• Proceedings of the Korean Society of Disaster Information Conference
• /
• 2022.10a
• /
• pp.145-147
• /
• 2022

본 논문은 대규모 텍스트 데이터에서 이슈를 발굴할 때 사용되는 기존의 정보 네트워크 또는 지식 그래프 구축 방법의 한계점을 지적하고, 문장 단위로 정보 네트워크를 구축하는 새로운 방법에 대해서 제안한다. 먼저 문장을 구성하는 단어와 캐릭터수의 분포를 측정하며 의성어와 같은 노이즈를 제거하기 위한 역치값을 설정하였다. 다음으로 BERT 기반 언어모델을 이용하여 모든 문장을 벡터화하고, 코사인 유사도를 이용하여 두 문장벡터에 대한 유사성을 측정하였다. 오분류된 유사도 결과를 최소화하기 위하여 명사형 단어의 의미적 연관성을 비교하는 알고리즘을 개발하였다. 제안된 유사문장 비교 알고리즘의 결과를 검토해 보면, 두 문장은 서술되는 형태가 다르지만 동일한 주제와 내용을 다루고 있는 것을 확인할 수 있었다. 본 논문에서 제안하는 방법은 단어 단위 지식 그래프 해석의 어려움을 극복할 수 있는 새로운 방법이다. 향후 이슈 및 트랜드 분석과 같은 미래연구 분야에 적용하면, 데이터 기반으로 특정 주제에 대한 사회적 관심을 수렴하고, 수요를 반영한 정책적 제언을 도출하는데 기여할 수 있을 것이다

• Journal of Intelligence and Information Systems
• /
• v.22 no.1
• /
• pp.83-105
• /
• 2016

Measuring an individual's subjective wellbeing in an accurate, unobtrusive, and cost-effective manner is a core success factor of the wellbeing support system, which is a type of medical IT service. However, measurements with a self-report questionnaire and wearable sensors are cost-intensive and obtrusive when the wellbeing support system should be running in real-time, despite being very accurate. Recently, reasoning the state of subjective wellbeing with conventional sentiment analysis and unstructured data has been proposed as an alternative to resolve the drawbacks of the self-report questionnaire and wearable sensors. However, this approach does not consider contextual polarity, which results in lower measurement accuracy. Moreover, there is no sentimental word net or ontology for the subjective wellbeing area. Hence, this paper proposes a method to extract keywords and their contextual polarity representing the subjective wellbeing state from the unstructured text in online websites in order to improve the reasoning accuracy of the sentiment analysis. The proposed method is as follows. First, a set of general sentimental words is proposed. SentiWordNet was adopted; this is the most widely used dictionary and contains about 100,000 words such as nouns, verbs, adjectives, and adverbs with polarities from -1.0 (extremely negative) to 1.0 (extremely positive). Second, corpora on subjective wellbeing (SWB corpora) were obtained by crawling online text. A survey was conducted to prepare a learning dataset that includes an individual's opinion and the level of self-report wellness, such as stress and depression. The participants were asked to respond with their feelings about online news on two topics. Next, three data sources were extracted from the SWB corpora: demographic information, psychographic information, and the structural characteristics of the text (e.g., the number of words used in the text, simple statistics on the special characters used). These were considered to adjust the level of a specific SWB. Finally, a set of reasoning rules was generated for each wellbeing factor to estimate the SWB of an individual based on the text written by the individual. The experimental results suggested that using contextual polarity for each SWB factor (e.g., stress, depression) significantly improved the estimation accuracy compared to conventional sentiment analysis methods incorporating SentiWordNet. Even though literature is available on Korean sentiment analysis, such studies only used only a limited set of sentimental words. Due to the small number of words, many sentences are overlooked and ignored when estimating the level of sentiment. However, the proposed method can identify multiple sentiment-neutral words as sentiment words in the context of a specific SWB factor. The results also suggest that a specific type of senti-word dictionary containing contextual polarity needs to be constructed along with a dictionary based on common sense such as SenticNet. These efforts will enrich and enlarge the application area of sentic computing. The study is helpful to practitioners and managers of wellness services in that a couple of characteristics of unstructured text have been identified for improving SWB. Consistent with the literature, the results showed that the gender and age affect the SWB state when the individual is exposed to an identical queue from the online text. In addition, the length of the textual response and usage pattern of special characters were found to indicate the individual's SWB. These imply that better SWB measurement should involve collecting the textual structure and the individual's demographic conditions. In the future, the proposed method should be improved by automated identification of the contextual polarity in order to enlarge the vocabulary in a cost-effective manner.

