• Journal of Intelligence and Information Systems
• /
• v.18 no.2
• /
• pp.47-60
• /
• 2012

Video data comes in the form of the unstructured and the complex structure. As the importance of efficient management and retrieval for video data increases, studies on the video parsing based on the visual features contained in the video contents are researched to reconstruct video data as the meaningful structure. The early studies on video parsing are focused on splitting video data into shots, but detecting the shot boundary defined with the physical boundary does not cosider the semantic association of video data. Recently, studies on structuralizing video shots having the semantic association to the video scene defined with the semantic boundary by utilizing clustering methods are actively progressed. Previous studies on detecting the video scene try to detect video scenes by utilizing clustering algorithms based on the similarity measure between video shots mainly depended on color features. However, the correct identification of a video shot or scene and the detection of the gradual transitions such as dissolve, fade and wipe are difficult because color features of video data contain a noise and are abruptly changed due to the intervention of an unexpected object. In this paper, to solve these problems, we propose the Scene Detector by using Color histogram, corner Edge and Object color histogram (SDCEO) that clusters similar shots organizing same event based on visual features including the color histogram, the corner edge and the object color histogram to detect video scenes. The SDCEO is worthy of notice in a sense that it uses the edge feature with the color feature, and as a result, it effectively detects the gradual transitions as well as the abrupt transitions. The SDCEO consists of the Shot Bound Identifier and the Video Scene Detector. The Shot Bound Identifier is comprised of the Color Histogram Analysis step and the Corner Edge Analysis step. In the Color Histogram Analysis step, SDCEO uses the color histogram feature to organizing shot boundaries. The color histogram, recording the percentage of each quantized color among all pixels in a frame, are chosen for their good performance, as also reported in other work of content-based image and video analysis. To organize shot boundaries, SDCEO joins associated sequential frames into shot boundaries by measuring the similarity of the color histogram between frames. In the Corner Edge Analysis step, SDCEO identifies the final shot boundaries by using the corner edge feature. SDCEO detect associated shot boundaries comparing the corner edge feature between the last frame of previous shot boundary and the first frame of next shot boundary. In the Key-frame Extraction step, SDCEO compares each frame with all frames and measures the similarity by using histogram euclidean distance, and then select the frame the most similar with all frames contained in same shot boundary as the key-frame. Video Scene Detector clusters associated shots organizing same event by utilizing the hierarchical agglomerative clustering method based on the visual features including the color histogram and the object color histogram. After detecting video scenes, SDCEO organizes final video scene by repetitive clustering until the simiarity distance between shot boundaries less than the threshold h. In this paper, we construct the prototype of SDCEO and experiments are carried out with the baseline data that are manually constructed, and the experimental results that the precision of shot boundary detection is 93.3% and the precision of video scene detection is 83.3% are satisfactory.

• Journal of Intelligence and Information Systems
• /
• v.25 no.4
• /
• pp.67-88
• /
• 2019

