값들의 분포 특징을 분석과 응답자별로 분류해서 응답자별 분포의 특징을 분석하였다. 이 논문에서는 이웃기반 추천시스템 협력적 필터링 알고리즘을 개선하기 위해 기존의 알고리즘과 변형된 알고리즘을 바탕으로 새로운 알고리즘을 제안하였다.

• 한국막학회:학술대회논문집
• /
• 한국막학회 1997년도 제5회 하계 Workshop (97 한,카 국제공동 Workshop, 고도 수처리를 위한 막분리 공정)
• /
• pp.1-20
• /
• 1997

The present standard of drinking water quality is not reached to the guidelines of WHO and US EPA recommended. The appraisal of safety is not appropriate by the results of intermittent and limitted analysis. 45 items of drinking water quality are regulated in the Korean standard and 9 items for inspection designated by Seoul City. This report is the results of analysis of the water quality in the water stations of Seoul which are concerned with the items of Korean water quality standard and the priolity pollutnats recommended by WHO. In the results, 45 items of water quality, and the priolity pollutants were not exceeded to the standard and criteria, while DDT, heptachlor-epoxide, THMs, benzo(a)pyrene, Ba, Al, Gross beta, $^{226}$Ra, $^{90}$Sr were detected, the levels were not exceeded to the WHO guidelines. In ordes to evalute the safety of drinking water quality, besides of the existed items of standard, new hazardouse pollutants should be considered monitored continenously. For the regulation of hazardous pollutants, it may be introduced from the risk assessment. According to the relevant assessment, the acceptable risk of pollutants estimated could be applied to set the water quality standard or recommendations or quidelines as well as the number of monitoring.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2007년도 추계학술대회
• /
• pp.602-609
• /
• 2007

Combining collaborative filtering with some other technique is most common in hybrid recommender systems. As many recommended items from collaborative filtering seem to be similar with respect to content, the collaborative-content hybrid system suffers in terms of quality recommendation and recommending new items as well. To alleviate such problem, we have developed a novel method that uses a diversity metric to select the dissimilar items among the recommended items from collaborative filtering, which together with the input when fed into content space let us improve and include new items in the recommendation. We present experimental results on movielens dataset that shows how our approach performs better than simple content-based system and naive hybrid system

• 대한산업공학회지
• /
• 제41권2호
• /
• pp.128-136
• /
• 2015

With the recent interests with culture technologies, many studies for recommendation systems have been done. In this vein, various music recommendation systems have been developed. However, they have often focused on the technical aspects such as feature extraction and similarity comparison, and have not sufficiently addressed them in user-centered perspectives. For users' high satisfaction with recommended music items, it is necessary to study how the items are connected to the users' actual desires. For this, our study proposes a novel music recommendation method based on serendipity, which means the freshness users feel for their familiar items. The serendipity is measured through the comparison of users' past and recent listening tendencies. We utilize neural networks to apply these tendencies to the recommendation process and to extract the features of music items as MFCCs (Mel-frequency cepstral coefficients). In that the recommendation method is developed based on the characteristics of user behaviors, it is expected that user satisfaction for the recommended items can be actually increased.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2001년도 춘계학술대회 논문집
• /
• pp.200-206
• /
• 2001

In the standard specifications for the urban EMU(Electric Multiple Unit) train, there are several items to ensure safety against accidents. The 21th -23th items have much relation with the crashworthiness of the urban EMU train. In this study, the rubber- tired AGT(Automated Guide-way Transit System) under development by KRRI is numerically evaluated in a crashworthy point of view by applying the above crashworthiness items. The numerical results show the detail design of the AGT satisfies the 22th and 23th items. But the design is recommended to adopt mechanical fuses to reduce the impact accelerations with respect to the 21th item.

• 한국멀티미디어학회논문지
• /
• 제25권8호
• /
• pp.1242-1250
• /
• 2022

When recommending cold items that do not have user-item interactions to users, even we adopt state-of-the-arts algorithms, the predicted information of cold items tends to have lower accuracy compared to warm items which have enough user-item interactions. The lack of information makes for recommender systems to recommend monotonic items which have a few top popular contents matched to user preferences. As a result, under-diversified items have a negative impact on not only recommendation diversity but also on recommendation accuracy when recommending cold items. To address the problem, we adopt a diversification algorithm which tries to make distributions of accumulated contents embedding of the two items groups, recommended items and the items in the target user's already interacted items, similar. Evaluation on a real world data set CiteULike shows that the proposed method improves not only the diversity but also the accuracy of cold item recommendation.

