• Korean Journal of Cognitive Science
• /
• v.20 no.2
• /
• pp.225-241
• /
• 2009

This paper presents an authorship attribution study in Korean conducted on a corpus of newspaper column texts. Based on the data set consisting of a total of 160 columns written by four columnists of Chosun Daily, the approach utilizes relative frequencies of various lexical units in Korean such as fully inflected words, morphemes, syllables and their bigrams in an attempt to establish authorship of a blind text selected from the set. Among these various lexical units, "the morpheme" is found to be most effective in predicting who among the four potential candidates authored a text, reporting accuracies of over 93%. The results indicate that quantitative and statistical techniques in authorship attribution and computational stylistics can be successfully applied to Korean texts.

• Journal of Information Management
• /
• v.40 no.2
• /
• pp.95-115
• /
• 2009

Author resolution is to disambiguate same-name author occurrences into real individuals. For this, pair-wise author similarities are computed for author name entities, and then clustering is performed. So far, many studies have employed hierarchical clustering techniques for author disambiguation. However, various hierarchical clustering methods have not been sufficiently investigated. This study covers an empirical evaluation and analysis of hierarchical clustering applied to Korean author resolution, using multiple distance functions such as Dice coefficient, Cosine similarity, Euclidean distance, Jaccard coefficient, Pearson correlation coefficient.

• Annual Conference on Human and Language Technology
• /
• 2006.10e
• /
• pp.89-97
• /
• 2006

과학기술 문헌에 대한, 정확한 인용 정의의 제공을 위해서는 인용 관계를 구성하는 인력에 대한 동명이인 문제가 우선적으로 해소되어야 한다. 본 논문에서는 정확한 저자 중심의 인용 관계 및 네트워크를 구축하기 위해 URI(Universal Resource Identifier)를 이용하는 방법을 제안한다. 본 연구의 특징은, 지속적으로 추가되고 갱신되는 인용 정보를 일관성 있게 유지하고 정확한 문헌으로의 접근성을 보장하기 위해, 시맨틱웹 기술의 하나인 URI를 문헌과 저자에 적용하여 저자 중심 인용 관계 및 네트워크를 구축한다는 것이다. 실험에서는, 국내 학술대회 발표 논문들로부터 2,872개의 저자 중심 인용 관계 쌍을 추출하였고, 이를 바탕으로 구축한 저자 인용 네트워크에서는 135개의 인용 네트워크 그룹을 발견할 수 있었다. 본 연구의 결과는 향후 국가과학기술인력 종합정보시스템에서 제공하는 인력 DB 및 과학기술정보 포털서비스인 YesKiSTi와의 연계를 통하여 새로운 개념의 다양한 연구자 네트워크 서비스를 제공할 수 있을 것으로 기대된다.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.26 no.5
• /
• pp.1191-1199
• /
• 2016

To ensure the fairness, journal reviewers use blind-review system which hides the author information of the journal. Even though the author information is blinded, we could identify the author by looking at the field of the journal or containing words and phrases in the text. In this paper, we collected 315 journals of 20 authors and extracted text data. Bag-of-words were generated after preprocessing and used as an input of artificial neural network. The experiment shows the possibility of circumventing the blind review through identifying the author of the journal. By the experiment, we demonstrate the limitation of the current blind-review system and emphasize the necessity of robust blind-review system.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.128-131
• /
• 2021

본 논문에서는 특정 코드를 분석하여 해당 코드를 작성한 저자가 누구인지 식별할 수 있는 머신 러닝 기반 코드 저자 식별 기술에 대해 소개한다. 먼저 소스 코드를 분석하여 저자를 확인하는 기법들에 알아볼 것이다. 또한 저자를 식별할 수 있는 정보가 다소 소실된 바이너리 코드를 분석하여 저자를 확인하는 기법을 살펴본 다음, 저자 식별 기법의 향후 연구 방향에 대해 탐색하고자 한다.