• Journal of Intelligence and Information Systems
• /
• v.25 no.4
• /
• pp.105-122
• /
• 2019

Dimensionality reduction is one of the methods to handle big data in text mining. For dimensionality reduction, we should consider the density of data, which has a significant influence on the performance of sentence classification. It requires lots of computations for data of higher dimensions. Eventually, it can cause lots of computational cost and overfitting in the model. Thus, the dimension reduction process is necessary to improve the performance of the model. Diverse methods have been proposed from only lessening the noise of data like misspelling or informal text to including semantic and syntactic information. On top of it, the expression and selection of the text features have impacts on the performance of the classifier for sentence classification, which is one of the fields of Natural Language Processing. The common goal of dimension reduction is to find latent space that is representative of raw data from observation space. Existing methods utilize various algorithms for dimensionality reduction, such as feature extraction and feature selection. In addition to these algorithms, word embeddings, learning low-dimensional vector space representations of words, that can capture semantic and syntactic information from data are also utilized. For improving performance, recent studies have suggested methods that the word dictionary is modified according to the positive and negative score of pre-defined words. The basic idea of this study is that similar words have similar vector representations. Once the feature selection algorithm selects the words that are not important, we thought the words that are similar to the selected words also have no impacts on sentence classification. This study proposes two ways to achieve more accurate classification that conduct selective word elimination under specific regulations and construct word embedding based on Word2Vec embedding. To select words having low importance from the text, we use information gain algorithm to measure the importance and cosine similarity to search for similar words. First, we eliminate words that have comparatively low information gain values from the raw text and form word embedding. Second, we select words additionally that are similar to the words that have a low level of information gain values and make word embedding. In the end, these filtered text and word embedding apply to the deep learning models; Convolutional Neural Network and Attention-Based Bidirectional LSTM. This study uses customer reviews on Kindle in Amazon.com, IMDB, and Yelp as datasets, and classify each data using the deep learning models. The reviews got more than five helpful votes, and the ratio of helpful votes was over 70% classified as helpful reviews. Also, Yelp only shows the number of helpful votes. We extracted 100,000 reviews which got more than five helpful votes using a random sampling method among 750,000 reviews. The minimal preprocessing was executed to each dataset, such as removing numbers and special characters from text data. To evaluate the proposed methods, we compared the performances of Word2Vec and GloVe word embeddings, which used all the words. We showed that one of the proposed methods is better than the embeddings with all the words. By removing unimportant words, we can get better performance. However, if we removed too many words, it showed that the performance was lowered. For future research, it is required to consider diverse ways of preprocessing and the in-depth analysis for the co-occurrence of words to measure similarity values among words. Also, we only applied the proposed method with Word2Vec. Other embedding methods such as GloVe, fastText, ELMo can be applied with the proposed methods, and it is possible to identify the possible combinations between word embedding methods and elimination methods.

• Journal of Intelligence and Information Systems
• /
• v.22 no.2
• /
• pp.33-56
• /
• 2016

