Jin-Young Bak
Sungkyunkwan University · Engineering
About the Lab
Professor Jin-Young Bak's research lab specializes in computational social science and natural language processing, focusing on understanding human behavior through large-scale textual data. The lab investigates self-disclosure, emotional expression, and interpersonal relationships in online conversations using machine learning and text mining techniques. It also explores applications in occupational safety through computer vision and deep learning, particularly in monitoring worker behavior on construction sites. Additionally, the lab engages in historical and literary studies, analyzing translation practices and cultural impacts in early 20th-century Korea.
Research Overview
Research Output Trend
Figures are computed from collected data and may differ slightly.
Selected Papers
15Self-disclosure, the act of revealing one-self to others, is an important social be-havior that strengthens interpersonal rela-tionships and increases social support. Al-though there are many social science stud-ies of self-disclosure, they are based on manual coding of small datasets and ques-tionnaires. We conduct a computational analysis of self-disclosure with a large dataset of naturally-occurring conversa-tions, a semi-supervised machine learning algorithm, and a computational analysis of
In social psychology, it is generally accepted that one discloses more of his/her personal information to someone in a strong relationship. We present a computational framework for automatically analyzing such self-disclosure behavior in Twitter conversations. Our framework uses text mining techniques to discover topics, emotions, sentiments, lexical patterns, as well as personally identifiable information (PII) and personally embarrassing information (PEI). Our preliminary results illustrate th
INTRODUCTION: Fatal fall from height accidents, especially on construction sites, persist, underscoring the importance of monitoring and managing worker behaviors to enhance safety. Deep learning showed the possibility of substituting the manual work of safety managers. However, applying detection results to determine compliance with safety regulations has limitations. METHOD: This study estimated the actual working height depending on the height of the object detection bounding box by specifyin
JinYeong Bak, Alice Oh. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.
홍난파는 1920년대 초반 최대의 전문 번역가다. 문학청년의 출현과번역 출판의 전성기를 예고한 홍난파는 1919~1924년에 세계 문학의번역에 열중했다. 홍난파의 번역 가운데 가장 문제적인 것은 홍난파의첫 번째 번역이자 식민지 시기에 유일하게 번역된 도스토옙스키의『가난한 사람들』이다. 홍난파는 청춘의 열애와 비련에 초점을 맞추어세계 문학을 번역한 동시에 창작의 밑거름으로 삼았다. 이 연구는 번역가로서 홍난파에 대한 조명을 통해 1920년대 초반의 번역을 둘러싼문학사적 조건과 효과를 재평가했으며, 번역 출판의 급격한 성장과 쇠락의 배경에 대한 탐구를 새로운 과제로 제시했다.
본 연구에서 는 sub-optimal 수준의 비타민과 무기질을 섭취하며, 고콜레스테롤 식이에 알코올 섭취를 병행하여 영양 불균형이 유도된 흰쥐를 대상으로 현미와 율무로 구성된 생식 또는 열처리생식을 식이에 첨가하여 5주간 사육시킨 후 체내 지질농도, 항산화체계 및 면역기능에 미치는 영향을 평가하여 다음과 같은 결과...
In a multidimensional two-phase flow analysis, bubble size significantly affects interfacial transfer terms such as mass, momentum, and energy. With regard to bubbly flow, the application of a simple correlation-type bubble size model presents certain advantages, including short calculation times and ease of usage. In this study, we propose a semi-theoretical correlation developed from a steady state bubble number density transport equation for predicting the distribution of local bubble size us
Automatic evaluation of open-domain dialogue response generation is very challenging because there are many appropriate responses for a given context. Existing evaluation models merely compare the generated response with the ground truth response and rate many of the appropriate responses as inappropriate if they deviate from the ground truth. One approach to resolve this problem is to consider the similarity of the generated response with the conversational context. In this paper, we propose an
우리나라가 주최하는 국제 디자인상인 K-디자인상의 신제품 디자인 콘셉트 수상작들에 내재된 창의성코드를 분석하고, 각 창의성코드가 어떤 고객 가치를 창출하는지 고찰하였다. 연구의 대상이 된 119개의 수상작 중 75개에 BCC 코드가 내재되어 있었으며, 이들로부터 관찰된 주요 내용은 다음과 같다. 첫째, 신제품 디자인 콘셉트에서 결합 코드와 속성의존 코드의 적용 빈도가 상대적으로 매우 높다. 이것은 결합이나 융합이 창의성의 중요한 원천이며, 속성의존을 통해 제품 고유의 기능성을 확장 또는 개선함으로써 고객의 가치를 창출할 기회가 많다는 것을 시사한다. 둘째, 고객과 그들의 요구사항을 새롭게 정의하는 것은 고객중심 혁신이란 관점에서 매우 중요하나 본 연구에서 검토한 신제품 디자인 콘셉트에서는 재정의 코드가 관찰되지 않았다. 재정의 코드의 적용을 통해 시장에서 크게 성공한 사례들이 많이 알려져 있다. 이것은 새로운 디자인 콘셉트가 도입되지 않더라도 고객이나 고객의 핵심적 요구사항을 새롭게
Styles of leaders when they make decisions in groups vary, and the different styles affect the performance of the group. To understand the key words and speakers associated with decisions, we initially formalize the problem as one of predicting leaders' decisions from discussion with group members. As a dataset, we introduce conversational meeting records from a historical corpus, and develop a hierarchical RNN structure with attention and pre-trained speaker embedding in the form of a, Conversa
We present a quantitative study of the An-nals of the Joseon Dynasty, the daily writ-ten records of the five hundred years of a monarchy in Korea. We first introduce the corpus, which is a series of books describ-ing the historical facts during the Joseon dynasty. We then define three categories of the monarchial ruling styles based on the written records and compare the twenty-five kings in the monarchy. Finally, we in-vestigate how kings show different ruling styles for various topics within t
Research Areas
Dive deeper into Jin-Young Bak's research on Nubint
Open this lab's papers in the app to read with AI, summarize, and cite in your writing.