Seongsoon Kim

Seongsoon Kim, Ph.D
 
Address: 
Room 501B, Woojeong Information and Communications Building,
Korea University, Anam-dong 5-ga, Seongbuk-gu,
Seoul 136-713, South Korea
 
Email: 
seongkim@korea[dot]ac[dot]kr
 
Phone: 
office) +82-2-3290-3566

■ Education

  • Korea University, Seoul, South Korea                                        3/13 - 8/17
    • Ph.D. in Computer Science 
    • Thesis title : "Designing and Evaluating Machine Reading Methods for Multi-domain Texts"
    • Advisor: Prof. Jaewoo Kang
  • Korea University, Seoul, South Korea                                        3/11 - 2/13 
    • M.S. in Computer Science
    • Thesis title : "Aspect-based Sentiment Analysis using Syntactic Features from User Generated Text"
    • Advisor: Prof. Jaewoo Kang

  • Chungnam National University, Daejeon, South Korea               3/05 - 2/11
    • B.E. in Computer Engineering (Dual Degree)
  • Stony Brook University, New York, United States                       8/07 - 12/09 
    • B.S. in Computer Science



■ Research Topics & Experiences

My research has been widely focused on discovering knowledge from big data and developing intelligent machine using Artificial Intelligence (AI) and Machine Learning (ML) approach.

- Social Bigdata-based Entity Search System on the Distributed Computing Platform
• Hadoop/Solr-based social Big Data index and search system
• Big Data (Web and social data) collection and processing system on top of the distributed cluster
• Search result visualization

- Machine Learning-based Text Analysis and Mining
• Identifying protein-protein interaction (PPI) in the biomedical texts
• Sentiment analysis and opinion mining
• Deceptive opinion spam analysis using machine learning models

- Artificial Intelligence
• Deep neural architecture
• Machine understanding system on multi-domain text (including user-generated contents on the Web, fictional story, and biomedical literature)


[Google Scholar][DBLP]

■ Publications

- International Journal

    • Seongsoon Kim*, Donghyeon Park*, Yonghwa Choi*, Kyubum Lee, Byounggun Kim, Minji Jeon, Jihhye Kim, Aik-Choon Tan and Jaewoo Kang "Can Machines Read Medical Research Articles? A Pilot Study of Biomedical Text Comprehension using an Attention-based Deep Neural Reader", JMIR 2017, (Under review)
    • Sunwon Lee, Donghyeon Kim, Kyubum Lee, Jaehoon Choi, Seongsoon Kim, Minji Jeon, Sangrak Lim, Donghee Choi, Sunkyu Kim, Aik-Choon Tan, Jaewoo Kang "BEST: Next-Generation Biomedical Entity Search Tool for Knowledge Discovery from Biomedical Literature", Plos One 2016, In-Press (SCIE, IF: 3.057)
    • Junkyu Lee, Seongsoon Kim, Sunwon Lee, Kyubum Lee, Jaewoo Kang "On the efficacy of per-relation basis performance evaluation for PPI extraction and a high-precision rule-based approach" BMC Medical Informatics and Decision Making 2013, Vol. 13, No. 1. Apr 5 2013 ( SCIE, IF: 1.48 )
    • Jaehoon Choi, Donghyeon Kim, Seongsoon Kim, Sunwon Lee, Kyubum Lee and Jaewoo Kang "BOSS: context-enhanced search for biomedical objects" BMC Medical Informatics and Decision Making, Vol. 12, No. 1. Apr 30 2012 ( SCIE, IF: 2.23 )

