• Journal of the Korean Society for information Management
• /
• v.23 no.4 s.62
• /
• pp.277-294
• /
• 2006

This paper examines a level of categorization performance in a real-life collection of abstract articles in the fields of science and technology, and tests the optimal size of documents per category in a training set using a kNN classifier. The corpus is built by choosing categories that hold more than 2,556 documents first, and then 2,556 documents per category are randomly selected. It is further divided into eight subsets of different size of training documents : each set is randomly selected to build training documents ranging from 20 documents (Tr-20) to 2,000 documents (Tr-2000) per category. The categorization performances of the 8 subsets are compared. The average performance of the eight subsets is 30% in $F_1$ measure which is relatively poor compared to the findings of previous studies. The experimental results suggest that among the eight subsets the Tr-100 appears to be the most optimal size for training a km classifier In addition, the correctness of subject categories assigned to the training sets is probed by manually reclassifying the training sets in order to support the above conclusion by establishing a relation between and the correctness and categorization performance.

• Journal of the Korean Society for information Management
• /
• v.23 no.2
• /
• pp.265-285
• /
• 2006

In text categorization a certain level of correctness of labels assigned to training documents is assumed without solid knowledge on that of real-world collections. Our research attempts to explore the quality of pre-assigned subject categories in a real-world collection, and to identify the relationship between the quality of category assignment in training set and text categorization performance. Particularly, we are interested in to what extent the performance can be improved by enhancing the quality (i.e., correctness) of category assignment in training documents. A collection of 1,150 abstracts in computer science is re-classified by an expert group, and divided into 907 training documents and 227 test documents (15 duplicates are removed). The performances of before and after re-classification groups, called Initial set and Recat-1/Recat-2 sets respectively, are compared using a kNN classifier. The average correctness of subject categories in the Initial set is 16%, and the categorization performance with the Initial set shows 17% in $F_1$ value. On the other hand, the Recat-1 set scores $F_1$ value of 61%, which is 3.6 times higher than that of the Initial set.

• Journal of the Korean Society for Library and Information Science
• /
• v.47 no.1
• /
• pp.57-79
• /
• 2013

The aim of this study is to reveal the categorizational and classificatory features of the subject-based classification (SBC) as a subject organization system. For this purpose, 12 SBC schemes of public libraries were selected and a comparative analysis was made between the traditional classification system, such as DDC and SBC in terms of the categorizational aspects, and canons for the classification. As a result, there were significant and considerable differences between the two types of classifications. This study concluded that SBC cannot be clearly explained and understood without a consideration of its essential and distinctive characteristics as a classification scheme.

• KLA journal
• /
• v.49 no.5
• /
• pp.26-31
• /
• 2008

• Journal of the Korean Society for information Management
• /
• v.29 no.2
• /
• pp.155-171
• /
• 2012

In text categorization, core terms of an input document are hardly selected as classification features if they do not occur in a training document set. Besides, synonymous terms with the same concept are usually treated as different features. This study aims to improve text categorization performance by integrating synonyms into a single feature and by replacing input terms not in the training document set with the most similar term occurring in training documents using Wikipedia. For the selection of classification features, experiments were performed in various settings composed of three different conditions: the use of category information of non-training terms, the part of Wikipedia used for measuring term-term similarity, and the type of similarity measures. The categorization performance of a kNN classifier was improved by 0.35~1.85% in $F_1$ value in all the experimental settings when non-learning terms were replaced by the learning term with the highest similarity above the threshold value. Although the improvement ratio is not as high as expected, several semantic as well as structural devices of Wikipedia could be used for selecting more effective classification features.

• Journal of the Korean Society for Library and Information Science
• /
• v.43 no.1
• /
• pp.313-332
• /
• 2009

Cross-language text categorization(CLTC) can classify documents automatically using training set from other language. In this study, collections appropriated for CLTC were extracted from KTSET. Classification performance of various CLTC methods were compared by SVM classifier using machine translation. Results showed that the classification performance in the order of poly-lingual training method, training-set translation and test-set translation. However, training-set translation could be regarded as the most useful method among CLTC, because it was efficient for machine translation and easily adapted to general environment. On the other hand, low performance was shown to be due to the feature reduction or features with no subject characteristics, which occurred in the process of machine translation of CLTC.

• Proceedings of the Korean Society for Information Management Conference
• /
• 2000.08a
• /
• pp.41-44
• /
• 2000

정보검색 시스템의 성능을 향상시키기 위해서 다양한 용어가중치 공식이 제안 되어왔다. 용어가중치는 질의와 문헌을 비교하는 검색의 경우뿐만 아니라 문헌과 문헌을 비교하는 자동분류에서도 성능에 영향을 미칠 수가 있다. 본 논문에서는 다양한 용어가중치 공식에 대해서 살펴보고, 문헌 자동분류 성능에 미치는 영향을 문헌 클러스터링 실험과 범주화 실험을 통해 확인해 보았다.

• Journal of the Korean Society for Library and Information Science
• /
• v.50 no.2
• /
• pp.245-269
• /
• 2016

In this study, we develop a categorization of citizens' information problems in their everyday life based on the characteristics in their information seeking behavior for developing information services which support to solve the problems practically. First of all, we extracted keywords related to their faced everyday life problems from the scripts of open-ended interviews with citizens who had diverse characteristics. The keywords were categorized into 6 groups, such as hobby/recreation, legal problems, current affairs, education, health, and economic matters, based on the characteristics in related information seeking behaviors. Then the 6-group categorization was tested statistically with questionnaire survey data based on their prefered information sources. Through the statistical test, the 6-group categorization has proved being valid. Based on the results, we suggested to reconsider the current information services in public libraries, and discussed a possibility to shift the services to problem-based information services.

• Proceedings of the Korean Society for Information Management Conference
• /
• 2000.08a
• /
• pp.29-32
• /
• 2000

자동문서 범주화에 이용되는 학습분류기 중에서 SVM은 자질 차원을 축소하지 않고도 좋은 성능을 보이고 있다. 본 실험에서는 KTSET 텍스트 컬렉션을 대상으로 두 개의 SVM 분류기를 이용하여 자질축소 및 자질표현에 따른 성능비교 실험을 하였다. 자질축소를 위하여 $\chi$$^2$통계량을 자질선정기준으로 사용하였으며, 자질값으로는 단어빈도 및 문헌빈도의 두 요소로 구성되는 다양한 가중치를 사용하였다. 실험결과 SVM은 자질축소에 큰 영향을 받지 않고 가중치 유형에 따라 성능의 차이를 보였다.

• Journal of the Korean Society for information Management
• /
• v.17 no.4
• /
• pp.229-248
• /
• 2000

Among several learning algorithms for lexl calegoriration. SVM(Snpport Vsctor Machines) has been provcd to ouq~e~fotm other classifiers. Th~study e~~aluales the categarizalion ability of en SVM classifier using the ModApte split of the Reutcrs-21578 dataset. First. an experiment 1s perlormed to test a few feature wetghtlng schemes that will be used in thc calegarization tasks. Second, (he categorization periarrnances of the lulear SVM and the non-linear SVM are compared. Finally. the binary SVM classifier is expanded into a multi-class classifier and thek pcrforrnnnces are comparativcly evaluated.