• Journal of Korean Society for Quality Management
• /
• v.50 no.1
• /
• pp.43-61
• /
• 2022

Purpose: The purpose of this study was verifying factors that affect to intention to use AI financial services and finding a way of building an user oriented AI ecology. Methods: This study used the UTAUT (Unified Theory of Acceptance and Use of Technology) model with independent variables such as performance expectancy, effort expectancy, social influence, facilitating conditions, trust, personal innovativeness and AI understanding as moderating variable. The data was collected through online & offline survey with questionnaire from 330 financial customers. Results: As a result, the analysis suggested that the performance expectancy, social influence, facilitating conditions, personal innovativeness are statistically significant to the intention to use AI. It was also found that AI knowledge of users differently influence the intention to use through the moderating effect on the facilitating conditions. Conclusion: Performance expectancy, social influence, facilitating conditions, personal innovativeness have positive causation to the intention to use in AI financial service. On the facilitating conditions, unlike other variables, it was found that the user's intention to use was different by the level of AI understanding. It means that customers could have the strong intention to use AI even though they don't have enough pieces of knowledge on the factors. Customers seem to be of recognition that the technology has certain benefits for themselves. The facilitating factors are significantly affected by AI understanding and differently effect on the intention to use AI.

• Management & Information Systems Review
• /
• v.34 no.3
• /
• pp.79-100
• /
• 2015

This study is to examine the factors that influence purchasing behavior and decision-making when consumers buy goods through mobile shopping, define purchasing decision-making with the steps of problem recognition, information search, alternative assessment, and purchasing behavior to understand mobile consumer behavior, and investigate how the factors of each step play roles and influence consumers' purchasing decision-making through positive analysis to figure out consumer purchasing behavior in mobile shopping. The study results, First, the user characteristics of information search influence flow. Second, in the relations between the user characteristics in the step of information search and perceived risk in alternative assessment, if recognition on gains is higher, perceived risk for time loss gets lower, and when the level of skills is higher, perceived risk gets higher, and it has been partly adopted that innovativeness does not influence risk perception. Third, in the relations between flow experience and purchasing intention, it has been found to be partially significant that remote presence and challenge do not influence purchasing intention but do influence excitement, attention concentration, and control and also do influence perceived risk and purchasing intention. Fourth, according to the results of analyzing the difference of consumer purchasing behavior by the types of involvement, practical involvement and sensual involvement, user characteristics and flow, and perceived risk differ by the types of products in terms of the search process, thereby changing purchasing intention. Lastly, the significance and limitations of this study was discussed.

• Annual Conference on Human and Language Technology
• /
• 1996.10a
• /
• pp.393-399
• /
• 1996

자연언어 대화에서 사용자의 정확한 의도(Intention)를 인지함에 있어서 나타나는 문제는, 자연언어 대화체의 생략성이 강한 문장의 불완전성 외에도, 여러 연속되는 대화체 문장에 분산되어 나타나는 사용자의 의도를 정확히 파악하는 것이다. 이러한 불완전한 대화체 문장 속에 산재되어 있는 사용자의 의도를 빠르고 신뢰성 있게 인지하여, 사용자와 시스템간의 원활한 자연언어 대화 상호작용 (Interaction)을 가능하게 하기 위하여 플랜 인지 시스템의 이용은 매우 효과적으로 보인다. 현재까지 개발된 대부분의 플랜 인지시스템들은 사용자의 액션 분석 및 플랜의 인지를 통하여 HCI를 지원하는 측면에 (예: 지능형 도움말) 집중되어 있다. 본 논문은 지역 광고 신문에 실린 매입-매도광고 데이타베이스의 검색을 위한 Natural language dialogue user interface에서 사용자 의도를 인지할 수 있는 플랜 인지 시스템을 기술하고 있다.

• Journal of Distribution Science
• /
• v.14 no.10
• /
• pp.165-178
• /
• 2016

Purpose - This study aims to empirically verify the impact of media richness, social presence, and prior life satisfaction on various continual usage or withdrawal behaviors of SNS users via both a positive path of satisfaction and a negative path of relative deprivation. By identifying these causal paths, we observe dynamic interactions of SNS user psychology in a balanced view, and provide some implications about design principles for SNS providers. Research design, data, and methodology - We developed 16 hypothesis based on media richness theory, social presence theory, social comparison theory, the literature about relative deprivation, and the literature about the various reactions of IS users. The rich SNS media, social presence recognition among peer SNS users, and prior life satisfaction could generate positive experience, attitude, and virtuous behavioral intentions among SNS users. At the same time, rich media, low social presence, and low prior life satisfaction could generate relative deprivation and could increase withdrawal behavioral intentions such as refusal to provide information, misrepresentation of information, and removal of uploaded information in SNS. Scenario surveys were conducted to collect data from potential SNS users. Data from 357 surveys were collected and analyzed through a PLS algorithm to test the hypotheses. Results - Media richness, social presence, and prior life satisfaction could significantly increase perceived enjoyment, satisfaction, and behavioral intention of continual usage and knowledge sharing. They also could significantly decrease refusal and misrepresentation intention. Relative deprivation is significantly decreased only by prior life satisfaction. Relative deprivation could not significantly decrease satisfaction, but it could significantly increase misrepresentation and removal intention, which could be regarded as information distortion intention. Conclusions - SNS providers should focus on developing rich media and social presence support because these two variables could impact the positive experiences of SNS users. Moreover, the positive experiences could heavily influence SNS user behavior. Some management is needed to prevent relative deprivation and its consequences of misrepresentation and removal intention. SNS providers should prevent SNS users from excessive image misrepresentation and removal as this information distortion could be the source of relative deprivation.