Many researchers have focused on developing bankruptcy prediction models using modeling techniques, such as statistical methods including multiple discriminant analysis (MDA) and logit analysis or artificial intelligence techniques containing artificial neural networks (ANN), decision trees, and support vector machines (SVM), to secure enhanced performance. Most of the bankruptcy prediction models in academic studies have used financial ratios as main input variables. The bankruptcy of firms is associated with firm's financial states and the external economic situation. However, the inclusion of qualitative information, such as the economic atmosphere, has not been actively discussed despite the fact that exploiting only financial ratios has some drawbacks. Accounting information, such as financial ratios, is based on past data, and it is usually determined one year before bankruptcy. Thus, a time lag exists between the point of closing financial statements and the point of credit evaluation. In addition, financial ratios do not contain environmental factors, such as external economic situations. Therefore, using only financial ratios may be insufficient in constructing a bankruptcy prediction model, because they essentially reflect past corporate internal accounting information while neglecting recent information. Thus, qualitative information must be added to the conventional bankruptcy prediction model to supplement accounting information. Due to the lack of an analytic mechanism for obtaining and processing qualitative information from various information sources, previous studies have only used qualitative information. However, recently, big data analytics, such as text mining techniques, have been drawing much attention in academia and industry, with an increasing amount of unstructured text data available on the web. A few previous studies have sought to adopt big data analytics in business prediction modeling. Nevertheless, the use of qualitative information on the web for business prediction modeling is still deemed to be in the primary stage, restricted to limited applications, such as stock prediction and movie revenue prediction applications. Thus, it is necessary to apply big data analytics techniques, such as text mining, to various business prediction problems, including credit risk evaluation. Analytic methods are required for processing qualitative information represented in unstructured text form due to the complexity of managing and processing unstructured text data. This study proposes a bankruptcy prediction model for Korean small- and medium-sized construction firms using both quantitative information, such as financial ratios, and qualitative information acquired from economic news articles. The performance of the proposed method depends on how well information types are transformed from qualitative into quantitative information that is suitable for incorporating into the bankruptcy prediction model. We employ big data analytics techniques, especially text mining, as a mechanism for processing qualitative information. The sentiment index is provided at the industry level by extracting from a large amount of text data to quantify the external economic atmosphere represented in the media. The proposed method involves keyword-based sentiment analysis using a domain-specific sentiment lexicon to extract sentiment from economic news articles. The generated sentiment lexicon is designed to represent sentiment for the construction business by considering the relationship between the occurring term and the actual situation with respect to the economic condition of the industry rather than the inherent semantics of the term. The experimental results proved that incorporating qualitative information based on big data analytics into the traditional bankruptcy prediction model based on accounting information is effective for enhancing the predictive performance. The sentiment variable extracted from economic news articles had an impact on corporate bankruptcy. In particular, a negative sentiment variable improved the accuracy of corporate bankruptcy prediction because the corporate bankruptcy of construction firms is sensitive to poor economic conditions. The bankruptcy prediction model using qualitative information based on big data analytics contributes to the field, in that it reflects not only relatively recent information but also environmental factors, such as external economic conditions.

• Journal of Technology Innovation
• /
• v.26 no.4
• /
• pp.199-232
• /
• 2018

There are increasing needs for understanding and fathoming of business management environment through big data analysis at industrial and corporative level. The research using the company disclosure information, which is comprehensively covering the business performance and the future plan of the company, is getting attention. However, there is limited research on developing applicable analytical models leveraging such corporate disclosure data due to its unstructured nature. This study proposes a text-mining-based analytical model for industrial and firm level analyses using publicly available company disclousre data. Specifically, we apply LDA topic model and word2vec word embedding model on the U.S. SEC data from the publicly listed firms and analyze the trends of business topics at the industrial and corporate levels. Using LDA topic modeling based on SEC EDGAR 10-K document, whole industrial management topics are figured out. For comparison of different pattern of industries' topic trend, software and hardware industries are compared in recent 20 years. Also, the changes of management subject at firm level are observed with comparison of two companies in software industry. The changes of topic trends provides lens for identifying decreasing and growing management subjects at industrial and firm level. Mapping companies and products(or services) based on dimension reduction after using word2vec word embedding model and principal component analysis of 10-K document at firm level in software industry, companies and products(services) that have similar management subjects are identified and also their changes in decades. For suggesting methodology to develop analysis model based on public management data at industrial and corporate level, there may be contributions in terms of making ground of practical methodology to identifying changes of managements subjects. However, there are required further researches to provide microscopic analytical model with regard to relation of technology management strategy between management performance in case of related to various pattern of management topics as of frequent changes of management subject or their momentum. Also more studies are needed for developing competitive context analysis model with product(service)-portfolios between firms.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.11
• /
• pp.471-480
• /
• 2023