Webtoon is a Korean-style digital comics platform that distributes comics content produced using the characteristic elements of the Internet in a form that can be consumed online. With the recent rapid growth of the webtoon industry and the exponential increase in the supply of webtoon content, the need for effective webtoon content recommendation measures is growing. Webtoons are digital content products that combine pictorial, literary and digital elements. Therefore, webtoons stimulate consumer sentiment by making readers have fun and engaging and empathizing with the situations in which webtoons are produced. In this context, it can be expected that the sentiment that webtoons evoke to consumers will serve as an important criterion for consumers' choice of webtoons. However, there is a lack of research to improve webtoons' recommendation performance by utilizing consumer sentiment. This study is aimed at developing consumer sentiment pattern maps that can support effective recommendations of webtoon content, focusing on consumer sentiments that have not been fully discussed previously. Metadata and consumer sentiments data were collected for 200 works serviced on the Korean webtoon platform 'Naver Webtoon' to conduct this study. 488 sentiment terms were collected for 127 works, excluding those that did not meet the purpose of the analysis. Next, similar or duplicate terms were combined or abstracted in accordance with the bottom-up approach. As a result, we have built webtoons specialized sentiment-index, which are reduced to a total of 63 emotive adjectives. By performing exploratory factor analysis on the constructed sentiment-index, we have derived three important dimensions for classifying webtoon types. The exploratory factor analysis was performed through the Principal Component Analysis (PCA) using varimax factor rotation. The three dimensions were named 'Immersion', 'Touch' and 'Irritant' respectively. Based on this, K-Means clustering was performed and the entire webtoons were classified into four types. Each type was named 'Snack', 'Drama', 'Irritant', and 'Romance'. For each type of webtoon, we wrote webtoon-sentiment 2-Mode network graphs and looked at the characteristics of the sentiment pattern appearing for each type. In addition, through profiling analysis, we were able to derive meaningful strategic implications for each type of webtoon. First, The 'Snack' cluster is a collection of webtoons that are fast-paced and highly entertaining. Many consumers are interested in these webtoons, but they don't rate them well. Also, consumers mostly use simple expressions of sentiment when talking about these webtoons. Webtoons belonging to 'Snack' are expected to appeal to modern people who want to consume content easily and quickly during short travel time, such as commuting time. Secondly, webtoons belonging to 'Drama' are expected to evoke realistic and everyday sentiments rather than exaggerated and light comic ones. When consumers talk about webtoons belonging to a 'Drama' cluster in online, they are found to express a variety of sentiments. It is appropriate to establish an OSMU(One source multi-use) strategy to extend these webtoons to other content such as movies and TV series. Third, the sentiment pattern map of 'Irritant' shows the sentiments that discourage customer interest by stimulating discomfort. Webtoons that evoke these sentiments are hard to get public attention. Artists should pay attention to these sentiments that cause inconvenience to consumers in creating webtoons. Finally, Webtoons belonging to 'Romance' do not evoke a variety of consumer sentiments, but they are interpreted as touching consumers. They are expected to be consumed as 'healing content' targeted at consumers with high levels of stress or mental fatigue in their lives. The results of this study are meaningful in that it identifies the applicability of consumer sentiment in the areas of recommendation and classification of webtoons, and provides guidelines to help members of webtoons' ecosystem better understand consumers and formulate strategies.

• 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.

• Radiation Oncology Journal
• /
• v.22 no.4
• /
• pp.316-324
• /
• 2004

Purpose : In radiotherapy of tumors in liver, enough planning target volume (PTV) margins are necessary to compensate breathing-related movement of tumor volumes. To overcome the problems, this study aims to obtain patients' body movements by using a moving phantom and an ultrasonic sensor, and to develop respiration sating techniques that can adjust patients' beds by using reversed values of the data obtained. Materials and Methods : The phantom made to measure patients' body movements is composed of a microprocessor (BS II, 20 MHz, 8K Byte), a sensor (Ultra-Sonic, range $3\~3$ m), host computer (RS232C) and stepping motor (torque 2.3 Kg) etc., and the program to control and operate it was developed. The program allows the phantom to move within the maximum range of 2 cm, its movements and corrections to take place In order, and x, y and z to move successively. After the moving phantom was adjusted by entering random movement data (three dimensional data form with distance of 2 cm), and the phantom movements were acquired using the ultra sonic sensor, the two data were compared and analyzed. And then, after the movements by respiration were acquired by using guinea pigs, the real-time respiration gating techniques were drawn by operating the phantom with the reversed values of the data. Results : The result of analyzing the acquisition-correction delay time the three types of data values and about each value separately shows that the data values coincided with one another within $1\%$ and that the acquisition-correction delay time was obtained real-time $(2.34{\times}10^{-4}sec)$. Conclusion : This study successfully confirms the clinic application possibility of respiration gating techniques by using a moving phantom and an ultrasonic sensor. With ongoing development of additional analysis system, which can be used in real-time set-up reproducibility analysis, it may be beneficially used in radiotherapy of moving tumors.