• Convergence Security Journal
• /
• v.11 no.3
• /
• pp.55-66
• /
• 2011

This research focus on the value of smart phones for university students in Korea, considering on the correlations between the main causes influencing intrinsic value(price attributes, function attributes), network value(learning effects attributes, externalities attributes) user satisfaction, and intentions of repurchase of the smart phones market in Korea. Through the statistical analyses on the 8 hypotheses from a research model, we found that intrinsic value and network value gave an attentive influence on user satisfaction and repurchase intention. Call charge and Liquid crystal display and Design of smart phone have an influenced user satisfaction and repurchase intention.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.267-286
• /
• 2023

The conversational agents such as AI speakers utilize voice conversation for human-computer interaction. Voice recognition errors often occur in conversational situations. Recognition errors in user utterance records can be categorized into two types. The first type is misrecognition errors, where the agent fails to recognize the user's speech entirely. The second type is misinterpretation errors, where the user's speech is recognized and services are provided, but the interpretation differs from the user's intention. Among these, misinterpretation errors require separate error detection as they are recorded as successful service interactions. In this study, various text separation methods were applied to detect misinterpretation. For each of these text separation methods, the similarity of consecutive speech pairs using word embedding and document embedding techniques, which convert words and documents into vectors. This approach goes beyond simple word-based similarity calculation to explore a new method for detecting misinterpretation errors. The research method involved utilizing real user utterance records to train and develop a detection model by applying patterns of misinterpretation error causes. The results revealed that the most significant analysis result was obtained through initial consonant extraction for detecting misinterpretation errors caused by the use of unregistered neologisms. Through comparison with other separation methods, different error types could be observed. This study has two main implications. First, for misinterpretation errors that are difficult to detect due to lack of recognition, the study proposed diverse text separation methods and found a novel method that improved performance remarkably. Second, if this is applied to conversational agents or voice recognition services requiring neologism detection, patterns of errors occurring from the voice recognition stage can be specified. The study proposed and verified that even if not categorized as errors, services can be provided according to user-desired results.

• Korean Journal of Cognitive Science
• /
• v.21 no.4
• /
• pp.459-480
• /
• 2010

A dialogue system includes various morphological analyses for recognizing a user's intention from the user's utterances. However, a user can represent various intentions via emotional states in addition to morphological expressions. Thus, a user's emotion recognition can analyze a user's intention in various manners. This paper presents a new method to automatically recognize a user's emotion for a dialogue system. For general emotions, we define nine categories using a psychological approach. For an optimal feature set, we organize a combination of sentential, a priori, and context features. Then, we employ a support vector machine (SVM) that has been widely used in various learning tasks to automatically classify a user's emotions. The experiment results show that our method has a 62.8% F-measure, 15% higher than the reference system.

• The Journal of Korea Robotics Society
• /
• v.19 no.2
• /
• pp.203-212
• /
• 2024

Simultaneous motion is essential in the activities of daily living (ADL). For motion intention recognition, surface electromyogram (sEMG) and corresponding motion label is necessary. However, this process is time-consuming and it may increase the burden of the user. Therefore, we propose a simultaneous motion recognition framework using data augmentation based on muscle activation model. The model consists of multiple point sources to be optimized while the number of point sources and their initial parameters are automatically determined. From the experimental results, it is shown that the framework has generated the data which are similar to the real one. This aspect is quantified with the following two metrics: structural similarity index measure (SSIM) and mean squared error (MSE). Furthermore, with k-nearest neighbor (k-NN) or support vector machine (SVM), the classification accuracy is also enhanced with the proposed framework. From these results, it can be concluded that the generalization property of the training data is enhanced and the classification accuracy is increased accordingly. We expect that this framework reduces the burden of the user from the excessive and time-consuming data acquisition.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.9
• /
• pp.215-223
• /
• 2017

Various methods for creating interesting games are used in the development process. Because the empirical part is difficult to measure and analyze, it usually only measures and analyzes the parts where data are easy to quantify. This is a clear limit to the fact that the experience of the game is important.This study proposes a system that recognizes the face of a game user and measures the emotion change from the recognized information in order to easily quantify the experience of the user who is playing the game. The system recognizes emotions and records them in real time from the face of the user who is playing the game. These recorded data include time and figures related to the progress of the game, and numerical values for emotions recognized from the face. Using the recorded data, it is possible to judge what kind of emotion the game induces to the user at a certain point in time. Numerical data on the recorded empirical part using the system of this study is expected to help develop the game according to the developer 's intention.

• Journal of KIISE
• /
• v.42 no.12
• /
• pp.1544-1550
• /
• 2015

Recently, the development of practical wearable robot interfaces has resulted in the emergence of wearable robots such as arm prosthetics or lower-limb exoskeletons. In this paper, we propose a novel method of wrist movement intention estimation based on a regression technique using electromyography of human bio-signals. In daily life, changes in user arm position changes cause decreases in performance by modulating EMG signals. Therefore, we propose an estimation method for robust wrist movement intention for arm position changes, combining several movement intention models based on the regression technique trained by different arm positions. In our experimental results, our method estimates wrist movement intention more accurately than previous methods.