초록

본 논문에서는 문헌의 적합성수준을 적합성정도에 따라 4그룹(부적합한, 조금 적합한, 적합한, 매우 적합한)으로 나눈 후 서로 다른 심사자가 적합성 판정을 내린 4개의 적합성 판정세트(A, B, C, D)에서 “조금 적합한” 문헌을 부적합문헌으로 분류했을 때와 적합문헌으로 분류하였을 때에, 초록/표제 시스템과 전문검색시스템에서 적합성피드백으로 인한 검색효율성의 증진은 어느 쪽이 더 혜택을 받게 되는 지를 연구하였다. “조금 적합한” 문헌을 적합문헌으로 포함시켰을 때 초록/표제시스템이 전문검색시스템보다 모든 적합성판정세트에서 검색효율성의 증가율이 높았고, 반면에 전문검색시스템에서는 “조금 적합한” 문헌을 적합문헌그룹에서 제외시켰을 때 검색효율성의 증가율이 일관성 있게 높아지는 것을 발견하였다. 이는 전문검색시스템에서는 적합문헌으로 포함된 “조금 적합한” 문헌으로부터 얻어지는 적합성피드백 정보는 잡음의 역할을 하게 되어 검색효율성의 증진에 도움이 안 되고 있음을 암시하고 있다. 특히, 매우 동질적인 문헌을 색인 및 검색대상으로 하고 있는 전문검색시스템에서는 잡음에 의해 초래되는 낮은 정확률을 개선하는 정교한 검색기법에 대한 연구가 지속되어야만 한다.

Abstract

This study examined the relative retrieval effectiveness after relevance feedback between two systems (Title/Abstract and Full-text) using four different sets of relevance judgment. Four relevance levels (not relevant, marginally relevant, relevant, highly relevant) are also used, each of which is determined by referees giving a relevance score to documents. This study also investigated how much the average precision was improved after relevance feedback when “marginally relevant” documents are included in the relevant class with the Title/Abstract system, and with the Full-text retrieval system as well. It is found that the Title/Abstract system benefited from relevance feedback with the marginally relevant documents. In case of the Title/Abstract system, the higher percentage of improvement was consistently obtained when including the marginally relevant documents in the relevance class, however the result was vice versa in case of the Full-text retrieval system. It implied that the marginally relevant documents in the relevant class had caused noises in the Full-text retrieval system.

초록

Abstract

The goal of this paper is to explore the field of Computer and Information Science with the aid of text mining techniques by mining Computer and Information Science related conference data available in DBLP (Digital Bibliography & Library Project). Although studies based on bibliometric analysis are most prevalent in investigating dynamics of a research field, we attempt to understand dynamics of the field by utilizing Latent Dirichlet Allocation (LDA)-based multinomial topic modeling. For this study, we collect 236,170 documents from 353 conferences related to Computer and Information Science in DBLP. We aim to include conferences in the field of Computer and Information Science as broad as possible. We analyze topic modeling results along with datasets collected over the period of 2000 to 2011 including top authors per topic and top conferences per topic. We identify the following four different patterns in topic trends in the field of computer and information science during this period: growing (network related topics), shrinking (AI and data mining related topics), continuing (web, text mining information retrieval and database related topics), and fluctuating pattern (HCI, information system and multimedia system related topics).