• The Journal of Bigdata
• /
• v.4 no.2
• /
• pp.35-45
• /
• 2019

Recently, the damage with social cost of malicious comments is increasing. In addition to the news of talent committing suicide through the effects of malicious comments. The damage to malicious comments including abusive language and slang is increasing and spreading in various type and forms throughout society. In this paper, we propose a technique for detecting abusive language using a bi-directional long short-term memory neural network model. We collected comments on the web through the web crawler and processed the stopwords on unused words such as English Alphabet or special characters. For the stopwords processed comments, the bidirectional long short-term memory neural network model considering the front word and back word of sentences was used to determine and detect abusive language. In order to use the bi-directional long short-term memory neural network, the detected comments were subjected to morphological analysis and vectorization, and each word was labeled with abusive language. Experimental results showed a performance of 88.79% for a total of 9,288 comments screened and collected.

• The Korean Journal of Applied Statistics
• /
• v.34 no.2
• /
• pp.191-204
• /
• 2021

Visual Question Answering (VQA) and image captioning are tasks that require understanding of the features of images and linguistic features of text. Therefore, co-attention may be the key to both tasks, which can connect image and text. In this paper, we propose a model to achieve high performance for VQA by image caption generated using a pretrained standard transformer model based on MSCOCO dataset. Captions unrelated to the question can rather interfere with answering, so some captions similar to the question were selected to use based on a similarity to the question. In addition, stopwords in the caption could not affect or interfere with answering, so the experiment was conducted after removing stopwords. Experiments were conducted on VQA-v2 data to compare the proposed model with the deep modular co-attention network (MCAN) model, which showed good performance by using co-attention between images and text. As a result, the proposed model outperformed the MCAN model.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.891-897
• /
• 2022

In big data analysis, raw text data mostly exists in various unstructured data forms, so it becomes a structured data form that can be analyzed only after undergoing heuristic pre-processing and computer post-processing cleansing. Therefore, in this study, unnecessary elements are purified through pre-processing of the collected raw data in order to apply the wordcloud of R program, which is one of the text data analysis techniques, and stopwords are removed in the post-processing process. Then, a case study of wordcloud analysis was conducted, which calculates the frequency of occurrence of words and expresses words with high frequency as key issues. In this study, to improve the problems of the "nested stopword source code" method, which is the existing stopword processing method, using the word cloud technique of R, we propose the use of "general stopword corpus" and "user-defined stopword corpus" and conduct case analysis. The advantages and disadvantages of the proposed "unstructured data cleansing process model" are comparatively verified and presented, and the practical application of word cloud visualization analysis using the "proposed external corpus cleansing technique" is presented.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.6
• /
• pp.935-940
• /
• 2023

Most text data collected through web scraping for artificial intelligence and big data analysis is generally large and unstructured, so a purification process is required for big data analysis. The process becomes structured data that can be analyzed through a heuristic pre-processing refining step and a post-processing machine refining step. Therefore, in this study, in the post-processing machine refining process, the Korean dictionary and the stopword dictionary are used to extract vocabularies for frequency analysis for word cloud analysis. In this process, "user-defined stopwords" are used to efficiently remove stopwords that were not removed. We propose a methodology for applying the "thesaurus" and examine the pros and cons of the proposed refining method through a case analysis using the "user-defined stop word thesaurus" technique proposed to complement the problems of the existing "stop word dictionary" method with R's word cloud technique. We present comparative verification and suggest the effectiveness of practical application of the proposed methodology.

• The Journal of Information Systems
• /
• v.28 no.4
• /
• pp.155-174
• /
• 2019

Purpose Social interest in financial statement notes has recently increased. However, contrary to the keen interest in financial statement notes, there is no morphological analyzer for accounting terms, which is why researchers are having considerable difficulty in carrying out research. In this study, we build a morphological analyzer for accounting related text mining techniques. This morphological analyzer can handle accounting terms like financial statements and we expect it to serve as a springboard for growth in the text mining research field. Design/methodology/approach In this study, we build customized korean morphological analyzer to extract proper accounting terms. First, we collect Company's Financial Statement notes, financial information data published by KPFIS(Korea Public Finance Information Service), K-IFRS accounting terms data. Second, we cleaning and tokeninzing and removing stopwords. Third, we customize morphological analyzer using n-gram methodology. Findings Existing morphological analyzer cannot extract accounting terms because it split accounting terms to many nouns. In this study, the new customized morphological analyzer can detect more appropriate accounting terms comparing to the existing morphological analyzer. We found that accounting words that were not detected by existing morphological analyzers were detected in new customized morphological analyzers.