• Journal of Life Science
• /
• v.18 no.4
• /
• pp.522-529
• /
• 2008

High-temperature requirement A2(HtrA2) has been known as a human homologue of bacterial HtrA that has a molecular chaperone function. HtrA2 is mitochondrial serine protease that plays a significant role in regulating the apoptosis; however, the physiological function of HtrA2 still remains elusive. To establish experimental system for the investigation of new insights into the function of HtrA2 in mammalian cells, we first obtained $HtrA2^{+/+}$ and $HtrA2^{-/-}$ MEF cells lines and identified those cells based on the expression pattern and subcellular localization of HtrA2, using immunoblot and biochemical assays. Additionally, we observed that the morphological characteristics of $HtrA2^{-/-}$ MEF cells are different form those of $HtrA2^{+/+}$ MEF cells, showing a rounded shape instead of a typical fibroblast-like shape. Growth rate of $HtrA2^{-/-}$ MEF cells was also 1.4-fold higher than that of $HtrA2^{+/+}$ MEF cells at 36 hours. Furthermore, we verified both MEF cell lines induced caspsase-dependent cell death in response to apoptotic stimuli such as heat shock, staurosporine, and rotenone. The relationship between HtrA2 and heat shock-induced cell death is the first demonstration of the research field of HtrA2. Our study suggests that those MEF cell lines are suitable reagents to further investigate the molecular mechanism by which HtrA2 regulates the balance between cell death and survival.

• Asia pacific journal of information systems
• /
• v.19 no.4
• /
• pp.177-200
• /
• 2009

AIn the advanced - economy, the services industry hasbecome a dominant sector. Evidently, the services sector has grown at a much faster rate than any other. For instance, in such developed countries as the U.S., the proportion of the services sector in its GDP is greater than 75%. Even in the developing countries including India and China, the magnitude of the services sector in their GDPs is rapidly growing. The increasing dependence on service gives rise to new initiatives including service science and service-dominant logic. These new initiatives propose a new theoretical prism to promote the better understanding of the changing economic structure. From the new perspectives, service is no longer regarded as a transaction or exchange, but rather co-creation of value through the interaction among service users, providers, and other stakeholders including partners, external environments, and customer communities. The purpose of this study is the following. First, we review previous literature on service, service innovation, and service systems and integrate the studies based on service dominant logic. Second, we categorize the ten propositions of service dominant logic into conceptual propositions and the ones that are directly related to service provision. Conceptual propositions are left out to form the research model. With the selected propositions, we define the research constructs for this study. Third, we develop measurement items for the new service concepts including service provider network, customer network, value co-creation, and convergence of service with product. We then propose a research model to explain the relationship among the factors that affect the value creation mechanism. Finally, we empirically investigate the effects of the factors on firm performance. Through the process of this research study, we want to show the value creation mechanism of service systems in which various participants in service provision interact with related parties in a joint effort to create values. To test the proposed hypotheses, we developed measurement items and distributed survey questionnaires to domestic companies. 500 survey questionnaires were distributed and 180 were returned among which 171 were usable. The results of the empirical test can be summarized as the following. First, service providers' network which is to help offer required services to customers is found to affect customer network, while it does not have a significant effect on value co-creation and product-service convergence. Second, customer network, on the other hand, appears to influence both value co-creation and product-service convergence. Third, value co-creation accomplished through the collaboration of service providers and customers is found to have a significant effect on both product-service convergence and firm performance. Finally, product-service convergence appears to affect firm performance. To interpret the results from the value creation mechanism perspective, service provider network well established to support customer network is found to have significant effect on customer network which in turn facilitates value co-creation in service provision and product-service convergence to lead to greater firm performance. The results have some enlightening implications for practitioners. If companies want to transform themselves into service-centered business enterprises, they have to consider the four factors suggested in this study: service provider network, customer network, value co-creation, and product-service convergence. That is, companies becoming a service-oriented organization need to understand what the four factors are and how the factors interact with one another in their business context. They then may want to devise a better tool to analyze the value creation mechanism and apply the four factors to their own environment. This research study contributes to the literature in following ways. First, this study is one of the very first empirical studies on the service dominant logic as it has categorized the fundamental propositions into conceptual and empirically testable ones and tested the proposed hypotheses against the data collected through the survey method. Most of the propositions are found to work as Vargo and Lusch have suggested. Second, by providing a testable set of relationships among the research variables, this study may provide policy makers and decision makers with some theoretical grounds for their decision making on what to do with service innovation and management. Finally, this study incorporates the concepts of value co-creation through the interaction between customers and service providers into the proposed research model and empirically tests the validity of the concepts. The results of this study will help establish a value creation mechanism in the service-based economy, which can be used to develop and implement new service provision.

