• The KIPS Transactions:PartB
• /
• v.15B no.1
• /
• pp.73-80
• /
• 2008

In this paper, an advertisement-keyword finding method using document clustering is proposed to solve problems by ambiguous words and incorrect identification of main keywords. News articles that have similar contents and the same advertisement-keywords are clustered to construct the contextual information of advertisement-keywords. In addition to news articles, the web page and summary of a product are also used to construct the contextual information. The given document is classified as one of the news article clusters, and then cluster-relevant advertisement-keywords are used to identify keywords in the document. We could achieve 21% precision improvement by our proposed method.

• The Journal of the Korea Contents Association
• /
• v.15 no.7
• /
• pp.84-92
• /
• 2015

Advertisement market using the augmented reality has been rapidly increasing recently due to integration with LBS(location based services). This study was conducted to examine the effect and acceptance intention of mobile augmented reality advertisement through TAM(Technology Acceptance Model). 'Contextual feature,' which is a characteristic of augmented reality advertisement, was selected as an outside effective variable, and perceived usefulness and perceived ease of use, which are the core variables of TAM, and attitude of advertisement and advertisement acceptance intention were selected as important evidences of Technology Acceptance Process. Also, the relationship between each evidences were investigated. As a result of the investigation of the outside influence on the acceptance model of augmented reality advertisement, it was shown that the contextual feature of augmented reality advertisement had meaningful influence on perceived usefulness and perceived ease of use, and it was also shown that it has positive influence on the attitude of advertisement and acceptance intention of advertisement.

• Journal of Information Technology Applications and Management
• /
• v.19 no.4
• /
• pp.115-135
• /
• 2012

Currently, smart signage as a new kind of advertisement media has been widely used and has had a significant effect on consumers. In this study, we examine the impact on the attitude towards smart signage advertisement based on the Ducoffe's Web advertisement model. In particular, we investigate how the advertising factors (interaction, informativeness, irritation, and entertainment) as well as the contextual factors (localization, immediacy, and personalization) have effects on the value and attitude towards smart signage advertisement. Furthermore, we examine the moderating effect of individual defensive propensity on the relationship between affecting factors and the advertising value. By analyzing 192 samples from undergraduates, we found that four out of seven factors have significant effects on the value towards smart signage. More specifically, for advertising factors, informativeness and irritation have positive effects on the advertising value. For contextual factors, on the other hand, localization and entertainment have positive effects on the value towards smart signage. Besides, we discovered that the defensive propensity moderate the relationship between localization and the advertising value.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.5
• /
• pp.1373-1387
• /
• 2012

Contextual advertising is an important revenue source for major service providers on the Web. Ads classification is one of main tasks in contextual advertising, and it is used to retrieve semantically relevant ads with respect to the content of web pages. However, it is difficult for traditional text classification methods to achieve satisfactory performance in ads classification due to scarce term features in ads. In this paper, we propose a novel ads classification method that handles the lack of term features for classifying ads with short text. The proposed method utilizes a vocabulary expansion technique using semantic associations among terms learned from large-scale search query logs. The evaluation results show that our methodology achieves 4.0% ~ 9.7% improvements in terms of the hierarchical f-measure over the baseline classifiers without vocabulary expansion.

• Journal of the Korean housing association
• /
• v.22 no.2
• /
• pp.131-139
• /
• 2011

This study is to examine architectural designers' views on the correlations between components and contextual principle of the roadside building facade with the roadside building facade on the border of Asian Culture Center in Gwangju which is expected to undergo a great change by public policies. For setting direction of the roadside building management at the region examined, height of facade, advertisement/signboard, security of continuity through surface pattern management, nodes building, array of height by story, awning/arcade and locality of advertisement/signboard should be induced to design with locality and consideration of local characteristics with silhouette, window and external colors is needed for discrimination from other cities. Regarding the realization method important thing was found that the planning and implementation of architectural design guidelines, architectural aesthetics of the pre-hearing enhancement, active citizen participation, and then additional landscape screening system, incentive schemes, landscape designation of landscape zone was found to be a major realization system.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2006.05a
• /
• pp.337-340
• /
• 2006

문맥광고는 인터넷 사용자들이 뉴스나 커뮤니티 사이트에서 콘텐츠를 조회할 때, 해당 콘텐츠와 일치하거나 관련성이 높은 제품 또는 서비스 정보를 제공하는 새로운 방식의 광고기법이다. 그러나 현재 제공되고 있는 서비스의 대부분은 콘텐츠와의 관계가 다소 떨어지거나, 수동적으로 광고주가 선택한 키워드 또는 카테고리 선택에 의해 서비스가 제공되고 있다. 따라서 문맥광고의 효율성을 높이기 위해서는 사용자가 조회한 콘텐츠내의 문맥정보를 분석하여 콘텐츠와의 관련성이 높은 서비스를 제공하는 방법에 대한 연구가 필요하다. 본 논문에서는 사용자가 조회한 콘텐츠의 내용과 보다 관련 있는 서비스 제공을 위해 콘텐츠의 내용을 대표할 수 있는 중요 키워드를 선정하고, 콘텐츠 내에서 추출된 키워드간의 연관성을 분석하여 콘텐츠와 관련된 서비스를 제공하는 방법에 대해 제안한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.10b
• /
• pp.189-193
• /
• 2006