- International Conference

    • Sunwon Lee, Donghyun Kim, Sunkyu Kim, Kyubum Lee, Jaehoon Choi, Seongsoon Kim, Minji Jeon, Sangrak Lim, Donghee Choi, Aik Choon Tan and Jaewoo Kang  "Next-Generation Biomedical Entity Search Tool for Knowledge Discovery from Biomedical Literature" The 25th Conference on Intelligent Systems for Molecular Biology and the 16th European Conference on Computational Biology (ISMB/ECCB 2017), Prague, Czech Republic, July 21-25 2017 (Poster) 
    • Kyubum Lee, Byounggun Kim, Sunkyu Kim, Yonghwa Choi, Wonho Shin, Sunwon Lee, Sungjoon Park, Seongsoon Kim, Aik Choon Tan and Jaewoo Kang  "Deep Learning of Mutation-Gene-Drug Relations from the Literature for Precision Medicine" The 25th Conference on Intelligent Systems for Molecular Biology and the 16th European Conference on Computational Biology (ISMB/ECCB 2017), Prague, Czech Republic, July 21-25 2017 (Poster) 
    • Seongsoon Kim*, Seongwoon Lee*, Donghyeon Park and Jaewoo Kang  "Constructing and Evaluating a Novel Crowdsourcing-based Paraphrased Opinion Spam Dataset" The 26th International World Wide Web Conference (WWW 2017), Perth, Australia, April 3-7 2017 (* These authors contributed equally to this work.) (Full paper, acceptance ratio: 17%
    • Jukyong Lee, Yonghwa Choi, Suhkyung Kim, Seongsoon Kim, Jaewoo Kang "SEMO: Searching Majority Opinions on Movies using SNS and QA Threads" The 25th International World Wide Web Conference (WWW 2016), Montreal, Canada, April 11-15 2016 (Demo)
    • Donghyeon Kim, Sunwon Lee, Kyubum Lee, Jaehoon Choi, Seongsoon Kim, Minji Jeon, Sangrak Lim, Donghee Choi, Aik-Choon Tan, Jaewoo Kang "BEST: Next-Generation Biomedical Entity Search Tool for Knowledge Discovery from Biomedical Literature" The 5th Annual Translational Bioinformatics Conference (TBC 2015), Tokyo, Japan, Nov 7-9 2015
    • Seongsoon Kim, Hyeokyoon Chang, Seongwoon Lee, Minhwan Yu, Jaewoo Kang "Deep Semantic Frame-based Deceptive Opinion Spam Analysis" In Proceedings of ACM International Conference on Information and Knowledge Management (CIKM 2015), Melbourne, Australia. Oct 19-23 2015 (Full paper)
    • Jaehoon Choi, Donghyeon Kim, Donghee Choi, Sangrak Lim, Seongsoon Kim, Youngjae Choi and Jaewoo Kang "Smith Search: Opinion-Based Restaurant Search Engine" 24th International World Wide Web Conference (WWW 2015), Florence, Italy. 18-22 May 2015 (Demo)
    • Junkyu Lee, Seongsoon Kim, Sunwon Lee, Kyubum Lee, Jaewoo Kang "High Precision Rule Based PPI Extraction and Per-Pair Basis Performance" ACM Sixth International Workshop on Data and Text Mining in Biomedical Informatics (DTMBIO 2012), Maui, Hawaii USA. Oct 29 2012
    • Jaehoon Choi, Donghyeon Kim, Seongsoon Kim, Junkyu Lee, Sunwon Lee and Jaewoo Kang "Consento: A New Framework for Opinion Based Entity Search and Summarization" Proceedings of the 21st ACM International Conference on Information and Knowledge Management (CIKM 2012), Hawaii, US. Oct 29-Nov 2 2012 (Short paper)
    • Jaehoon Choi, Donghyeon Kim, Seongsoon Kim, Junkyu Lee, Sangrak Im, Sunwon Lee and Jaewoo Kang "Consento: A Consensus Search Engine for Answering Subjective Queries" Proceedings of the 21st International Conference on World Wide Web (WWW '12), Lyon, France. Apr 16-20 2012 (Poster)
    • Jaehoon Choi, Donghyeon Kim, Seongsoon Kim, Sunwon Lee, Kyubum Lee and Jaewoo Kang "BOSS: A Biomedical Object Search System" ACM Fifth International Workshop on Data and Text Mining in Biomedical Informatics (DTMBIO 2011), Glasgow, UK. Oct 24 2011


- Domestic Journal
    • 이성운, 김성순, 박동현, 강재우 "크라우드소싱 기반 문장재구성 방법을 통한 의견 스팸 데이터셋 생성 및 특성 분석" KIISE Transactions on Computing Practices, Vol.22, No.7, pp.338-343, Jul 2016
    • 최재훈, 최동희, 김동현, 김성순, 임상락, 강재우 "소셜 빅데이터를 활용한 의사 결정 검색 기술" 정보과학회지, Vol. 32, Issue 296, Pages 44-52. Jan 2014
    • 이철성, 최동희, 김성순, 강재우 "한글 마이크로블로그 텍스트의 감정 분류 및 분석" 정보과학회논문지: 데이타베이스, Vol. 40, No. 3, Pages 159-167. Jun 2013


- Domestic Conference
    • 박동현, 김성순, 최용화, 강재우 "기계 이해의 학습을 위한 새로운 데이터셋의 제안" 한국멀티미디어학회 2016 추계학술대회 (구두발표), Oct 21-22 2016
    • 이성운, 김성순, 박동현, 강재우 "크라우드소싱 기반 문장재구성 방법을 통한 의견 스팸 데이터셋 생성 및 특성 분석" 한국정보과학회 2015년 동계학술대회 (구두발표, 우수논문), Dec 17-19 2015
    • 김성순, 장혁윤, 이성운, 강재우 "의미 프레임 자질 기반 의견 스팸 분석" 한국정보처리학회 2015년 춘계학술대회 (구두발표), April 25 2015
    • 임상락, 김성순, 장혁윤, 강재우 "문맥의 활용을 통한 개체 중의성 해결 조사" 2015 한국데이터베이스학술대회 논문집 Vol.1 No.1 (구두발표), May 15-16 2015


- Patent
    • 장부루, 김성순, 강재우 "SNS의 사용자, 텍스트 및 이미지 정보를 이용한 딥러닝 기반 관심지점 예측 모델", 출원 중

    • Seongsoon KIM, Hyeokyoon CHANG, Sung-Woon LEE, Jaewoo KANG "METHOD, DEVICE, COMPUTER PROGRAM AND COMPUTER READABLE RECORDING MEDIUM FOR DETERMINING OPINION SPAM BASED ON FRAME"출원국:미국, 출원번호: 15/135,209, 출원일자: 2016-04-21
    • 김성순, 장혁윤, 이성운, 강재우 "프레임 기반 의견스팸 판단장치프레임 기반 의견스팸 판단방법프레임 기반으로 의견스팸을 판단하기 위한 컴퓨터 프로그램 및 컴퓨터 판독가능 기록매체", 등록국가:대한민국, 등록번호: 10-1656741, 등록일자: 2016-09-06



■ Activity

- Subreviewer

    • VLDB 2016
    • BigComp 2015
    • ICDE 2015
    • WWW 2014
    • ICWSM 2014
    • WWW 2013
    • LBM 2013
    • BIBM 2013