The Korean construction order volume in South Korea grew significantly from 91.3 trillion won in public orders in 2013 to a total of 212 trillion won in 2021, particularly in the private sector. As the size of the domestic and overseas markets grew, the scale and complexity of EPC (Engineering, Procurement, Construction) projects increased, and risk management of project management and ITB (Invitation to Bid) documents became a critical issue. The time granted to actual construction companies in the bidding process following the EPC project award is not only limited, but also extremely challenging to review all the risk terms in the ITB document due to manpower and cost issues. Previous research attempted to categorize the risk terms in EPC contract documents and detect them based on AI, but there were limitations to practical use due to problems related to data, such as the limit of labeled data utilization and class imbalance. Therefore, this study aims to develop an AI model that can categorize the contract terms based on the FIDIC Yellow 2017(Federation Internationale Des Ingenieurs-Conseils Contract terms) standard in detail, rather than defining and classifying risk terms like previous research. A multi-text classification function is necessary because the contract terms that need to be reviewed in detail may vary depending on the scale and type of the project. To enhance the performance of the multi-text classification model, we developed the ELECTRA PLM (Pre-trained Language Model) capable of efficiently learning the context of text data from the pre-training stage, and conducted a four-step experiment to validate the performance of the model. As a result, the ensemble version of the self-developed ITB-ELECTRA model and Legal-BERT achieved the best performance with a weighted average F1-Score of 76% in the classification of 57 contract terms.

• Journal of Internet Computing and Services
• /
• v.16 no.2
• /
• pp.57-66
• /
• 2015

Considerable research efforts are being directed towards analyzing unstructured data such as text files and log files using commercial and noncommercial analytical tools. In particular, researchers are trying to extract meaningful knowledge through text mining in not only business but also many other areas such as politics, economics, and cultural studies. For instance, several studies have examined national pending issues by analyzing large volumes of text on various social issues. However, it is difficult to provide successful information services that can identify R&D documents on specific national pending issues. While users may specify certain keywords relating to national pending issues, they usually fail to retrieve appropriate R&D information primarily due to discrepancies between these terms and the corresponding terms actually used in the R&D documents. Thus, we need an intermediate logic to overcome these discrepancies, also to identify and package appropriate R&D information on specific national pending issues. To address this requirement, three methodologies are proposed in this study-a hybrid methodology for extracting and integrating keywords pertaining to national pending issues, a methodology for packaging R&D information that corresponds to national pending issues, and a methodology for constructing an associative issue network based on relevant R&D information. Data analysis techniques such as text mining, social network analysis, and association rules mining are utilized for establishing these methodologies. As the experiment result, the keyword enhancement rate by the proposed integration methodology reveals to be about 42.8%. For the second objective, three key analyses were conducted and a number of association rules between national pending issue keywords and R&D keywords were derived. The experiment regarding to the third objective, which is issue clustering based on R&D keywords is still in progress and expected to give tangible results in the future.

• Journal of Korean Philosophical Society
• /
• v.116
• /
• pp.155-180
• /
• 2010

