• Asia pacific journal of information systems
• /
• v.19 no.2
• /
• pp.157-178
• /
• 2009

Corporate credit rating is a very important factor in the market for corporate debt. Information concerning corporate operations is often disseminated to market participants through the changes in credit ratings that are published by professional rating agencies, such as Standard and Poor's (S&P) and Moody's Investor Service. Since these agencies generally require a large fee for the service, and the periodically provided ratings sometimes do not reflect the default risk of the company at the time, it may be advantageous for bond-market participants to be able to classify credit ratings before the agencies actually publish them. As a result, it is very important for companies (especially, financial companies) to develop a proper model of credit rating. From a technical perspective, the credit rating constitutes a typical, multiclass, classification problem because rating agencies generally have ten or more categories of ratings. For example, S&P's ratings range from AAA for the highest-quality bonds to D for the lowest-quality bonds. The professional rating agencies emphasize the importance of analysts' subjective judgments in the determination of credit ratings. However, in practice, a mathematical model that uses the financial variables of companies plays an important role in determining credit ratings, since it is convenient to apply and cost efficient. These financial variables include the ratios that represent a company's leverage status, liquidity status, and profitability status. Several statistical and artificial intelligence (AI) techniques have been applied as tools for predicting credit ratings. Among them, artificial neural networks are most prevalent in the area of finance because of their broad applicability to many business problems and their preeminent ability to adapt. However, artificial neural networks also have many defects, including the difficulty in determining the values of the control parameters and the number of processing elements in the layer as well as the risk of over-fitting. Of late, because of their robustness and high accuracy, support vector machines (SVMs) have become popular as a solution for problems with generating accurate prediction. An SVM's solution may be globally optimal because SVMs seek to minimize structural risk. On the other hand, artificial neural network models may tend to find locally optimal solutions because they seek to minimize empirical risk. In addition, no parameters need to be tuned in SVMs, barring the upper bound for non-separable cases in linear SVMs. Since SVMs were originally devised for binary classification, however they are not intrinsically geared for multiclass classifications as in credit ratings. Thus, researchers have tried to extend the original SVM to multiclass classification. Hitherto, a variety of techniques to extend standard SVMs to multiclass SVMs (MSVMs) has been proposed in the literature Only a few types of MSVM are, however, tested using prior studies that apply MSVMs to credit ratings studies. In this study, we examined six different techniques of MSVMs: (1) One-Against-One, (2) One-Against-AIL (3) DAGSVM, (4) ECOC, (5) Method of Weston and Watkins, and (6) Method of Crammer and Singer. In addition, we examined the prediction accuracy of some modified version of conventional MSVM techniques. To find the most appropriate technique of MSVMs for corporate bond rating, we applied all the techniques of MSVMs to a real-world case of credit rating in Korea. The best application is in corporate bond rating, which is the most frequently studied area of credit rating for specific debt issues or other financial obligations. For our study the research data were collected from National Information and Credit Evaluation, Inc., a major bond-rating company in Korea. The data set is comprised of the bond-ratings for the year 2002 and various financial variables for 1,295 companies from the manufacturing industry in Korea. We compared the results of these techniques with one another, and with those of traditional methods for credit ratings, such as multiple discriminant analysis (MDA), multinomial logistic regression (MLOGIT), and artificial neural networks (ANNs). As a result, we found that DAGSVM with an ordered list was the best approach for the prediction of bond rating. In addition, we found that the modified version of ECOC approach can yield higher prediction accuracy for the cases showing clear patterns.

• Asia pacific journal of information systems
• /
• v.21 no.4
• /
• pp.1-25
• /
• 2011

