Donghyuk Shin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Donghyuk Shin has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Ahyun Kim
Department of Chemistry, Yonsei University, Seoul 03722, Republic of Korea
1 shared publication Amy Ostrom
W. P. Carey School of Business, Arizona State University, Tempe, USA
1 shared publicationAndrew B. Whinston
University of Texas at Austin - Department of Information, Risk and Operations Management
1 shared publicationAnimesh Animesh
McGill University
1 shared publication- Ga Young Ko
Kyung Hee University
1 shared publication - Gene Moo Lee
University of British Columbia
1 shared publication
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 6856-6859
When Persona Simulations Are Informative: Graph-Structured Signals for Pluralistic Opinion Sensing
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 6856-6859
Open AccessWhen Persona Simulations Are Informative: Graph-Structured Signals for Pluralistic Opinion Sensing
- 17 June 2026
- Published by SAGE Publications in Journal of Service Research
- Vol. 29 (3) , 339-359
The 2026 Service Research Priorities: AI-Driven Discovery, Interdisciplinary Influence Dynamics, and the “Interactive Service Scholarship Incubator” for Personalized Priorities
This article presents the 2026 Service Research Priorities (SRPs), developed via a hybrid AI–human agenda-setting approach. We construct large-scale concept networks from more than 10,500 service-related articles in core service journals and Financial Times (FT) 50 outlets, and apply machine-learning link prediction to identify high-probability, but underexplored, concept pairs. Fifteen forward-looking themes emerge that fall into four topical clusters: (a) Human–AI Agency, Interactions, and Service Reconfiguration; (b) AI-Enabled Omnichannel Engagement and Ecosystem Orchestration; (c) Responsible, Inclusive, and Resilient AI Service Systems; and (d) Psychological Dynamics of Service Experiences. Comparing the themes’ relevance in the service outlets vis-à-vis the FT50 journals helps identify where service research currently leads, where it imports from adjacent disciplines, and where cross-fertilization is most promising. Furthermore, we reflect our themes against the 2021 SRPs, distinguishing “emerging,” “evolved,” and “continuing” priorities. Importantly, we also survey the Journal of Service Research leadership to further calibrate and enrich the AI-derived SRPs. Next, we introduce a new descriptive statistic, the “Interdisciplinary Influence Index,” to map which disciplines “drive” a particular service theme within the literature broadly defined. Finally, we provide the “Interactive Service Scholarship Incubator” app that enables scholars to explore the underlying concept network, predicted links, and themes, in light of their own interests and skill sets. Together, these SRPs offer a scalable roadmap for high-impact future service scholarship and practice.
- 17 June 2026
- Published by SAGE Publications in Journal of Service Research
- Vol. 29 (3) , 339-359
The 2026 Service Research Priorities: AI-Driven Discovery, Interdisciplinary Influence Dynamics, and the “Interactive Service Scholarship Incubator” for Personalized Priorities
This article presents the 2026 Service Research Priorities (SRPs), developed via a hybrid AI–human agenda-setting approach. We construct large-scale concept networks from more than 10,500 service-related articles in core service journals and Financial Times (FT) 50 outlets, and apply machine-learning link prediction to identify high-probability, but underexplored, concept pairs. Fifteen forward-looking themes emerge that fall into four topical clusters: (a) Human–AI Agency, Interactions, and Service Reconfiguration; (b) AI-Enabled Omnichannel Engagement and Ecosystem Orchestration; (c) Responsible, Inclusive, and Resilient AI Service Systems; and (d) Psychological Dynamics of Service Experiences. Comparing the themes’ relevance in the service outlets vis-à-vis the FT50 journals helps identify where service research currently leads, where it imports from adjacent disciplines, and where cross-fertilization is most promising. Furthermore, we reflect our themes against the 2021 SRPs, distinguishing “emerging,” “evolved,” and “continuing” priorities. Importantly, we also survey the Journal of Service Research leadership to further calibrate and enrich the AI-derived SRPs. Next, we introduce a new descriptive statistic, the “Interdisciplinary Influence Index,” to map which disciplines “drive” a particular service theme within the literature broadly defined. Finally, we provide the “Interactive Service Scholarship Incubator” app that enables scholars to explore the underlying concept network, predicted links, and themes, in light of their own interests and skill sets. Together, these SRPs offer a scalable roadmap for high-impact future service scholarship and practice.