• Asia pacific journal of information systems
• /
• v.20 no.1
• /
• pp.127-140
• /
• 2010

The benefit that a consumer derives from the use of a good often depends on the number of other consumers purchasing the same goods or other compatible items. This property, which is known as network externality, is significant in many IT related industries. Over the past few decades, network externalities have been recognized in the context of physical networks such as the telephone and railroad industries. Today, as many products are provided as a form of system that consists of compatible components, the appreciation of network externality is becoming increasingly important. Network externalities have been extensively studied among economists who have been seeking to explain new phenomena resulting from rapid advancements in ICT (Information and Communication Technology). As a result of these efforts, a new body of theories for 'New Economy' has been proposed. The theoretical bottom-line argument of such theories is that technologies subject to network effects exhibit multiple equilibriums and will finally lock into a monopoly with one standard cornering the entire market. They emphasize that such "tippiness" is a typical characteristic in such networked markets, describing that multiple incompatible technologies rarely coexist and that the switch to a single, leading standard occurs suddenly. Moreover, it is argued that this standardization process is path dependent, and the ultimate outcome is unpredictable. With incomplete information about other actors' preferences, there can be excess inertia, as consumers only moderately favor the change, and hence are themselves insufficiently motivated to start the bandwagon rolling, but would get on it once it did start to roll. This startup problem can prevent the adoption of any standard at all, even if it is preferred by everyone. Conversely, excess momentum is another possible outcome, for example, if a sponsoring firm uses low prices during early periods of diffusion. The aim of this paper is to analyze the dynamics of the adoption process in markets exhibiting network effects by focusing on two factors; switching and agent heterogeneity. Switching is an important factor that should be considered in analyzing the adoption process. An agent's switching invokes switching by other adopters, which brings about a positive feedback process that can significantly complicate the adoption process. Agent heterogeneity also plays a important role in shaping the early development of the adoption process, which has a significant impact on the later development of the process. The effects of these two factors are analyzed by developing an agent-based simulation model. ABM is a computer-based simulation methodology that can offer many advantages over traditional analytical approaches. The model is designed such that agents have diverse preferences regarding technology and are allowed to switch their previous choice. The simulation results showed that the adoption processes in a market exhibiting networks effects are significantly affected by the distribution of agents and the occurrence of switching. In particular, it is found that both weak heterogeneity and strong network effects cause agents to start to switch early and this plays a role of expediting the emergence of 'lock-in.' When network effects are strong, agents are easily affected by changes in early market shares. This causes agents to switch earlier and in turn speeds up the market's tipping. The same effect is found in the case of highly homogeneous agents. When agents are highly homogeneous, the market starts to tip toward one technology rapidly, and its choice is not always consistent with the populations' initial inclination. Increased volatility and faster lock-in increase the possibility that the market will reach an unexpected outcome. The primary contribution of this study is the elucidation of the role of parameters characterizing the market in the development of the lock-in process, and identification of conditions where such unexpected outcomes happen.

• Korean Journal of Food Science and Technology
• /
• v.42 no.2
• /
• pp.223-232
• /
• 2010

