This page has only limited features, please log in for full access.

Prof. Jinsoo Park
Seoul National University College of Business Administration

Basic Info


Research Keywords & Expertise

0 Interoperability
0 Ontology
0 Ontology Development
0 Ontology Engineering
0 Data Semantics

Honors and Awards

The user has no records in this section


Career Timeline

The user has no records in this section.


Short Biography

The user biography is not available.
Following
Followers
Co Authors
The list of users this user is following is empty.
Following: 0 users

Feed

Journal article
Published: 01 March 2021 in Information Systems Research
Reads 0
Downloads 0

Axiomatic Theories and Improving the Relevance of Information Systems Research This paper examines the fact that a significant number of empirical information systems (IS) studies engage in confirmative testing of self-evident axiomatic theories without yielding highly relevant knowledge for the IS community. The authors conduct both a horizontal analysis of 72 representative IS theories and an in-depth vertical analysis of 3 well-known theories (i.e., technology acceptance model, diffusion of innovation theory, and institutional theory) in order to measure how pervasive such testing of axiomatic theories is. The authors discovered that more than 60% of 666 hypotheses from the horizontal analysis could be regarded as axiomatic theory elements. In the vertical analysis, 68.1% of 1,301 hypotheses from 148 articles were axiomatic. Based on these findings, the authors propose four complementary IS research approaches: (1) identifying disconfirming boundary conditions, (2) measuring the relative importance of axiomatic causal factors, (3) measuring the stage of progression toward visionary goals when the nature of the axiomatic theory can be extended to future visions, and (4) engaging in the conceptual design of visionary axiomatic goals. They argue that these complementary IS research approaches can enhance the relevance of IS research outcomes without sacrificing methodological rigor.

ACS Style

Jae Kyu Lee; Jinsoo Park; Shirley Gregor; Victoria Yoon. Axiomatic Theories and Improving the Relevance of Information Systems Research. Information Systems Research 2021, 32, 147 -171.

AMA Style

Jae Kyu Lee, Jinsoo Park, Shirley Gregor, Victoria Yoon. Axiomatic Theories and Improving the Relevance of Information Systems Research. Information Systems Research. 2021; 32 (1):147-171.

Chicago/Turabian Style

Jae Kyu Lee; Jinsoo Park; Shirley Gregor; Victoria Yoon. 2021. "Axiomatic Theories and Improving the Relevance of Information Systems Research." Information Systems Research 32, no. 1: 147-171.

Journal article
Published: 13 April 2020 in Decision Support Systems
Reads 0
Downloads 0

Proliferating applications of deep learning, along with the prevalence of large-scale text datasets, have revolutionized the natural language processing (NLP) field, thereby driving the recent explosive growth. Nevertheless, it is argued that state-of-the-art studies focus excessively on producing quantitative performances superior to existing models, by playing “the Kaggle game.” Hence, the field requires more effort in solving new problems and proposing novel approaches and architectures. We claim that one of the promising and constructive efforts would be to design transparent and accountable artificial intelligence (AI) systems for text analytics. By doing so, we can enhance the applicability and problem-solving capacity of the system for real-world decision support. It is widely accepted that deep learning models demonstrate remarkable performances compared to existing algorithms. However, they are often criticized for being less interpretable, i.e., the “black box.” In such cases, users tend to hesitate to utilize them for decision-making, especially in crucial tasks. Such complexity obstructs transparency and accountability of the overall system, potentially debilitating the deployment of decision support systems powered by AI. Furthermore, recent regulations are emphasizing fairness and transparency in algorithms to a greater extent, turning explanations more compulsory than voluntary. Thus, to enhance the transparency and accountability of the decision support system and preserve the capacity to model complex text data at the same time, we propose the Explaining and Visualizing Convolutional neural networks for Text information (EVCT) framework. By adopting and ameliorating cutting-edge methods in NLP and image processing, the EVCT framework provides a human-interpretable solution to the problem of text classification while minimizing information loss. Experimental results with large-scale, real-world datasets show that EVCT performs comparably to benchmark models, including widely used deep learning models. In addition, we provide instances of human-interpretable and relevant visualized explanations obtained from applying EVCT to the dataset and possible applications for real-world decision support.

