• Journal of Information Processing Systems
• /
• v.13 no.4
• /
• pp.863-875
• /
• 2017

The traditional text similarity measurement methods based on word frequency vector ignore the semantic relationships between words, which has become the obstacle to text similarity calculation, together with the high-dimensionality and sparsity of document vector. To address the problems, the improved singular value decomposition is used to reduce dimensionality and remove noises of the text representation model. The optimal number of singular values is analyzed and the semantic relevance between words can be calculated in constructed semantic space. An inverted index construction algorithm and the similarity definitions between vectors are proposed to calculate the similarity between two documents on the semantic level. The experimental results on benchmark corpus demonstrate that the proposed method promotes the evaluation metrics of F-measure.

• International conference on construction engineering and project management
• /
• 2015.10a
• /
• pp.37-38
• /
• 2015

A number of documents containing important and useful knowledge have been generated over time in the construction industry. Such text-based knowledge plays an important role in the construction industry for decision-making and business strategy development by being used as best practice for upcoming projects, delivering lessons learned for better risk management and project control. Thus, practical and usable knowledge creation from construction documents is necessary to improve business efficiency. This study proposes a knowledge creating system from construction documents using text mining and the design comprises three main steps - text mining preprocessing, weight calculation of each term, and visualization. A system prototype was developed as a pilot study of the system design. This study is significant because it validates a knowledge creating system design based on text mining and visualization functionality through the developed system prototype. Automated visualization was found to significantly reduce unnecessary time consumption and energy for processing existing data and reading a range of documents to get to their core, and helped the system to provide an insight into the construction industry.

• Journal of Broadcast Engineering
• /
• v.28 no.2
• /
• pp.178-184
• /
• 2023

Finding texts in general scene images and recognizing their contents is a very important task that can be used as a basis for robot vision, visual assistance, and so on. However, for the low-resolution text images, the degradations, such as noise or blur included in text images, are more noticeable, which leads to severe performance degradation of text recognition accuracy. In this paper, we propose a new Korean text image super-resolution based on a Transformer-based model, which generally shows higher performance than convolutional neural networks. In the experiments, we show that text recognition accuracy for Korean text images can be improved when our proposed text image super-resolution method is used. We also propose a new Korean text image dataset for training our model, which contains massive HR-LR Korean text image pairs.

• Journal of Digital Contents Society
• /
• v.18 no.4
• /
• pp.777-785
• /
• 2017

In the modern real world, we can extract and recognize some texts to get a lot of information from the scene containing them, so the techniques for extracting and recognizing text areas from a scene are constantly evolving. They can be largely divided into texture-based method, connected component method, and mixture of both. Texture-based method finds and extracts text based on the fact that text and others have different values such as image color and brightness. Connected component method is determined by using the geometrical properties after making similar pixels adjacent to each pixel to the connection element. In this paper, we propose a method to adaptively change to improve the accuracy of text region extraction, detect and correct the slope of the image using edge and image segmentation. The method only extracts the exact area containing the text by correcting the slope of the image, so that the extracting rate is 15% more accurate than MSER and 10% more accurate than EEMSER.

• The KIPS Transactions:PartB
• /
• v.13B no.4 s.107
• /
• pp.409-416
• /
• 2006

In this paper, we propose an algorithm for extracting text regions from spam-mail images using color layer. The CLTE(color layer-based text extraction) divides the input image into eight planes as color layers. It extracts connected components on the eight images, and then classifies them into text regions and non-text regions based on the component sizes. We also propose an algorithm for recovering damaged text strokes from the extracted text image. In the binary image, there are two types of damaged strokes: (1) middle strokes such as 'ㅣ' or 'ㅡ' are deleted, and (2) the first and/or last strokes such as 'ㅇ' or 'ㅁ' are filled with black pixels. An experiment with 200 spam-mail images shows that the proposed approach is more accurate than conventional methods by over 10%.

• Database Research
• /
• v.34 no.3
• /
• pp.3-13
• /
• 2018

Text classification is one of the text mining technologies that classifies a given textual document into its appropriate categories and is used in various fields such as spam email detection, news classification, question answering, emotional analysis, and chat bot. In general, the text classification system utilizes machine learning algorithms, and among a number of algorithms, naïve Bayes and support vector machine, which are suitable for text data, are known to have reasonable performance. Recently, with the development of deep learning technology, several researches on applying deep neural networks such as recurrent neural networks (RNN) and convolutional neural networks (CNN) have been introduced to improve the performance of text classification system. However, the current text classification techniques have not yet reached the perfect level of text classification. This paper focuses on the fact that the text data is expressed as a vector only with the word dimensions, which impairs the semantic information inherent in the text, and proposes a neural network architecture based upon the semantic tensor space model.

