• Journal of Information Processing Systems
• /
• v.17 no.4
• /
• pp.818-833
• /
• 2021

To address the problems of low precision rate, insufficient feature extraction, and poor contextual ability in existing text sentiment analysis methods, a mixed model account of a CNN-BiLSTM-TE (convolutional neural network, bidirectional long short-term memory, and topic extraction) model was proposed. First, Chinese text data was converted into vectors through the method of transfer learning by Word2Vec. Second, local features were extracted by the CNN model. Then, contextual information was extracted by the BiLSTM neural network and the emotional tendency was obtained using softmax. Finally, topics were extracted by the term frequency-inverse document frequency and K-means. Compared with the CNN, BiLSTM, and gate recurrent unit (GRU) models, the CNN-BiLSTM-TE model's F1-score was higher than other models by 0.0147, 0.006, and 0.0052, respectively. Then compared with CNN-LSTM, LSTM-CNN, and BiLSTM-CNN models, the F1-score was higher by 0.0071, 0.0038, and 0.0049, respectively. Experimental results showed that the CNN-BiLSTM-TE model can effectively improve various indicators in application. Lastly, performed scalability verification through a takeaway dataset, which has great value in practical applications.

• Science of Emotion and Sensibility
• /
• v.25 no.3
• /
• pp.107-116
• /
• 2022

Purpose: Researchers have shown that aesthetic judgments of artworks depend on contexts, such as the authenticity of an artwork (Newman & Bloom, 2011) and an artwork's location of display (Kirk et al., 2009; Silveira et al., 2015). The present study aims to examine whether contextual information related to the creator, such as whether an artwork was created by a human or artificial intelligence (AI), influences viewers' preference judgments of an artwork. Methods: Images of Impressionist landscape paintings were selected as human-made artworks. AI-made artwork stimuli were created using Google's Deep Dream Generator by mimicking the Impressionist style via deep learning algorithms. Participants performed a preference rating task on each of the 108 artwork stimuli accompanied by one of the two creator labels. After this task, an art experience questionnaire (AEQ) was given to participants to examine whether individual differences in art experience influence their preference judgments. Results: Setting AEQ scores as a covariate in a two-way ANCOVA analysis, the stimuli with the human-made context were preferred over the stimuli with the AI-made context. Regarding the types of stimuli, the viewers preferred AI-made stimuli to human-made stimuli. There was no interaction effect between the two factors. Conclusion: These results suggest that preferences for visual artworks are influenced by the contextual information of the creator when the individual differences in art experience are controlled.

• Journal of KIISE
• /
• v.43 no.10
• /
• pp.1154-1164
• /
• 2016

To prevent the use of one's smartphone by another user, the authentication checks the owner in several ways. However, whenever the owner does use his/her smartphone, this authentication requires an unnecessary action, and sometimes he/she finally decides not to use an authentication method. This can cause a fatal problem in the smartphone's security. We propose a sustainable android platform-based authentication mode to solve this security issue and to facilitate secure authentication. In the proposed model, a smartphone identifies the current situation and then performs the authentication. In order to define the risk of the situation, we conducted a survey and analyzed the survey results by age, location, behavior, etc. Finally, a demonstration program was implemented to show the relationship between risk and security authentication methods.

• 한국HCI학회:학술대회논문집
• /
• 2006.02b
• /
• pp.543-548
• /
• 2006

2005년 발표된 애플사의 아이포드 셔플 디지털 음악 재생기는 오랫동안 잊혀지거나 제대로 사용되지 않았던 음악 재생 방법인 셔플(Shuffle)기능에 대한 재조명을 하고 이를 새로운 사용자 경험으로 만들어 냈다. 본 논문에서는 이와 같은iPod 셔플, 라디오등 음악 콘텐츠의 선곡과 플레이하는 방법에 대해 비교 분석하였으며 이를 통해 보다 향상된 방법으로서 컨텐츠 저장구조를 항해하는것이 가능하면서도 사용자의 특별한 의지에 의한 조종없이도 적절한 선곡을 제공하며 또한 특별한 그래픽 유저 인터페이스 장치를 필요로 하지 않는 방법이 필요함을 고찰하였다. 이러한 분석된 결과를 바탕으로 맥락적 컨텐츠 구성 방법에 관한 새로운 디자인안을 창출하였다. 이 디자인 안은 사용자 사용패턴 추출장치, 가상 채널 형성 장치, 환경 분석 장치로 구성된 지능화된 컴퓨터 시스템에 의해 사용자에게 맥락적인 무작위 음악 재생 방법을 제공하는 것이다.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.1
• /
• pp.33-39
• /
• 2010

