• Journal of the Korean Society for information Management
• /
• v.33 no.2
• /
• pp.33-59
• /
• 2016

This study examined the factors affecting the performance of automatic classification for the domestic conference papers based on machine learning techniques. In particular, In view of the classification performance that assigning automatically the class labels to the papers in Proceedings of the Conference of Korean Society for Information Management using Rocchio algorithm, I investigated the characteristics of the key factors (classifier formation methods, training set size, weighting schemes, label assigning methods) through the diversified experiments. Consequently, It is more effective that apply proper parameters (${\beta}$, ${\lambda}$) and training set size (more than 5 years) according to the classification environments and properties of the document set. and If the performance is equivalent, I discovered that the use of the more simple methods (single weighting schemes) is very efficient. Also, because the classification of domestic papers is corresponding with multi-label classification which assigning more than one label to an article, it is necessary to develop the optimum classification model based on the characteristics of the key factors in consideration of this environment.

• Journal of the Korean Society for information Management
• /
• v.35 no.2
• /
• pp.63-88
• /
• 2018

This research evaluated differences of classification performance for feature selection methods using LDA topic model and Doc2Vec which is based on word embedding using deep learning, feature corpus sizes and classification algorithms. In addition to find the feature corpus with high performance of classification, an experiment was conducted using feature corpus was composed differently according to the location of the document and by adjusting the size of the feature corpus. Conclusionally, in the experiments using deep learning evaluate training frequency and specifically considered information for context inference. This study constructed biomedical document dataset, Disease-35083 which consisted biomedical scholarly documents provided by PMC and categorized by the disease category. Throughout the study this research verifies which type and size of feature corpus produces the highest performance and, also suggests some feature corpus which carry an extensibility to specific feature by displaying efficiency during the training time. Additionally, this research compares the differences between deep learning and existing method and suggests an appropriate method by classification environment.

• Journal of the Korean Society for information Management
• /
• v.39 no.1
• /
• pp.69-90
• /
• 2022

As basic data that can systematically support and evaluate R&D activities as well as set current and future research directions by grasping specific trends in domestic academic research, I sought efficient ways to assign standardized subject categories (control keywords) to individual journal papers. To this end, I conducted various experiments on major factors affecting the performance of automatic classification, focusing on feature selection techniques, for the purpose of automatically allocating the classification categories on the National Research Foundation of Korea's Academic Research Classification Scheme to domestic journal papers. As a result, the automatic classification of domestic journal papers, which are imbalanced datasets of the real environment, showed that a fairly good level of performance can be expected using more simple classifiers, feature selection techniques, and relatively small training sets.

• Journal of the Korean Society for information Management
• /
• v.23 no.1 s.59
• /
• pp.279-299
• /
• 2006

This study utilizes various approaches of machine learning in the process of automatically assigning descriptors to journal articles. The effectiveness of feature selection and the size of training set were examined, after selecting core journals in the field of information science and organizing test collection from the articles of the past 11 years. Regarding feature selection, after reducing the feature set using $x^2$ statistics(CHI) and criteria that prefer high-frequency features(COS, GSS, JAC), the trained Support Vector Machines(SVM) performed the best. With respect to the size of the training set, it significantly influenced the performance of Support Vector Machines(SVM) and Voted Perceptron(VTP). However, it had little effect on Naive Bayes(NB).

• Journal of the Korean Society for information Management
• /
• v.29 no.2
• /
• pp.225-246
• /
• 2012

This study purported to investigate the possibility of automatic descriptor assignment using the reclassification of author keywords in domestic scholarly databases. In the first stage, we selected optimal classifiers and parameters for the reclassification by comparing the characteristics of machine learning classifiers. In the next stage, learning the author keywords that were assigned to the selected articles on readings, the author keywords were automatically added to another set of relevant articles. We examined whether the author keyword reclassifications had the effect of vocabulary control just as descriptors collocate the documents on the same topic. The results showed the author keyword reclassification had the capability of the automatic descriptor assignment.