문맥광고 또는 컨텍스트 기반 광고란 사용자들이 선택한 웹 콘텐츠 내용을 기반으로 하여 연관성 있는 광고를 자동으로 선택하여 사용자에게 제공하는 광고기법이다. 즉, 웹 사이트를 방문하는 고객을 타겟으로 하여 그들이 찾고자 하는 것과 관련된 광고를 내보냄으로써 효과적인 광고가 이루어지도록 하는 것이다. 그러나 기존의 문맥광고는 사용자가 관심을 가지는 키워드가 아닌 광고주가 선택한 키워드를 중심으로 광고 내용을 선택하기 때문에 사용자의 실제적인 관심이 반영되지 않아 광고의 효과가 떨어지는 문제점을 가지고 있다. 이러한 문제를 해결하기 위해 본 논문에서는 사용자가 웹 콘텐츠를 선택할 때 마다 사용자의 선호도를 동적으로 학습하고, 학습된 선호도를 문맥광고에 활용하는 개인화된 문맥광고를 제안한다. 실험을 위해서 제안한 방법으로 광고를 생성해서 보여주는 웹 브라우저를 구현하여 기존의 문맥광고와 개인화된 문맥광고에 대한 사용자의 평가를 비교하였다. 실험 결과 본 논문에서 제안한 개인화된 문맥광고가 ‘콘텐츠의 내용과의 연관성’, ‘사용자의 클릭여부’ 등의 항목에서 기존의 문맥광고에 비해 우수하다는 결과를 얻을 수 있었다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.10b
• /
• pp.362-365
• /
• 2006

인터넷 사용자가 급증함에 따라 온톨로지를 이용한 지능형 웹이나 인터넷 사용자에게 개인 맞춤형 서비스를 제공하기 위한 다양한 연구가 진행되고 있다. 대표적인 예로 문맥광고는 인터넷 사용자들이 뉴스나 커뮤니티 사이트에서 콘텐츠를 조회하고, 해당 콘텐츠와 일치하거나 관련성이 높은 제품 또는 서비스 정보를 제공하는 광고기법이다. 그러나 문맥 광고는 사용자에게 다양한 콘텐츠 및 사이트 추천 서비스를 제공하지 못하고 있다. 따라서 다양한 콘텐츠 및 사이트 추천 서비스를 제공하기 위해 본 논문에서는 사용자가 조회한 콘텐츠의 내용을 대표할 수 있는 중요 키워드를 선정하고, 콘텐츠 내에서 추출된 키워드간의 연관성을 분석하여 관련 콘텐츠 및 사이트를 추천하는 방법에 대해 제안한다. 또한 연관키워드리스트 생성방법을 고속연관규칙을 이용하여 처리속도를 줄이고, 사용자가 선호할 만한 다양한 콘텐츠와 관련된 사이트를 제공하는 방법에 대해 제안한다.

• Journal of Information Processing Systems
• /
• v.13 no.5
• /
• pp.1052-1070
• /
• 2017

For the autoencoder (AE) implemented as a construction component, this paper uses the method of greedy layer-by-layer pre-training without supervision to construct the stacked autoencoder (SAE) to extract the abstract features of the original input data, which is regarded as the input of the logistic regression (LR) model, after which the click-through rate (CTR) of the user to the advertisement under the contextual environment can be obtained. These experiments show that, compared with the usual logistic regression model and support vector regression model used in the field of predicting the advertising CTR in the industry, the SAE-LR model has a relatively large promotion in the AUC value. Based on the improvement of accuracy of advertising CTR prediction, the enterprises can accurately understand and have cognition for the needs of their customers, which promotes the multi-path development with high efficiency and low cost under the condition of internet finance.

• Asia Marketing Journal
• /
• v.15 no.2
• /
• pp.117-132
• /
• 2013

Recent developments in embodied cognition suggest that people process environmental information by using their bodily state and mental simulation. The focus of embodiment theory is that cognitive processing is based on the interaction among the body, the mind, and the world. Based on embodied theories of cognition, the authors predict that when the representation of marathon running is activated, bodily feedback such as tiredness and thirst will occur because mental simulation of marathon running contains sensorimotor representation of marathon running. As a result, it is predicted that participants primed with marathon runner will have more desire to have products that enable thirsty-quenching. Specifically, this research proposes that consumers' tendency to adopt the perspective of others influences embodied cognition, since perspective taking leads people to assimilate their own self-judgments and behaviors toward the cognitive representations of others. An experiment reveals that both perceptual and cognitive perspective taking tendencies moderate how participants respond to the contextual cues. The effect of perspective taking is moderated by whether participants are prompted to adopt a first-person view or a third-person view. In detail, among the high perspective takers, those in the marathon-first-person condition drink more the mineral water than those in the marathon-third-person condition, who in turn drink more the mineral water than those in the control condition. Among the low perceptual perspective takers, however, there are no significant differences in the amount of mineral water intake. This research delivers important insights for advertising messages. When being exposed to an advertisement, high perspective taking consumers may be more engaged in the advertised message than low perspective taking consumers, which in turn high (vs. low) perspective taking consumers' tendency to respond behaviorally consistent with the message may be higher. Based on the findings of this research, if the message induces the high perspective taking consumers to have a first- (vs. third-) person view, this effect may be stronger. Moreover, if the advertising message contains behaviors, such as using the target product, inducing consumers to mimic the behaviors seems to bring more behavioral responses which marketers intend.