Seoul National University · Computer Science
Professor Soomin Kim's research lab specializes in human-computer interaction, with a focus on leveraging conversational agents and AI to enhance digital communication and decision-making processes. The lab explores the design and evaluation of intelligent chatbots that improve data quality in surveys, facilitate structured group discussions, and support deliberative online dialogue. Additionally, the lab investigates user behaviors in algorithmic systems, including strategies to circumvent or 'game' algorithms in online communities, and examines the socio-technical implications of emerging technologies like blockchain in smart cities. The overarching goal is to create more equitable, transparent, and effective digital interaction systems through human-centered AI design.
Figures are computed from collected data and may differ slightly.
This study aims to explore the feasibility of a text-based virtual agent as a new survey method to overcome the web survey's common response quality problems, which are caused by respondents' inattention. To this end, we conducted a 2 (platform: web vs. chatbot) × 2 (conversational style: formal vs. casual) experiment. We used satisficing theory to compare the responses' data quality. We found that the participants in the chatbot survey, as compared to those in the web survey, were more likely t
Although group chat discussions are prevalent in daily life, they have a number of limitations. When discussing in a group chat, reaching a consensus often takes time, members contribute unevenly to the discussion, and messages are unorganized. Hence, we aimed to explore the feasibility of a facilitator chatbot agent to improve group chat discussions. We conducted a needfinding survey to identify key features for a facilitator chatbot. We then implemented GroupfeedBot, a chatbot agent that could
Online chat functions as a discussion channel for diverse social issues. However, deliberative discussion and consensus-reaching can be difficult in online chats in part because of the lack of structure. To explore the feasibility of a conversational agent that enables deliberative discussion, we designed and developed DebateBot, a chatbot that structures discussion and encourages reticent participants to contribute. We conducted a 2 (discussion structure: unstructured vs. structured) × 2 (discu
Blockchain technology is valuable due to the renowned characteristics, such as immutability, security, and transparency. Although blockchain’s effectiveness and efficiency are yet to be proven, its potential for resolving social issues is attracting the attention of public administrations, private entities, and individuals to adopt or develop this technology. In this paper, some of the most high-profile blockchain-enabled smart city applications in South Korea, the United States and China are sa
Individuals interact with algorithms in various ways. Users even game and circumvent algorithms so as to achieve favorable outcomes. This study aims to come to an understanding of how various stakeholders interact with each other in tricking algorithms, with a focus towards online review communities. We employed a mixed-method approach in order to explore how and why users write machine non-translatable reviews as well as how those encrypted messages are perceived by those receiving them. We fou
Automated journalism, automatically generating stories based on algorithms, has received considerable critical attention in diverse fields. However, automated journalism has not addressed the TV industry in much detail. This research aims to create a system to automatically generate news about TV ratings. The framework will involve undergoing the processes of data gathering, identifying important events by predefined algorithms, generating a story in narrative format, and publishing the output.
Onggi, which is described as a breathing pottery, has strongly influenced the traditional food culture in Korea. In this study Onggi is compared to porcelains including celadon and white porcelain to analyze the sources of pore formation. The differences in starting materials are examined for chemical and mineralogical compositions, particle size and distribution. The gas permeability of the fired samples is correlated to the matrix microstructure. The broad particle size distribution and high i
The benefit of multi-bit flip-flop (MBFF) as opposed to single-bit flip-flop is sharing in-cell clock inverters among the master and slave latches in the internal flip-flops of MBFF. Theoretically, the more flip-flops an MBFF has, the more power saving it can achieve. However, in practice, physically increasing the size of MBFF to accommodate many flip-flops imposes two new challenging problems in physical design: (1) non-flexible MBFF cell flipping for multiple D-to-Q signals and (2) unbalanced
Live quiz shows that make use of mobile applications embed aspects of both games and live streaming. To understand users' motivations and experiences related to these mobile quiz shows, we used a mixed-methods approach that includes interviews (N = 16) and a survey (N = 296). We conducted a thematic analysis of interviews to identify seven motivations, five of which were verified through a factor analysis of survey data: interactivity, offline integration, achievement, ease of enjoyment, and fin
In this article, we aim to offer audiences opportunities to have an immersive experience with the statistical figures in the news. We go beyond the current numerical information representation method to develop a new system for improving the numerical experience. We implemented three different conditions for representing numerical information: 1) text, 2) infographic, 3) VR. We will observe user responses to these methods by measuring engagement, immersion and flow status to detect narrative exp
WARNING: This article contains contents that may offend the readers. Strategies that insert intentional noise into text when posting it are commonly observed in the online space, and sometimes they aim to let only certain community users understand the genuine semantics. In this paper, we explore the purpose of such actions by categorizing them into tricks, memes, fillers, and codes, and organize the linguistic strategies that are used for each purpose. Through this, we identify that such strate
A new congestion control scheme denoted the instantaneous variant of NewReno is proposed. In this method, a sender instantly enters into the slow start phase when it receives the first partial ACK during the fast recovery phase. Performance evaluation shows that the instantaneous variant of NewReno expedites packet loss recovery and increases the goodput.
Open papers in the app to read, cite, and organize with AI.