• 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.

• Journal of the HCI Society of Korea
• /
• v.2 no.1
• /
• pp.13-24
• /
• 2007

For many years, human-computer interaction (HCI) practitioners have focused on usability in order to enhance the user experience, and companies have seen it as an area where they can gain advantages over their competitors. However, a focus on usability limits the potential of HCI research because it restricts the concept of user experience to just an implemented functionality of the information technology (IT). Therefore, it is necessary to expand the boundary of user experience research into a holistic dimension. We suggest that one of the most powerful ways to broadly understand user experience with an IT is to investigate the attributes of an IT and users' perceived values and to construct a user experience structure, a hierarchical structure between the attributes of an IT and users' perceived values. This study thus undertakes two research tasks: to develop a specific methodology, which is the visual probing, for constructing a user experience structure with the attributes of an IT and users' perceived values, and then to build a user experience structure practically by conducting a case study to a specific IT: mobile data service.

• Archives of design research
• /
• v.16 no.2
• /
• pp.395-404
• /
• 2003

As scenario-based design is expanded to various fields of design, it is introduced to HCI(Human Computer Interaction) in order to figure out user information & tasks. However, scenario based design methods that is focused on collecting scenarios regarding users'needs, is mainly utilized conceptual design stage for system itself. There is a gap between users'need scenarios to interface design of HCI system. In this study, web survey is suggested as scenario based interface design method in order to connect scenario collecting to task specification and to menu structure design of home-network controller. The degree of users'need for specified tasks was verified to various kinds of users through web survey and it decideddepth and order of menu structure. Tasks also was categorized to situation mode and users can make their own menu structure by selecting menu contents or even mode itself, because degrees of need for specified task situation were varied by lifestyle of user group. Finally, it is found that web survey method can be applied to collect and database various scenarios of. various users when a questionnaire is well designed for collection.

• The Journal of Information Systems
• /
• v.27 no.1
• /
• pp.153-169
• /
• 2018

Purpose Since human brains catch images faster than texts or numbers, infographics has been widely used in business in the form of "information dashboard" to enhance the efficiency of decision-making. Groupware, however, has neglected the adoption and use of infographics, in particular, in the idea generation process. Given that an overall performance of groupware-based idea generation is no better than that of the (paper-and-pencil-based) Nominal Group Technique, Jung et al. (2010) adopted the notion of infographics in the form of performance feedback to solve the productivity paradox. With the consistent results, which demonstrate beneficial effects of infographics on performance enhancement, an interesting observation that groups with the bar chart treatment performed better than groups with the dot chart treatment was made. The main purpose of this study was to find if there were a performance consistency between the outcomes from the previous study and the outcomes from the current study. Design/methodology/approach In experiment 1, we employed the same system used in the previous study (i.e., Jung et al., 2010). As individuals' contributions accumulated, the mechanism visually displayed individuals' performances two-dimensionally in the form of a bar chart or a dot chart. Then, we compared the performance outcomes from this study to the outcomes from previous study (i.e., Jung et al., 2010). In experiment 2, we modified the performance graph to test the effect of "playfulness" on performance by converting dots to car images. Then, we compared the performance outcome from experiment 2 to the outcomes from experiment 1. Findings Just like our interesting (and unexpected) finding in Jung et al.'s study (2010), the outcome confirmed a consistent superior performance of a bar chart. This implies that a bar chart is a better choice when stimulating performance with a visual aid in the context of groupware-based idea generation. Although a bar chart was criticized in a way that errors of length-area judgments are 40 ~ 250% greater than those of positional judgments along a common scale, such illusion turned out to be facilitating upward performance comparison better. Regarding Experiment 2, the outcome showed that the revised-dot graph is as good as the bar graph in terms of quantity and quality score of ideas. We attribute the performance enhancement of the resized-dot to the interaction between the motivational characteristic and the situational characteristic of playfulness because individuals in the revised-dot graph treatment performed better than individuals in the dot graph treatment. Given the order of performance (Bar >= Revised Dot > Dot) that the revised-dot treatment performed the same as (or lower than) the bar treatment, an additional research is warranted to reach to a consistent outcome.