• The Journal of Information Systems
• /
• v.29 no.4
• /
• pp.171-191
• /
• 2020

Purpose The study aims to compare the online review writing behavior of users in China and the United States through text mining on online reviews' text content. In particular, existing studies have verified that there are differences in online reviews between different cultures. Therefore, the purpose of this study is to compare the differences between reviews written by Chinese and American tourists by analyzing text contents of online reviews based on cultural theory. Design/methodology/approach This study collected and analyzed online review data for hotels, targeting Chinese and US tourists who visited Korea. Then, we analyzed review data through text mining like sentiment analysis and topic modeling analysis method based on previous research analysis. Findings The results showed that Chinese tourists gave higher ratings and relatively less negative ratings than American tourists. And American tourists have more negative sentiments and emotions in writing online reviews than Chinese tourists. Also, through the analysis results using topic modeling, it was confirmed that Chinese tourists mentioned more topics about the hotel location, room, and price, while American tourists mentioned more topics about hotel service. American tourists also mention more topics about hotels than Chinese tourists, indicating that American tourists tend to provide more information through online reviews.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.43 no.4
• /
• pp.33-40
• /
• 2020

In order to satisfy customers, it is important to identify the quality elements that affect customers' satisfaction. The Kano model has been widely used in identifying multi-dimensional quality attributes in this purpose. However, the model suffers from various shortcomings and limitations, especially those related to survey practices such as the data amount, reply attitude and cost. In this research, a model based on the text sentiment analysis is proposed, which aims to substitute the survey-based data gathering process of Kano models with sentiment analysis. In this model, from the set of opinion text, quality elements for the research are extracted using the morpheme analysis. The opinions' polarity attributes are evaluated using text sentiment analysis, and those polarity text items are transformed into equivalent Kano survey questions. Replies for the transformed survey questions are generated based on the total score of the original data. Then, the question-reply set is analyzed using both the original Kano evaluation method and the satisfaction index method. The proposed research model has been tested using a large amount of data of public IT service project evaluations. The result shows that it can replace the existing practice and it promises advantages in terms of quality and cost of data gathering. The authors hope that the proposed model of this research may serve as a new quality analysis model for a wide range of areas.

• International Journal of Computer Science & Network Security
• /
• v.22 no.8
• /
• pp.242-248
• /
• 2022

The article presents the analysis of modern methods of automatic comparison of original and unoriginal text to detect textual plagiarism. The study covers two types of plagiarism - literal, when plagiarists directly make exact copying of the text without changing anything, and intelligent, using more sophisticated techniques, which are harder to detect due to the text manipulation, like words and signs replacement. Standard techniques related to extrinsic detection are string-based, vector space and semantic-based. The first, most common and most successful target models for detecting literal plagiarism - N-gram and Vector Space are analyzed, and their advantages and disadvantages are evaluated. The most effective target models that allow detecting intelligent plagiarism, particularly identifying paraphrases by measuring the semantic similarity of short components of the text, are investigated. Models using neural network architecture and based on natural language sentence matching approaches such as Densely Interactive Inference Network (DIIN), Bilateral Multi-Perspective Matching (BiMPM) and Bidirectional Encoder Representations from Transformers (BERT) and its family of models are considered. The progress in improving plagiarism detection systems, techniques and related models is summarized. Relevant and urgent problems that remain unresolved in detecting intelligent plagiarism - effective recognition of unoriginal ideas and qualitatively paraphrased text - are outlined.

• Proceedings of the CALSEC Conference
• /
• 2004.02a
• /
• pp.294-301
• /
• 2004

·Text-mining approach to e-documents organization based on topic hierarchy - Machine-Learning ＆ information Theory-based ㆍ 'Category(topic) discovery' problem → document bundle-based user-constraint document clustering ㆍ 'Automatic categorization' problem → Accelerated EM with CU-based active learning → 'Hierarchy Construction' problem → Unsupervised learning of category subsumption relation