• 지능정보연구
• /
• 제23권1호
• /
• pp.127-141
• /
• 2017

인터넷과 모바일 관련 기술의 발전과 기기의 보급은 물리적 공간의 제약을 극복하게 하고, 다양한 상품과 서비스를 소비자에게 제공함으로써, 소비자에게 선택의 폭을 넓히는 기회를 제공하는 반면, 많은 시간과 노력을 기울이고도 소비자가 자신의 기호에 적합한 품목을 선택하기 힘들어지는 부작용을 낳았다. 이에 따라, 기업은 추천 시스템을 활용하여 소비자가 원하는 품목을 더 쉽게 찾는 수단을 제공하고 있다. 상품 간의 연관성을 통계적으로 분석하는 연관 규칙 마이닝 기법은 직관적인 형태의 척도를 규칙과 함께 제공함으로써, 이로부터 도출된 규칙에 포함된 품목 간의 관계를 이해하고, 이를 추천에 적용하기 쉽다는 강점을 갖는다. 그러나, 서로 다른 규칙의 척도가 일관되게 어느 한 쪽의 규칙이 더 우위에 있음을 알려주지 못한다면, 수많은 품목 중 추천에 적합한 품목을 적절히 선별해내기 힘든 상황이 발생한다. 본 연구에서는 추천 상품의 순위를 결정할 수 있도록 연관 규칙 마이닝 기법에 회귀분석모형을 보완적으로 적용하는 방안을 제시하고자 수행되었다. 연관 규칙 마이닝에서 보편적으로 사용되고 있는 지지도, 신뢰도, 향상도를 활용하여 모형을 구현함으로써, 직관적으로 이해하기 쉬울 뿐만 아니라, 실무에서도 활용하기 쉬운 방안을 제시하고자 하였다. 국내 최대규모의 온라인 쇼핑몰의 주문 데이터를 활용한 실험을 통해, 제안된 모형으로부터 얻어진 추천 점수를 기반으로 추천상품을 결정하고, 이를 추천에 적용함으로써 추천 적중률을 향상시킬 수 있음을 보였다. 특히, 최근 모바일 상거래가 빠르게 확산됨에 따라, 제한된 화면에 한정된 수의 추천 품목을 제시해야 하는 상황에서 적합한 추천 기법임을 확인할 수 있었다.

• Spatial Information Research
• /
• 제6권2호
• /
• pp.169-182
• /
• 1998

구역중심 토지정보시스템은 도시계획 행정가와 연구자에게 중요한 정보시스템 중의 하나이다. 이 연구는 구역중심 토지정보시스템을 구축하기 위해서 필요한 계획분석구역의 개념 정립과 수치지도를 활용한 구축방법론에 관한 연구이다. 구역중심 토지정보시스템을 구축하기 위한 기초작업으로서, 본 연구에서는 계획분석구역의 개념을 설정하고, 이를 포항시에 적용하여 여러 가지 유형의 구역을 구분해 보았다. 또 기존의 통계연보나 행정이 가지고 있는 통계자료 중에서 구역중심 토지정보시스템을 구축시 필요한 정보의 종류 및 출처 등을 구체적으로 살펴보았다. 본 연구에서는 수치지도를 활용하여 GIS를 구축하기 위해서 수치지도가 가지고 있는 지형정보에 관한 730여개의 세분류 항목 중에서 구역중심 토지정보시스템에 필요하게 될 84개의 세분류 항목을 선정해보기도 하고, 좀 더 세부적인 토지정보를 위해서 필요한 약 250여개의 세분류 항목이 필요함도 지적되었다. 이 연구의 의의는 토지정보시스템에 관한 기존의 많은 연구가 필지중심 토지정보시스템에 관한 내용이었는데 반하여, 구역중심 토지정보시스템의 구축 필요성을 제기하고 또, 구역중심 시스템 구축을 위해서 필요한 기본적인 개념과 방법론에 관한 구체적인 방향을 제시하였다는 데 있다.