ACS Style

Buomsoo Kim; Jinsoo Park; Jihae Suh. Transparency and accountability in AI decision support: Explaining and visualizing convolutional neural networks for text information. Decision Support Systems 2020, 134, 113302 .

AMA Style

Buomsoo Kim, Jinsoo Park, Jihae Suh. Transparency and accountability in AI decision support: Explaining and visualizing convolutional neural networks for text information. Decision Support Systems. 2020; 134 ():113302.

Chicago/Turabian Style

Buomsoo Kim; Jinsoo Park; Jihae Suh. 2020. "Transparency and accountability in AI decision support: Explaining and visualizing convolutional neural networks for text information." Decision Support Systems 134, no. : 113302.

Journal article
Published: 02 December 2019 in Sustainability
Reads 0
Downloads 0

E-commerce is increasingly competitive and there is a constant need for new approaches and technology to facilitate exchange. Emerging techniques include the use of artificial intelligence (AI). One AI tool that has sparked interest in e-commerce is the automated negotiation agent (negotiation-agent). This study examines such agents, and proposes an offer strategy model of integrative negotiation for a negotiation-agent with a focus on negotiation agent-to-human interaction. More specifically, a new offer strategy was developed based on the integrative bargaining model, which emphasizes the importance of exchanging information among negotiators and multi-issue negotiation that includes package offers to achieve an integrative (win-win) outcome. This study incorporated an argumentation-based negotiation and the negotiation tactic of multiple equivalent simultaneous offers, which was programmed into the negotiation-agent. An experiment was conducted performing 49 negotiation-agent-to-human negotiations over three issues in online purchase tasks to demonstrate the effectiveness of the proposed strategy. Experimental results indicated that the proposed offer strategy with agent negotiation can enhance the persuasiveness of an offer and the performance of negotiation outcome (human counterpart’s perception toward negotiation process, opponent–agent and desire for future negotiation). The findings confirmed the effectiveness of the proposed design and demonstrated an innovative approach to e-commerce transactions.

ACS Style

Jinsoo Park; Hamirahanim Abdul Rahman; Jihae Suh; Hazami Hussin. A Study of Integrative Bargaining Model with Argumentation-Based Negotiation. Sustainability 2019, 11, 6832 .

AMA Style

Jinsoo Park, Hamirahanim Abdul Rahman, Jihae Suh, Hazami Hussin. A Study of Integrative Bargaining Model with Argumentation-Based Negotiation. Sustainability. 2019; 11 (23):6832.

Chicago/Turabian Style

Jinsoo Park; Hamirahanim Abdul Rahman; Jihae Suh; Hazami Hussin. 2019. "A Study of Integrative Bargaining Model with Argumentation-Based Negotiation." Sustainability 11, no. 23: 6832.

Journal article
Published: 25 May 2018 in ACM SIGMIS Database: the DATABASE for Advances in Information Systems
Reads 0
Downloads 0

Information systems (IS) is one of the most rapidly changing disciplines in the social science field, and it is currently facing a new academic shift. The prevailing concepts, such as big data and Internet of things (IoT), imply that there is a plethora of research opportunities for IS researchers. Since these opportunities lie mostly in conjunction with other disciplines closely related to IS, it is essential to identify the interaction between IS and those disciplines. A few studies using bibliometric analysis have been published regarding this topic. However, we have identified several limitations in them: (i) inclusion of only a small journal basket, (ii) focus on a very restricted area of discipline, and (iii) a methodological limitation that can lead to the failure to capture the authentic knowledge flow between IS and other disciplines. We attempt to extend previous studies by proposing a comprehensive analysis model with the largest journal basket and areas of disciplines. As a result of our analysis, a knowledge flow structure different from that of past research is identified. In addition, through the discussion on emerging reference disciplines, we discover new research opportunities into which IS researchers can delve.

