• Journal of Digital Convergence
• /
• v.18 no.7
• /
• pp.93-99
• /
• 2020

Text mining is one of the big data analysis methods that extracts meaningful information from atypical large-scale text data. In this study, text mining was used to monitor citizens' opinions on the policies and systems being implemented. We collected 5,108 newspaper articles and 748 online cafe posts related to 'Gyeonggi Lacal Currency' and performed frequency analysis, TF-IDF analysis, association analysis, and word tree visualization analysis. As a result, many articles related to the purpose of introducing local currency, the benefits provided, and the method of use. However, the contents related to the actual use of local currency were written in the online cafe posts. In order to revitalize local currency, the news was involved in the promotion of local currency as an informant. Online cafe posts consisted of the opinions of citizens who are local currency users. SNS and text mining are expected to effectively activate various policies as well as local currency.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.11
• /
• pp.521-526
• /
• 2017

Data format of Big data is diverse and vast, and its generation speed is very fast, requiring new management and analysis methods, not traditional data processing methods. Textual mining techniques can be used to extract useful information from unstructured text written in human language in online documents on social networks. Identifying trends in the message of politics, economy, and culture left behind in social media is a factor in understanding what topics they are interested in. In this study, text mining was performed on online news related to a given keyword using topic - oriented analysis technique. We use Latent Dirichiet Allocation (LDA) to extract information from web documents and analyze which subjects are interested in a given keyword, and which topics are related to which core values are related.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.11
• /
• pp.3935-3949
• /
• 2021

With the rapid development of Internet and big data technology, various online social network platforms have been established, producing massive information every day. Hot topic discovery aims to dig out meaningful content that users commonly concern about from the massive information on the Internet. Most of the existing hot topic discovery methods focus on a single network data source, and can hardly grasp hot spots as a whole, nor meet the challenges of text sparsity and topic hotness evaluation in cross-network scenarios. This paper proposes a novel hot topic discovery method across social network based on an im-proved LDA model, which first integrates the text information from multiple social network platforms into a unified data set, then obtains the potential topic distribution in the text through the improved LDA model. Finally, it adopts a heat evaluation method based on the word frequency of topic label words to take the latent topic with the highest heat value as a hot topic. This paper obtains data from the online social networks and constructs a cross-network topic discovery data set. The experimental results demonstrate the superiority of the proposed method compared to baseline methods.

• Journal of the Korean Society for information Management
• /
• v.24 no.4
• /
• pp.305-321
• /
• 2007

The purpose of this study is to examine whether the information resources referenced by human indexers during indexing process are effective on Text Categorization. More specifically, information resources from bibliographic information as well as full text information were explored in the context of a typical scientific journal article data set. The experiment results pointed out that information resources such as citation, source title, and title were not significantly different with full text. Whereas keyword was found to be significantly different with full text. The findings of this study identify that information resources referenced by human indexers can be considered good candidates for text categorization for automatic subject term assignment.

• Journal of Korea Society of Industrial Information Systems
• /
• v.21 no.3
• /
• pp.7-12
• /
• 2016

In a hostile Internet environment, steganography has focused to hide a secret message inside the cover medium for increasing the security. That is the complement of the encryption. This paper presents a text steganography techniques using the Hangul text. To enhance the security level, secret messages have been encrypted first through the genetic algorithm operator crossover. And then embedded into an cover text to form the stego text without changing its noticeable properties and structures. To maintain the capacity in the cover media to 3.69%, the experiments show that the size of the stego text was increased up to 14%.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.115-124
• /
• 2022

In this paper, YOLO and EAST models are tested to analyze their performance in text area detecting for real-world and normal text images. The earl ier YOLO models which include YOLOv3 have been known to underperform in detecting text areas for given images, but the recently released YOLOv4 and YOLOv5 achieved promising performances to detect text area included in various images. Experimental results show that both of YOLO v4 and v5 models are expected to be widely used for text detection in the filed of scene text recognition in the future.

• Knowledge Management Research
• /
• v.20 no.4
• /
• pp.23-38
• /
• 2019

The Korean government has been trying to create new economic value-added and jobs by the openness and utilization of open government data. However, most of open government data has poor utilization rate. Although open government data standardization is a major cause of those inactivation, it is not sufficient to conduct empirical research on open government data itself. Based on this trend, this paper aims to find the priority area for opening data and suggests a realistic directions of standardization of open government data. Text mining and social network analysis approaches are used to analyze open government data and standardization. This research suggests the guides to open government data managers in practical view from selection of data to standardization direction. In addition, this research has academic implications to the knowledge management systems in terms of suggesting standardization direction by using various techniques.

• Communications for Statistical Applications and Methods
• /
• v.30 no.3
• /
• pp.343-354
• /
• 2023

Recently, there have been many improvements in general language models using architectures such as GPT-3 proposed by Brown et al. (2020). Nevertheless, training complex models can hardly be done if the number of data is very small. Data augmentation that addressed this problem was more than normal success in image data. Image augmentation technology significantly improves model performance without any additional data or architectural changes (Perez and Wang, 2017). However, applying this technique to textual data has many challenges because the noise to be added is veiled. Thus, we have developed a novel method for performing data augmentation on text data. We divide the data into signals with positive or negative meaning and noise without them, and then perform data augmentation using k-doc augmentation to randomly combine signals and noises from all data to generate new data.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.10
• /
• pp.455-460
• /
• 2023

Text augmentation is a methodology that creates new augmented texts by transforming or generating original texts for the purpose of improving the performance of NLP models. However existing text augmentation techniques have limitations such as lack of expressive diversity semantic distortion and limited number of augmented texts. Recently text augmentation using large language models and few-shot learning can overcome these limitations but there is also a risk of noise generation due to incorrect generation. In this paper, we propose a text augmentation method called TAGS that generates multiple candidate texts and selects the appropriate text as the augmented text. TAGS generates various expressions using few-shot learning while effectively selecting suitable data even with a small amount of original text by using contrastive learning and similarity comparison. We applied this method to task-oriented chatbot data and achieved more than sixty times quantitative improvement. We also analyzed the generated texts to confirm that they produced semantically and expressively diverse texts compared to the original texts. Moreover, we trained and evaluated a classification model using the augmented texts and showed that it improved the performance by more than 0.1915, confirming that it helps to improve the actual model performance.

• Journal of Korea Society of Industrial Information Systems
• /
• v.17 no.1
• /
• pp.21-29
• /
• 2012

In this paper, we propose a new method to select colors representing the meaning of text contents based on the cognitive relation between words and colors, Our method is designed on the previous study revealing the existence of crucial words to estimate the colors associated with the meaning of text contents, Using the associative probability of each color with a given word and the strength of color association of the word, we estimate the probability of colors associated with a given text. The goal of this study is to propose a system to recommend the cognitively plausible colors for the meaning of the input text. To build a versatile and efficient database used by our system, two psychological experiments were conducted by using news site articles. In experiment 1, we collected 498 words which were chosen by the participants as having the strong association with color. Subsequently, we investigated which color was associated with each word in experiment 2. In addition to those data, we employed the estimated values of the strength of color association and the colors associated with the words included in a very large corpus of newspapers (approximately 130,000 words) based on the similarity between the words obtained by Latent Semantic Analysis (LSA). Therefore our method allows us to select colors for a large variety of words or sentences. Finally, we verified that our system cognitively succeeded in proposing the colors associated with the meaning of the input text, comparing the correct colors answered by participants with the estimated colors by our method. Our system is expected to be of use in various types of situations such as the data visualization, the information retrieval, the art or web pages design, and so on.