• Journal of KIISE:Databases
• /
• v.27 no.1
• /
• pp.90-100
• /
• 2000

We propose, in this paper, a new query expansion technique with term reweighting. All terms in the documents feedbacked from a user, excluding stopwords, are selected as candidate terms for query expansion and reweighted using the relevance degree which is calculated from the term-distribution similarity between a candidate term and each term in initial query. The term-distribution similarity of two terms is a measure on how similar their occurrence distributions in relevant documents are. The terms to be actually expanded are selected using the relevance degree and combined with initial query to construct an expanded query. We use KT-set 1.0 and KT-set 2.0 to evaluate performance and compare our method with two methods, one with no relevance feedback and the other with Dec-Hi method which is similar to our method. based on recall and precision.

• Journal of Information Management
• /
• v.23 no.1
• /
• pp.39-62
• /
• 1992

In this paper about 60 auxiliary words and 320 stopwords are selected from analysis of sample data, four types of stop word are classified left, right and - auxiliary word truncation & normal. And a keyword extraction system is suggested which undertakes efficient truncation of auxiliary word from words, conversion of Chinese word to Korean and exclusion of stopword. The selected keyeords in this system show 92.2% of accordance ratio compared with manually selected keywords by expert. And then compound words consist of $4{\sim}6$ character generate twice of additional new words and 58.8% words of those are useful as keyword.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.4
• /
• pp.495-502
• /
• 2022

Web crawler, which is mainly used to collect text on the web today, is difficult to maintain and expand because researchers must implement different collection logic by collection channel after analyzing tags and styles of HTML documents. To solve this problem, the web crawler should be able to collect text by formalizing HTML documents to the same structure. In this paper, we designed and implemented WCTT(Web Crawling system based on Tag path and Text appearance frequency), a web crawling system that collects text with a single collection logic by formalizing HTML documents based on tag path and text appearance frequency. Because WCTT collects texts with the same logic for all collection channels, it is easy to maintain and expand the collection channel. In addition, it provides the preprocessing function that removes stopwords and extracts only nouns for keyword network analysis and so on.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.4
• /
• pp.745-750
• /
• 2021

In Big data visualization analysis of unstructured text data, raw data is mostly large-capacity, and analysis techniques cannot be applied without cleansing it unstructured. Therefore, from the collected raw data, unnecessary data is removed through the first heuristic cleansing process and Stopwords are removed through the second machine cleansing process. Then, the frequency of the vocabulary is calculated, visualized using the word cloud technique, and key issues are extracted and informationalized, and the results are analyzed. In this study, we propose a new Stopword cleansing technique using an external Stopword set (DB) in Python word cloud, and derive the problems and effectiveness of this technique through practical case analysis. And, through this verification result, the utility of the practical application of word cloud analysis applying the proposed cleansing technique is presented.

• Journal of Information Science Theory and Practice
• /
• v.10 no.spc
• /
• pp.143-153
• /
• 2022

With the development of networks and the increase in the number of network devices, the number of cyber attacks targeting them is also increasing. Since these cyber-attacks aim to steal important information and destroy systems, it is necessary to minimize social and economic damage through early detection and rapid response. Many studies using machine learning (ML) and artificial intelligence (AI) have been conducted, among which payload learning is one of the most intuitive and effective methods to detect malicious behavior. In this study, we propose a preprocessing method to maximize the performance of the model when learning the payload in term units. The proposed method constructs a high-quality learning data set by eliminating unnecessary noise (stopwords) and preserving important features in consideration of the machine language and natural language characteristics of the packet payload. Our method consists of three steps: Preserving significant special characters, Generating a stopword list, and Class label refinement. By processing packets of various and complex structures based on these three processes, it is possible to make high-quality training data that can be helpful to build high-performance ML/AI models for security monitoring. We prove the effectiveness of the proposed method by comparing the performance of the AI model to which the proposed method is applied and not. Forthermore, by evaluating the performance of the AI model applied proposed method in the real-world Security Operating Center (SOC) environment with live network traffic, we demonstrate the applicability of the our method to the real environment.