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 6664-6667
PlaceSim: An LLM-based Interactive Platform for Human Behavior Simulation in Physical Facilities
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 6664-6667
Open AccessPlaceSim: An LLM-based Interactive Platform for Human Behavior Simulation in Physical Facilities
- 1 June 2023
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Management Science
- Vol. 69 (6) , 3616-3649
Learning Outside the Classroom During a Pandemic: Evidence from an Artificial Intelligence-Based Education App
Drawing on the notion of compensatory behavior, this paper studies how students compensate for learning loss during a pandemic and what role artificial intelligence (AI) plays in this regard. We further probe into a difference in compensatory behavior for learning loss in terms of quantity, pattern, and pace (i.e., tripartite aspect of learning behavior) of AI-powered learning app usage depending on the level of pandemic threat and the proximity of a goal to students. Results show that the pandemic threat affects student learning behavior differently. Immediately following the COVID-19 outbreak, students who live in the epicenter of the outbreak (versus those who do not) use the app less at first, but with time, they use it more (quantity), on a more regular basis (pattern), and rebound to a curriculum path (pace) comparable to students who do not live in the outbreak’s epicenter. These findings collectively explain behavior that is consistent with compensation for learning loss. The results also partially corroborate the goal-proximity effect, revealing that proximity to a goal (e.g., the degree to which the national university admission exam is approaching) has a moderating role in explaining the tripartite perspective of student learning behavior. Overall, these findings have important theoretical and practical implications for understanding how innovative education technologies can not only facilitate student learning during adversity, but also support learning recovery after adversity. This paper was accepted by D. J. Wu, information systems. Supplemental Material: Data files available at https://doi.org/10.1287/mnsc.2022.4531 .
- 1 June 2023
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Management Science
- Vol. 69 (6) , 3616-3649
Learning Outside the Classroom During a Pandemic: Evidence from an Artificial Intelligence-Based Education App
Drawing on the notion of compensatory behavior, this paper studies how students compensate for learning loss during a pandemic and what role artificial intelligence (AI) plays in this regard. We further probe into a difference in compensatory behavior for learning loss in terms of quantity, pattern, and pace (i.e., tripartite aspect of learning behavior) of AI-powered learning app usage depending on the level of pandemic threat and the proximity of a goal to students. Results show that the pandemic threat affects student learning behavior differently. Immediately following the COVID-19 outbreak, students who live in the epicenter of the outbreak (versus those who do not) use the app less at first, but with time, they use it more (quantity), on a more regular basis (pattern), and rebound to a curriculum path (pace) comparable to students who do not live in the outbreak’s epicenter. These findings collectively explain behavior that is consistent with compensation for learning loss. The results also partially corroborate the goal-proximity effect, revealing that proximity to a goal (e.g., the degree to which the national university admission exam is approaching) has a moderating role in explaining the tripartite perspective of student learning behavior. Overall, these findings have important theoretical and practical implications for understanding how innovative education technologies can not only facilitate student learning during adversity, but also support learning recovery after adversity. This paper was accepted by D. J. Wu, information systems. Supplemental Material: Data files available at https://doi.org/10.1287/mnsc.2022.4531 .
- 8 February 2022
- Published by Springer Nature in Marketing Letters
- Vol. 33 (4) , 545-561
Predicting Firm Market Performance Using the Social Media Promoter Score
- 8 February 2022
- Published by Springer Nature in Marketing Letters
- Vol. 33 (4) , 545-561
Predicting Firm Market Performance Using the Social Media Promoter Score
- Open Access
- 30 December 2020
- Published by People and Global Business Association in GLOBAL BUSINESS FINANCE REVIEW
- Vol. 25 (4) , 33-50
An Analysis of the Impact of Product Recall on Stock Prices based on Google Trend Search Counts
- 30 December 2020
- Published by People and Global Business Association in GLOBAL BUSINESS FINANCE REVIEW
- Vol. 25 (4) , 33-50
Open AccessAn Analysis of the Impact of Product Recall on Stock Prices based on Google Trend Search Counts
- Open Access
- 12 June 2017
- Published by Elsevier in SSRN Electronic Journal
Customer Attitude from Social Media, Customer Satisfaction Index, and Firm Value
Social media has emerged as a key source of understanding customer satisfaction, which is used by investors in their investment decision. Nonetheless, whether and how social media metrics on customer attitude toward the company has not been thoroughly examined. This study develops a new index of customer satisfaction by using sentiment and content analyses of customer-generated social media content. Across multiple social media platforms, we found that positive testimonials (i.e., “Likes” from Facebook) and positive blogs have statistically positive associations with customer satisfaction, while customer complaints (from Facebook), negative blogs, and negative tweets are negatively associated with it by using a semiparametric model. Furthermore, we found that the proposed customer satisfaction index based on social media metrics is positively and statistically associated with firm’s market performance. In addition, we suggest that the new social media metrics about customer attitude toward the company would strongly complement existing customer satisfaction index such as ACSI.