Crude polysaccharide (WG-PL-CP) was fractionated from fermented ginseng with Phellinus linteus in solid culture to enhance the immunostimulation of ginseng. WG-PL-CP produce three active polysaccharide-rich fractions (WG-PL-CP-II, III, and IV) on DEAE-Sepharose CL-6B ($Cl^-$ form). WG-PL-CP-III displayed higher mitogenic activity (1.98-fold of the saline control at $100\;{\mu}g/mL$) than did WG-CP-III or PL-CP-III (1.60- or 1.65-fold, respectively), and potent intestinal immune system modulating activity through Peyer's patch was obtained by WG-PL-CP-IV only (1.56-fold). Meanwhile, WG-PL-CP-II and III significantly enhanced macrophage stimulating activity (2.01- and 1.94-fold) compared to WG-CP-II and III (1.73- and 1.66-fold) or PL-CP-II and III (1.79- and 1.72-fold). In addition, WG-PL-CP-III and IV mainly contained neutral sugar (73.5 and 67.3%) and uronic acid (23.2 and 24.6%). Component sugar analysis also showed that WG-PL-CP-III consisted mainly of uronic acid as well as the neutral sugars Glc, Ara, Gal, Rha and Xyl (molar ratio of 0.81:1.00:0.49:0.42:0.28:0.20), whereas WG-PL-CP-IV was mainly comprised of uronic acid, Ara, Rha, Gal, Xyl and Glc (1.00:0.75:0.69:0.63:0.42:0.34). Therefore, it is assumed that these active polysaccharides play an important role in enhancing the immunostimulation of fermented ginseng with P. linteus in solid culture.

• Journal of Intelligence and Information Systems
• /
• v.22 no.2
• /
• pp.127-142
• /
• 2016

Deep learning model is a kind of neural networks that allows multiple hidden layers. There are various deep learning architectures such as convolutional neural networks, deep belief networks and recurrent neural networks. Those have been applied to fields like computer vision, automatic speech recognition, natural language processing, audio recognition and bioinformatics where they have been shown to produce state-of-the-art results on various tasks. Among those architectures, convolutional neural networks and recurrent neural networks are classified as the supervised learning model. And in recent years, those supervised learning models have gained more popularity than unsupervised learning models such as deep belief networks, because supervised learning models have shown fashionable applications in such fields mentioned above. Deep learning models can be trained with backpropagation algorithm. Backpropagation is an abbreviation for "backward propagation of errors" and a common method of training artificial neural networks used in conjunction with an optimization method such as gradient descent. The method calculates the gradient of an error function with respect to all the weights in the network. The gradient is fed to the optimization method which in turn uses it to update the weights, in an attempt to minimize the error function. Convolutional neural networks use a special architecture which is particularly well-adapted to classify images. Using this architecture makes convolutional networks fast to train. This, in turn, helps us train deep, muti-layer networks, which are very good at classifying images. These days, deep convolutional networks are used in most neural networks for image recognition. Convolutional neural networks use three basic ideas: local receptive fields, shared weights, and pooling. By local receptive fields, we mean that each neuron in the first(or any) hidden layer will be connected to a small region of the input(or previous layer's) neurons. Shared weights mean that we're going to use the same weights and bias for each of the local receptive field. This means that all the neurons in the hidden layer detect exactly the same feature, just at different locations in the input image. In addition to the convolutional layers just described, convolutional neural networks also contain pooling layers. Pooling layers are usually used immediately after convolutional layers. What the pooling layers do is to simplify the information in the output from the convolutional layer. Recent convolutional network architectures have 10 to 20 hidden layers and billions of connections between units. Training deep learning networks has taken weeks several years ago, but thanks to progress in GPU and algorithm enhancement, training time has reduced to several hours. Neural networks with time-varying behavior are known as recurrent neural networks or RNNs. A recurrent neural network is a class of artificial neural network where connections between units form a directed cycle. This creates an internal state of the network which allows it to exhibit dynamic temporal behavior. Unlike feedforward neural networks, RNNs can use their internal memory to process arbitrary sequences of inputs. Early RNN models turned out to be very difficult to train, harder even than deep feedforward networks. The reason is the unstable gradient problem such as vanishing gradient and exploding gradient. The gradient can get smaller and smaller as it is propagated back through layers. This makes learning in early layers extremely slow. The problem actually gets worse in RNNs, since gradients aren't just propagated backward through layers, they're propagated backward through time. If the network runs for a long time, that can make the gradient extremely unstable and hard to learn from. It has been possible to incorporate an idea known as long short-term memory units (LSTMs) into RNNs. LSTMs make it much easier to get good results when training RNNs, and many recent papers make use of LSTMs or related ideas.

• 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.