• Journal of Korean Library and Information Science Society
• /
• v.50 no.4
• /
• pp.305-337
• /
• 2019

The aim of this thesis is to explore some aspects and characteristics of 109 volumes of collections of works at Uiryeong area in Gyeongsangnam-do Province. The author analyzed type of printing, type of collections of works, their birth year and the family name of the author, the place and the year, and the publisher of the publication of these different 109 kinds of the collections of works. The results are as follows: The collections of works demonstrate their forefathers' academic competencies. The types of printings were divided into 4 types, wood block printing, wooden movable-type printing, new lead-type printing, lithography printing. Of the collections of works 48% were wooden movable-type printing. The types of collections of works were divided into 3 types, Munjip(文集), Yujip(遺集), and Silgi(實記). Of the collections of works 49% were Munjip. The authors were local intellectuals. Of these authors 67% of authors were born in the 19th century. Twenty nine lineage groups published collections of works at Uiryeong area. 90% of the publications were published in the 20th century. In terms of place, 81% of the collections of works were published in the worshipping halls for their ancestors. 63% of the collections of works were published within 50 years after the author had died.

• Journal of Internet Computing and Services
• /
• v.21 no.2
• /
• pp.1-8
• /
• 2020

Recently, the number of APT(Advanced Persistent Threats) attack using malware has been increasing, and research is underway to prevent and detect them. While it is important to detect and block attacks before they occur, it is also important to make an effective response through an accurate analysis for attack case and attack type, these respond which can be determined by analyzing the attack group of such attacks. Therefore, this paper propose a framework based on genetic algorithm for analyzing malware and understanding attacker group's features. The framework uses decompiler and disassembler to extract related code in collected malware, and analyzes information related to author through code analysis. Malware has unique characteristics that only it has, which can be said to be features that can identify the author or attacker groups of that malware. So, we select specific features only having attack group among the various features extracted from binary and source code through the authorship clustering method, and apply genetic algorithm to accurate clustering to infer specific features. Also, we find features which based on characteristics each group of malware authors has that can express each group, and create profiles to verify that the group of authors is correctly clustered. In this paper, we do experiment about author classification using genetic algorithm and finding specific features to express author characteristic. In experiment result, we identified an author classification accuracy of 86% and selected features to be used for authorship analysis among the information extracted through genetic algorithm.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.05a
• /
• pp.711-713
• /
• 2013

Various human resource information of the world can be found according to spread of social network such as facebook and twitter. There are an amounts of researcher information on the science and technology area but it is difficult to find a suitable researcher for research or business such as research partner, because researcher information is not systematically arranged. To solver this problem, we are constructing authority data system for science and technology based on authority information of overseas academic papers. In this paper, in order to construct the authority data, we extracts author identification elements from millions of overseas academic papers, which are published from 1994 to 2012. There are more than 50 author identification elements such as author name, affiliation, paper title, publisher, year, keywords, co-author, co-author's affiliation in Korean, English, Chinese, and Japanese. We construct the element database by extracting and storing an author identification information based on the elements from overseas academic papers. Future works includes that the authority database for overseas academic papers is constructed by storing an academic activities of researchers after author clustering with these extracted elements. The authority data is used to improve the researcher information utilization and activate community to find a suitable research partner or a business examiner.

• Journal of the Korean Society for Library and Information Science
• /
• v.51 no.2
• /
• pp.117-132
• /
• 2017

This paper aims to explore the impacts of various authorship-related factors on future citations of conference articles in 'Information Science' discipline. A large body of bibliometric studies has suggested that the impacts of various authorship-related factors on the future citations vary by the discipline and there is no well-grounded factor that is unanimously significant across all academic fields. That is, it is necessary to separately assess the impact of authorship-related factors on 'Information Science' articles. Moreover, while a number of bibliometric studies have focused on journal articles, the exploration of conference articles has been significantly fewer. Therefore, this study, which is based on 1,957 conference articles in 'Information Science' field, examined several factors about authors and the contributions of the factors to the future citation. The sources of citation rates of conference articles were Google Scholar and Scopus. As the results, among eight factors considered in this paper, the first authors' publishing tenure and job title and the average number of publications of other authors significantly contributed to the changes of citations. However, the number of authors, the number of affiliated institues, the number of the first authors' publications and the average publishing tenure of the other authors made little contributions on citations.

• Journal of KIISE:Software and Applications
• /
• v.34 no.2
• /
• pp.150-159
• /
• 2007

For the construction of accurate scientific citation information, author disambiguation should be primarily resolved. This study proposes a method that utilizes URI(Uniform Resource Identifier) to create precise author citation networks. The adoption of URIs for representing authors and papers in this study enables us to maintain the integrity of constantly changing citation information and to guarantee the accessibility to the right literature. In experiments, we extracted 2,872 author-centric citation relation pairs from recent major IT-related proceedings written in Korean. From those, 135 citation network groups were discovered. The findings of this study are expected to be applied to a variety of researcher network services and scientific information portal services.