The three means of listening, reflection and meditation (${\acute{s}}raava{\d{n}}a$, manana and $nididhy{\bar{a}}sana$) which are central devices of practice in $Ved{\bar{a}}nta$ philosophy should be understood not as a continuative step but as a methodological extension on condition of having one and the same purpose. In other words, the three means should be interpreted in a listening-oriented manner, in which the process has to be methodologically extended to reflection and meditation only when the direct knowledge on the reality is not gained in listening. This kind of interpretation can be more justified by displaying significant characteristics of Indian philosophy implied in the three means. It can be easily said that $Ved{\bar{a}}nta$ belonging to the liberation-centric tradition is a project of 'regaining essential self' through which the self becomes essential self by knowing that self. In this case the listening-oriented interpretation coincides with the basic teachings of $Ved{\bar{a}}nta$, since listening alone can be a sufficient means for obtaining knowledge of the original self. Further, as the project of 'regaining essential self' is carried out by the three means, these can be called a sort of 'event' that is carried out according to the scenario of $Ved{\bar{a}}ntic$ metaphysics. In this case listening is a course of comprehending the scenario of event participated by oneself, and that participant can accomplish the project by way of listening the scenario alone judged as somewhat more effective for liberation. However, in the later $Ved{\bar{a}}nta$ there arises a meditation-oriented interpretation of which three means are regarded not as a methodological extension but as a continuative step, because of the emphasis on meditation under the lasting influence of other philosophical systems. This is a result of epistemic desire that tries to convert what is heard to what is specially perceived or what is given to what is accepted. It may be said that this interpretation emphasizing the phased transition from the indirect to the direct of knowledge is an attempt to rationalize the repetitive delay of event as the actual failure of project. Furthermore, an assertion of the later $Ved{\bar{a}}nta$ which refers the fourth means called $sam{\bar{a}}dhi$ is based on the logic that the self-realization is possible apart from and outside the text, and accordingly it is incompatible with an assertion of the early $Ved{\bar{a}}nta$ that the self-realization is a reproduction as it is of the scenario guided by the absolute text. After all, the standard interpretation on the three means in $Ved{\bar{a}}nta$ have to be the listening-oriented, but not be the meditation-oriented or the $sam{\bar{a}}dhi$-oriented.

• Journal of Practical Agriculture & Fisheries Research
• /
• v.22 no.2
• /
• pp.99-114
• /
• 2020

In this study we examined the topic analysis and correlation analysis by text mining from the self introduction letter of freshman at Korea National College of Agriculture and Fisheries(KNCAF) in 2020. The analysis items of the 3rd question were and the 4th question were the motivation for applying to college, the academic plan and the career plan. The text mining to the 3rd question showed that the frequency of 'friends' was overwhelmingly high, followed by keywords such as 'thought', 'time', 'opinion', 'activity', and 'club'. In the 4th question, keyword frequency such as 'thought', 'agriculture', 'KNCAF', 'farm', 'father' was high. The result of association rules analysis for each question showed that the relationship with the highest support level, which means the frequency and importance of the rule, was the {friend} <=> {thought}, {thought} <=> {KNCAF}. The confidence level of a correlation between keywords was the highest in the rules of {teacher}=>{friend}, {agriculture, KNCAF}=>{thought}. Also the lift level that indicates the closeness of two words was the highest in the rules of {friend} <=> {teacher}, {knowledge} <=> {professional}. These keywords are found to play a very important roles in analyzing betweenness centrality and analyzing degree centrality between keywords. The results of frequency analysis and association analysis were visualized with word cloud and correlation graphs to make it easier to understand all the results.

• Journal of Practical Agriculture & Fisheries Research
• /
• v.21 no.1
• /
• pp.99-114
• /
• 2019

In this study we examined the preferences of eight college living factors for students at Korea National College of Agriculture and Fisheries(KNCAF). Analytical techniques of unstructured data used opinion mining and text mining techniques, and the analysis results of text mining were visualized as word cloud. The college life factors included eight topics that were closely related to students: 'my present', 'my 10 years later', 'friendship', 'college festival', 'student restaurant', 'college dormitory', 'KNCAF', and 'long-term field practice'. In the text submitted by the students, we have established a dictionary of positive words and negative words to evaluate the preference by classifying the emotions of positive and negative. As a result, KNCAF students showed more than 85% positive emotions about the theme of 'student restaurant' and 'friendship'. But students' positive feelings about 'long-term field practice' and 'college dormitory' showed the lowest satisfaction rate of not exceeding 60%. The rest of the topics showed satisfaction of 69.3~74.2%. The gender differences showed that the positive emotions of male students were high in the topics of 'my present', 'my 10 years later', 'friendship', 'college dormitory' and 'long-term field practice'. And those of female were high in 'college festival', 'student restaurant' and 'KNCAF'. In addition, using text mining technique, the main words of positive and negative words were extracted, and word cloud was created to visualize the results.