- 12 June 2017
- Published by Elsevier in SSRN Electronic Journal
Open AccessCustomer Attitude from Social Media, Customer Satisfaction Index, and Firm Value
Social media has emerged as a key source of understanding customer satisfaction, which is used by investors in their investment decision. Nonetheless, whether and how social media metrics on customer attitude toward the company has not been thoroughly examined. This study develops a new index of customer satisfaction by using sentiment and content analyses of customer-generated social media content. Across multiple social media platforms, we found that positive testimonials (i.e., “Likes” from Facebook) and positive blogs have statistically positive associations with customer satisfaction, while customer complaints (from Facebook), negative blogs, and negative tweets are negatively associated with it by using a semiparametric model. Furthermore, we found that the proposed customer satisfaction index based on social media metrics is positively and statistically associated with firm’s market performance. In addition, we suggest that the new social media metrics about customer attitude toward the company would strongly complement existing customer satisfaction index such as ACSI.
- Open Access
- 27 June 2016
- Published by Elsevier in SSRN Electronic Journal
Content Complexity, Similarity, and Consistency in Social Media: A Deep Learning Approach
In the present study, we investigate the effect of social media content on subsequent customer engagement (likes and reblogs) using a large-scale dataset from Tumblr. Our study focuses on company-generated posts, which consist of two main information sources: visual (images) and textual (text and tags). We employ state-of-the-art machine learning approaches including deep learning to extract data-driven features from both sources that effectively capture their semantics in a systematic and scaleable manner. With such semantic representations, we develop novel complexity, similarity, and consistency measures of social media content. Our empirical results show that proper visual stimuli (e.g., beautiful images, adult-content, celebrities, etc.), complementary textual content, and consistent themes have positive effects on the engagement, and that content demanding significant concentration levels (e.g., video, images with complex semantics, text with diverse topics, complex sentences, etc.) have the opposite effects. Further analyses at different perspectives (industry-level, hedonic/utilitarian products, followers/non-followers, short/long-term engagements) show the heterogeneous effects of visual and textual features. This work contributes to the literature by exemplifying how unstructured multimedia data (image, video, and audio) can be translated into insights. Our framework for semantic content analysis, particularly for visual content, illustrates how to leverage deep learning methods to better model and analyze multimedia data for effective marketing and social media strategies.
- 27 June 2016
- Published by Elsevier in SSRN Electronic Journal
Open AccessContent Complexity, Similarity, and Consistency in Social Media: A Deep Learning Approach
In the present study, we investigate the effect of social media content on subsequent customer engagement (likes and reblogs) using a large-scale dataset from Tumblr. Our study focuses on company-generated posts, which consist of two main information sources: visual (images) and textual (text and tags). We employ state-of-the-art machine learning approaches including deep learning to extract data-driven features from both sources that effectively capture their semantics in a systematic and scaleable manner. With such semantic representations, we develop novel complexity, similarity, and consistency measures of social media content. Our empirical results show that proper visual stimuli (e.g., beautiful images, adult-content, celebrities, etc.), complementary textual content, and consistent themes have positive effects on the engagement, and that content demanding significant concentration levels (e.g., video, images with complex semantics, text with diverse topics, complex sentences, etc.) have the opposite effects. Further analyses at different perspectives (industry-level, hedonic/utilitarian products, followers/non-followers, short/long-term engagements) show the heterogeneous effects of visual and textual features. This work contributes to the literature by exemplifying how unstructured multimedia data (image, video, and audio) can be translated into insights. Our framework for semantic content analysis, particularly for visual content, illustrates how to leverage deep learning methods to better model and analyze multimedia data for effective marketing and social media strategies.
- 1 April 2009
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 593-596
Nearest Mean Classification via One-Class SVM
We propose a new multi-class classification algorithm based on one-class SVM and nearest mean classifier methods. A wrapper-style feature selection scheme designed specifically for our algorithm is also provided for increased classification accuracy. It will be demonstrated that the proposed classification algorithm provide excellent performance, and in particular, performs strictly better than some of the currently known best classification algorithms on five biological datasets.
- 1 April 2009
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 593-596
Nearest Mean Classification via One-Class SVM
We propose a new multi-class classification algorithm based on one-class SVM and nearest mean classifier methods. A wrapper-style feature selection scheme designed specifically for our algorithm is also provided for increased classification accuracy. It will be demonstrated that the proposed classification algorithm provide excellent performance, and in particular, performs strictly better than some of the currently known best classification algorithms on five biological datasets.