The interaction of emotion is an important factor in Human-Robot Interaction(HRI). This requires a contextual appraisal of emotion extracting the emotional information according to the events happened from past to present. In this paper an emotion appraisal system based on the cognitive context is presented. Firstly, a conventional emotion appraisal model is simplified to model a contextual emotion appraisal which defines the types of emotion appraisal, the target of the emotion induced from analyzing emotional verbs, and the transition of emotions in the context. We employ a language based cognitive system and its sentential memory and object descriptor to define the type and target of emotion and to evaluate the emotion varying with the process of time with the a priori emotional evaluation of targets. In a experimentation, we simulate the proposed emotion appraisal system with a scenario and show the feasibility of the system to HRI.

• Journal of Information Technology Applications and Management
• /
• v.9 no.4
• /
• pp.179-204
• /
• 2002

The purpose of this study is to empirically Investigate the critical success factors affecting the participation of B2B e-marketplace from a perspective of buyers and sellers. The research model presented in this study suggests that the success of B2B e-marketplace depends on the degree of participation of buyers and sellers. It is hypothesized that the participation of buyers and sellers is related with several contextual factors. The contextual factors included: (a) industry and market factor; (b) Internal environment factor; (c) product factor; (d) Inter-organizational factor; and (e) B2B e-marketplace system and strategy factor. An analysis of data from 31 buyer firms and 31 seller firms reveals that those five factors have a significant effect on the participation and success of B2B e-marketplace. The implications of the study are discussed and further research directions are proposed.

• Journal of Korea Multimedia Society
• /
• v.24 no.12
• /
• pp.1693-1707
• /
• 2021

The purpose of this study was to improve the experience of visiting obstetrics and gynecology of single women. After analyzing previous studies on Korean single women's perception of visiting obstetrics and gynecology, Contextual Interviews and Cultural Probes were conducted on single women in their 20s who visited obstetrics and gynecology. Based on this, personas were constructed to solidify the direction of problem solving by identifying the behavioral patterns and characteristics of single women. In this study, factors that hinder unmarried women's visits to obstetrics and gynecology and improvement measures were derived based on the information obtained using service design tools such as User Journey Mapping and Stakeholders' Map. Afterwards, a preference survey was conducted to increase the persuasiveness of the proposed method. The follow-up research task is to produce and propose the derived solution as a prototype that can be used in the actual field, and then proceed with user evaluation.

• ETRI Journal
• /
• v.45 no.1
• /
• pp.93-104
• /
• 2023

Coreference resolution is a task in discourse analysis that links several headwords used in any document object. We suggest pointer networks-based coreference resolution for Korean using multi-task learning (MTL) with an attention mechanism for a hierarchical structure. As Korean is a head-final language, the head can easily be found. Our model learns the distribution by referring to the same entity position and utilizes a pointer network to conduct coreference resolution depending on the input headword. As the input is a document, the input sequence is very long. Thus, the core idea is to learn the word- and sentence-level distributions in parallel with MTL, while using a shared representation to address the long sequence problem. The suggested technique is used to generate word representations for Korean based on contextual information using pre-trained language models for Korean. In the same experimental conditions, our model performed roughly 1.8% better on CoNLL F1 than previous research without hierarchical structure.

• Proceedings of the Korea Society of Design Studies Conference
• /
• 2005.05a
• /
• pp.268-269
• /
• 2005

• Korean Journal of Remote Sensing
• /
• v.5 no.2
• /
• pp.85-90
• /
• 1989

A new graph-theoretic clustering method based on relaxation labeling is proposed. More accurate classification is achieved by using relaxation labeling which take advantage of contextual information. Moreover, threshold selection is not needed in this method.