ACS Style

Kyuhan Lee; Jinsoo Park; Jihae Suh. Investigating Knowledge Flows between Information Systems and Other Disciplines:. ACM SIGMIS Database: the DATABASE for Advances in Information Systems 2018, 49, 14 -34.

AMA Style

Kyuhan Lee, Jinsoo Park, Jihae Suh. Investigating Knowledge Flows between Information Systems and Other Disciplines:. ACM SIGMIS Database: the DATABASE for Advances in Information Systems. 2018; 49 (2):14-34.

Chicago/Turabian Style

Kyuhan Lee; Jinsoo Park; Jihae Suh. 2018. "Investigating Knowledge Flows between Information Systems and Other Disciplines:." ACM SIGMIS Database: the DATABASE for Advances in Information Systems 49, no. 2: 14-34.

Article
Published: 19 August 2016 in Information Systems Frontiers
Reads 0
Downloads 0

Previous studies on predicting the box-office performance of a movie using machine learning techniques have shown practical levels of predictive accuracy. Their works are technically- and methodologically-oriented, focusing mainly on what algorithms are better at predicting the movie performance. However, the accuracy of prediction model can also be elevated by taking other perspectives such as introducing unexplored features that might be related to the prediction of the outcomes. In this paper, we examine multiple approaches to improve the performance of the prediction model. First, we develop and add a new feature derived from the theory of transmedia storytelling. Such theory-driven feature selection not only increases the forecast accuracy, but also enhances the interpretability of a prediction model. Second, we use an ensemble approach, which has rarely been adopted in the research on predicting box-office performance. As a result, the proposed model, Cinema Ensemble Model (CEM), outperforms the prediction models from the past studies that use machine learning algorithms. We suggest that CEM can be extensively used for industrial experts as a powerful tool for improving decision-making process.

ACS Style

Kyuhan Lee; Jinsoo Park; Iljoo Kim; Youngeok Choi. Predicting movie success with machine learning techniques: ways to improve accuracy. Information Systems Frontiers 2016, 20, 577 -588.

AMA Style

Kyuhan Lee, Jinsoo Park, Iljoo Kim, Youngeok Choi. Predicting movie success with machine learning techniques: ways to improve accuracy. Information Systems Frontiers. 2016; 20 (3):577-588.

Chicago/Turabian Style

Kyuhan Lee; Jinsoo Park; Iljoo Kim; Youngeok Choi. 2016. "Predicting movie success with machine learning techniques: ways to improve accuracy." Information Systems Frontiers 20, no. 3: 577-588.

Journal article
Published: 01 April 2016 in Journal of Database Management
Reads 0
Downloads 0

This research proposes a novel method of measuring the dynamics of semantic relatedness. Research on semantic relatedness has a long history in the fields of computational linguistics, psychology, computer science, as well as information systems. Computing semantic relatedness has played a critical role in various situations, such as data integration and keyword recommendation. Many researchers have tried to propose more sophisticated techniques to measure semantic relatedness. However, little research has considered the change of semantic relatedness with the flow of time and occurrence of events. The authors' proposed method is validated by actual corpus data collected from a particular context over a specific period of time. They test the feasibility of our proposed method by constructing semantic networks by using the corpus collected during a different period of time. The experiment results show that our method can detect and manage the changes in semantic relatedness between concepts. Based on the results, the authors discuss the need for a dynamic semantic relatedness paradigm.

ACS Style

Youngseok Choi; Jungsuk Oh; Jinsoo Park. A Novel Approach to Managing the Dynamic Nature of Semantic Relatedness. Journal of Database Management 2016, 27, 1 -26.

AMA Style

Youngseok Choi, Jungsuk Oh, Jinsoo Park. A Novel Approach to Managing the Dynamic Nature of Semantic Relatedness. Journal of Database Management. 2016; 27 (2):1-26.