• Journal of the HCI Society of Korea
• /
• v.11 no.3
• /
• pp.23-30
• /
• 2016

The landscape of the current fitness trackers is not only limited to the aerobic exercises but also the weight training is comparatively excluded. Recently, a few weight training fitness tracker was released, human-computer interaction was not well designed due to the lack of considering the context. Because body movement would be intense while doing exercises, having exercise performers hold or operate a device makes a negative experience. As the wearable device is always inseparable to body, it could provide effective feedback because holding or operating a device is not necessary. Therefore, this study aims to make the exercise performers feel a natural feedback through the wearable device to do effective exercises. As a result, this study identified three findings. First, the information which exercise performers most needed was 'during exercise.' and the most necessary information for exercise performers through wearable device's sensory feedback was about 'pace control' with counting and motivation. Second, the order of the most preferred presentation type of sensory feedback was auditory feedback, haptic feedback and visual feedback. Third, the satisfaction, utility, usefulness score of sensory feedback as same as the personal trainer's feedback. In conclusion, this study illustrated the feedback design implications using a wearable device while doing weight training and the possibilities that wearable device could be substitute for personal trainer.

• The KIPS Transactions:PartD
• /
• v.18D no.3
• /
• pp.179-184
• /
• 2011

Current mobile devices have surpassed its boundaries as a more communication tool to a smart device which provides additional features. These features have supported the smart life of its users, but have reached its limit from low-performance processors and short-battery time. These issues can be resolved b implementing higher performing hardware, but they come with a burden of high cost. This paper introduces a new way of managing computing resources in a mobile device by enhancing the quality of human-computer interaction. The real-speed felt by users are mainly influenced by the time it takes form a user's input to the device to display the completed result on the screen. Since the size of the screen for mobile devices are small, if the processor only fetch data to be used for displaying on screen, the time can be significantly reduced. MVC+Prefetch Controller pattern accomplished this goal by using the minimum amount of data from DB to fetch display and still manages to support high-speed data transfer to achieve seamless display. This idea has been realized by practice using Samsung mobile phone S8500, which demonstrated the superior performance on user's perspective.

• Journal of Intelligence and Information Systems
• /
• v.20 no.2
• /
• pp.179-192
• /
• 2014

Keeping in line with the recent changes in the information technology environment, the online learning environment that supports multiple users' participation such as MOOC (Massive Open Online Courses) has become important. One of the largest professional associations in Information Technology, IEEE Computer Society, announced that "Supporting New Learning Styles" is a crucial trend in 2014. Popular MOOC services, CourseRa and edX, have continued to build active learning environment with a large number of lectures accessible anywhere using smart devices, and have been used by an increasing number of users. In addition, collaborative web services (e.g., blogs and Wikipedia) also support the creation of various user-uploaded learning materials, resulting in a vast amount of new lectures and learning materials being created every day in the online space. However, it is difficult for an online educational system to keep a learner' motivation as learning occurs remotely, with limited capability to share knowledge among the learners. Thus, it is essential to understand which materials are needed for each learner and how to motivate learners to actively participate in online learning system. To overcome these issues, leveraging the constructivism theory and collective intelligence, we have developed a social bookmarking system called WeStudy, which supports learning material sharing among the users and provides personalized learning material recommendations. Constructivism theory argues that knowledge is being constructed while learners interact with the world. Collective intelligence can be separated into two types: (1) collaborative collective intelligence, which can be built on the basis of direct collaboration among the participants (e.g., Wikipedia), and (2) integrative collective intelligence, which produces new forms of knowledge by combining independent and distributed information through highly advanced technologies and algorithms (e.g., Google PageRank, Recommender systems). Recommender system, one of the examples of integrative collective intelligence, is to utilize online activities of the users and recommend what users may be interested in. Our system included both collaborative collective intelligence functions and integrative collective intelligence functions. We analyzed well-known Web services based on collective intelligence such as Wikipedia, Slideshare, and Videolectures to identify main design factors that support collective intelligence. Based on this analysis, in addition to sharing online resources through social bookmarking, we selected three essential functions for our system: 1) multimodal visualization of learning materials through two forms (e.g., list and graph), 2) personalized recommendation of learning materials, and 3) explicit designation of learners of their interest. After developing web-based WeStudy system, we conducted usability testing through the heuristic evaluation method that included seven heuristic indices: features and functionality, cognitive page, navigation, search and filtering, control and feedback, forms, context and text. We recruited 10 experts who majored in Human Computer Interaction and worked in the same field, and requested both quantitative and qualitative evaluation of the system. The evaluation results show that, relative to the other functions evaluated, the list/graph page produced higher scores on all indices except for contexts & text. In case of contexts & text, learning material page produced the best score, compared with the other functions. In general, the explicit designation of learners of their interests, one of the distinctive functions, received lower scores on all usability indices because of its unfamiliar functionality to the users. In summary, the evaluation results show that our system has achieved high usability with good performance with some minor issues, which need to be fully addressed before the public release of the system to large-scale users. The study findings provide practical guidelines for the design and development of various systems that utilize collective intelligence.