• Journal of the Korean Society for information Management
• /
• v.25 no.1
• /
• pp.211-233
• /
• 2008

This study examines various weighting methods for improving the performance of automatic classification based on Rocchio algorithm on two collections(LISA, Reuters-21578). First, three factors for weighting are identified as document factor, document factor, category factor for each weighting schemes, the performance of each was investigated. Second, the performance of combined weighting methods between the single schemes were examined. As a result, for the single schemes based on each factor, category-factor-based schemes showed the best performance, document set-factor-based schemes the second, and document-factor-based schemes the worst. For the combined weighting schemes, the schemes(idf*cat) which combine document set factor with category factor show better performance than the combined schemes(tf*cat or ltf*cat) which combine document factor with category factor as well as the common schemes (tfidf or ltfidf) that combining document factor with document set factor. However, according to the results of comparing the single weighting schemes with combined weighting schemes in the view of the collections, while category-factor-based schemes(cat only) perform best on LISA, the combined schemes(idf*cat) which combine document set factor with category factor showed best performance on the Reuters-21578. Therefore for the practical application of the weighting methods, it needs careful consideration of the categories in a collection for automatic classification.

• Proceedings of the Korean Society for Cognitive Science Conference
• /
• 2000.05a
• /
• pp.61-67
• /
• 2000

본고는 텍스트로 제시된 한국어 문장의 형태통사론적 오류와 의미적 논항결합시 하위범주화요건을 위배하는 논항선택 오류의 인식 및 판단에 따른 ERP(Event-Related Potential)를 검출하여, 이에 대한 문장이해과정의 시간추이적 양상을 연구의 대상으로 하였다. 참여한 피험자로부터 각각의 유형에 대한 통계분석 결과, 통사적 오류 추출에서 의미적 오류 추출에 이르기까지 기존의 연구에서 제시된 오류패턴 요소들(ELAN, N400, P600)을 확인하였으며, 아울러 한국어 문장이해과정의 특이성을 관찰할 수 있었다. 이를 통해 문장묵독시 일어나는 여러 종류의 문법오류에 대한 개별적 성격규명과 함께, 이들의 문법틀 내에서의 상호관계에 대한 일련의 가설설정이 이루어질 수 있으며, 또한 문장이해 메커니즘의 신경적 기전의 특성 규명으로 부수될 인간지능 모사가능성에 생리학적 토대가 더해 질 것으로 추정되는 바, 언어이해와 대뇌기전지형을 결정짓는 또 다른 규준이 될 것이다.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.22 no.2
• /
• pp.5-25
• /
• 2011

This study aims to identify the most effective statistical feature selecting method and context window size for word sense disambiguation using supervised methods. In this study, features were selected by four different methods: information gain, document frequency, chi-square, and relevancy. The result of weight comparison showed that identifying the most appropriate features could improve word sense disambiguation performance. Information gain was the highest. SVM classifier was not affected by feature selection and showed better performance in a larger feature set and context size. Naive Bayes classifier was the best performance on 10 percent of feature set size. kNN classifier on under 10 percent of feature set size. When feature selection methods are applied to word sense disambiguation, combinations of a small set of features and larger context window size, or a large set of features and small context windows size can make best performance improvements.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.3
• /
• pp.1-12
• /
• 2024

In this paper, we fine-tuned KoAlpaca, a large-scale Korean language model, and implemented a blog text generation system utilizing it. Blogs on social media platforms are widely used as a marketing tool for businesses. We constructed training data of positive reviews through emotion analysis and refinement of collected sponsored blog texts and applied QLoRA for the lightweight training of KoAlpaca. QLoRA is a fine-tuning approach that significantly reduces the memory usage required for training, with experiments in an environment with a parameter size of 12.8B showing up to a 58.8% decrease in memory usage compared to LoRA. To evaluate the generative performance of the fine-tuned model, texts generated from 100 inputs not included in the training data produced on average more than twice the number of words compared to the pre-trained model, with texts of positive sentiment also appearing more than twice as often. In a survey conducted for qualitative evaluation of generative performance, responses indicated that the fine-tuned model's generated outputs were more relevant to the given topics on average 77.5% of the time. This demonstrates that the positive review generation language model for sponsored content in this paper can enhance the efficiency of time management for content creation and ensure consistent marketing effects. However, to reduce the generation of content that deviates from the category of positive reviews due to elements of the pre-trained model, we plan to proceed with fine-tuning using the augmentation of training data.

• The Journal of the Korea Contents Association
• /
• v.13 no.7
• /
• pp.16-23
• /
• 2013

This paper analyzes the artistic practical use of social network visualization through the aesthetic information interpretation. The first social network visualization has emerged as 'Sociogram' in the form of social network analysis(SNA). Since social network has complex, the analyzing technology of social network has emerged. Early social network visualization has a practical purpose to measure the social structure, but current social network visualization divided into various forms from artistic expressions through information. This paper divide into two categories based on the artistic application of social network visualization. First, this research focuses on the static graph based on analog. Second, this research analyze the category of interacted visualization to generate a real-time digital image. This paper presents the fusion of paradigm between engineering and art through this way.