Chicago/Turabian Style

Youngseok Choi; Jungsuk Oh; Jinsoo Park. 2016. "A Novel Approach to Managing the Dynamic Nature of Semantic Relatedness." Journal of Database Management 27, no. 2: 1-26.

Journal article
Published: 31 March 2013 in Journal of Intelligence and Information Systems
Reads 0
Downloads 0
ACS Style

Youngseok Choi; Jinsoo Park. The Need for Paradigm Shift in Semantic Similarity and Semantic Relatedness : From Cognitive Semantics Perspective. Journal of Intelligence and Information Systems 2013, 19, 111 -123.

AMA Style

Youngseok Choi, Jinsoo Park. The Need for Paradigm Shift in Semantic Similarity and Semantic Relatedness : From Cognitive Semantics Perspective. Journal of Intelligence and Information Systems. 2013; 19 (1):111-123.

Chicago/Turabian Style

Youngseok Choi; Jinsoo Park. 2013. "The Need for Paradigm Shift in Semantic Similarity and Semantic Relatedness : From Cognitive Semantics Perspective." Journal of Intelligence and Information Systems 19, no. 1: 111-123.

Chapter
Published: 22 January 2013 in Innovations in Database Design, Web Applications, and Information Systems Management
Reads 0
Downloads 0

The information space of the Semantic Web has different characteristics from that of the World Wide Web (WWW). One main difference is that in the Semantic Web, the direction of Resource Description Framework (RDF) links does not have the same meaning as the direction of hyperlinks in the WWW, because the link direction is determined not by a voting process but by a specific schema in the Semantic Web. Considering this fundamental difference, the authors propose a method for ranking Semantic Web resources independent of link directions and show the convergence of the algorithm and experimental results. This method focuses on the classes rather than the properties. The property weights are assigned depending on the relative significance of the property to the resource importance of each class. It solves some problems reported in prior studies, including the Tightly Knit Community (TKC) effect, as well as having higher accuracy and validity compared to existing methods.

ACS Style

Hyunjung Park; Sangkyu Rho; Jinsoo Park. A Link-Based Ranking Algorithm for Semantic Web Resources. Innovations in Database Design, Web Applications, and Information Systems Management 2013, 1 -25.

AMA Style

Hyunjung Park, Sangkyu Rho, Jinsoo Park. A Link-Based Ranking Algorithm for Semantic Web Resources. Innovations in Database Design, Web Applications, and Information Systems Management. 2013; ():1-25.

Chicago/Turabian Style

Hyunjung Park; Sangkyu Rho; Jinsoo Park. 2013. "A Link-Based Ranking Algorithm for Semantic Web Resources." Innovations in Database Design, Web Applications, and Information Systems Management , no. : 1-25.

Research article
Published: 20 November 2012 in Information Development
Reads 0
Downloads 0

This paper tries to identify what shapes the mobile services industry and what changes will take place to the worldwide mobile business. Two case markets are introduced for comparison and analysis: Japan and Finland. Japan is an exemplar country where both the mobile subscription penetration rate and the revenue from data transfer are world record high. Finland is a birthplace of the world’s leading handset manufacturer as well as the center for a substantial number of innovations in Europe. The two countries represent a stark contrast in the industry structure: vertical and integrated vs. horizontal and modular. After an in-depth comparison of the two markets, a brief prospect of the future mobile industry is provided.

ACS Style

Jinsoo Park; Minjung Choi. A cross-national study on mobile business: how will ecosystems evolve? Information Development 2012, 30, 9 -21.

AMA Style

Jinsoo Park, Minjung Choi. A cross-national study on mobile business: how will ecosystems evolve? Information Development. 2012; 30 (1):9-21.

Chicago/Turabian Style

Jinsoo Park; Minjung Choi. 2012. "A cross-national study on mobile business: how will ecosystems evolve?" Information Development 30, no. 1: 9-21.