Internet-based commerce has undergone an explosive growth over the past decade as consumers today find it more economical as well as more convenient to shop online. Nevertheless, the shift in the common mode of shopping from offline to online commerce has caused consumers to have worries over such issues as private information leakage, online fraud, discrepancy in product quality and grade, unsuccessful delivery, and so forth, Numerous studies have been undertaken to examine the role of perceived risk as a chief barrier to online purchases and to understand the theoretical relationships among perceived risk, trust and purchase intentions, However, most studies focus on empirically investigating the effects of trust on perceived risk, with little attention devoted to the effects of perceived risk on trust, While the influence trust has on perceived risk is worth studying, the influence in the opposite direction is equally important, enabling insights into the potential of perceived risk as a prohibitor of trust, According to Pavlou (2003), the primary source of the perceived risk is either the technological uncertainty of the Internet environment or the behavioral uncertainty of the transaction partner. Due to such types of uncertainty, an increase in the worries over the perceived risk may negatively affect trust, For example, if a consumer who sends sensitive transaction data over Internet is concerned that his or her private information may leak out because of the lack of security, trust may decrease (Olivero and Lunt, 2004), By the same token, if the consumer feels that the online merchant has the potential to profit by behaving in an opportunistic manner taking advantage of the remote, impersonal nature of online commerce, then it is unlikely that the merchant will be trusted, That is, the more the probable danger is likely to occur, the less trust and the greater need to control the transaction (Olivero and Lunt, 2004), In summary, a review of the related studies indicates that while some researchers looked at the influence of overall perceived risk on trust level, not much attention has been given to the effects of different types of perceived risk, In this context the present research aims at addressing the need to study how trust is affected by different types of perceived risk, We classified perceived risk into six different types based on the literature, and empirically analyzed the impact of each type of perceived risk upon consumer trust in an online merchant and further its impact upon purchase intentions. To meet our research objectives, we developed a conceptual model depicting the nomological structure of the relationships among our research variables, and also formulated a total of seven hypotheses. The model and hypotheses were tested using an empirical analysis based on a questionnaire survey of 206 college students. The reliability was evaluated via Cronbach's alphas, the minimum of which was found to be 0.73, and therefore the questionnaire items are all deemed reliable. In addition, the results of confirmatory factor analysis (CFA) designed to check the validity of the measurement model indicate that the convergent, discriminate, and nomological validities of the model are all acceptable. The structural equation modeling analysis to test the hypotheses yielded the following results. Of the first six hypotheses (H1-1 through H1-6) designed to examine the relationships between each risk type and trust, three hypotheses including H1-1 (performance risk ${\rightarrow}$ trust), H1-2 (psychological risk ${\rightarrow}$ trust) and H1-5 (online payment risk ${\rightarrow}$ trust) were supported with path coefficients of -0.30, -0.27 and -0.16 respectively. Finally, H2 (trust ${\rightarrow}$ purchase intentions) was supported with relatively high path coefficients of 0.73. Results of the empirical study offer the following findings and implications. First. it was found that it was performance risk, psychological risk and online payment risk that have a statistically significant influence upon consumer trust in an online merchant. It implies that a consumer may find an online merchant untrustworthy if either the product quality or the product grade does not match his or her expectations. For that reason, online merchants including digital storefronts and e-marketplaces are suggested to pursue a strategy focusing on identifying the target customers and offering products that they feel best meet performance and psychological needs of those customers. Thus, they should do their best to make it widely known that their products are of as good quality and grade as those purchased from offline department stores. In addition, it may be inferred that today's online consumers remain concerned about the security of the online commerce environment due to the repeated occurrences of hacking or private information leakage. Online merchants should take steps to remove potential vulnerabilities and provide online notices to emphasize that their website is secure. Second, consumer's overall trust was found to have a statistically significant influence on purchase intentions. This finding, which is consistent with the results of numerous prior studies, suggests that increased sales will become a reality only with enhanced consumer trust.

• Journal of Technology Innovation
• /
• v.20 no.2
• /
• pp.75-107
• /
• 2012

Previous researches on technological innovation have several limitations such as lack of general mechanism for technological innovation(inputs, throughputs and outputs of technological innovation), large company oriented studies, and ignoring importance of technology management capabilities. So, this study suggested a new model using resource-based theory and system theory, and empirically applied that to SMEs. Structural equation model analysis by using 223 SMEs in Daegu region provided a support for most of hypotheses. Research results showed that all of factors on technological innovation were significantly and positively related with each other: inputs(R&D leadership, innovation strategy, R&D investment, R&D human resource management, external network), throughputs(portfolio management, project management, technology commercialization) and output(technological innovation). In case of technological innovation inputs, R&D leadership influenced on innovation strategy positively and significantly. And R&D leadership and innovation strategy had positive and significant effects on R&D investment, R&D human resource management and external network. R&D human resource management and external network exerted positive and significant influences on technological innovation throughputs such as portfolio management and project management. But R&D investment did not significant impacts on technological innovation throughputs. Among technological innovation throughputs, both portfolio management and project management had positive and significant effect on technology commercialization. In addition, technology commercialization acted positively and significantly technological innovation output. This study suggests necessary of efforts to implement innovation strategy and manage R&D human resource effectively based on CEO's innovativeness and entrepreneurship. Also, if SMEs want to develop technology and commercialize it, they have to cooperate with external technology resources and informations. Research results revealed that proper level of R&D investment, internal and external communication, information sharing, and learning and cooperative culture were very important for improvement of technological innovation performance in SMEs. Especially, this research suggested that if SMEs manage technological innovation process effectively based on resource-based and system approaches, then they can overcome their resource limitations and gain high technological innovation performance. Also, useful policy support for technological innovation of central or regional government by this research model is important factor for SMEs' technological innovation performance.

• Management & Information Systems Review
• /
• v.32 no.5
• /
• pp.193-231
• /
• 2013

As developed IT, Word-of-Mouth(WOM) used varied terms as buzz marketing and viral marketing, and impressed that importance. Despite introduced new marketing tool on managers and professionals, online word-of-mouth including SNS lack of study on social network what based viral in marketing. In social network, patterns of relationship between individuals influence each other individual behaviors. Therefore this research grouped friendship-network and advice-network by characteristics, studied on trust of information source that antecedents of word-of-mouth in network. This study examined that affect- and cognition based trust affect WOM acceptance as WOM behaviors and examined effect of type of product as moderating variable. Additional this literature studied that WOM acceptance affect WOM recommend. To find the Influence of Trust on Word-of-Mouth Behaviors, a survey has done 206 samples(undergraduate students). The results of this study are as following : First, type of trust different friendship network and advice network. Affect-based trust is outstanding in friendship network than in advice network, while cognition-based trust stands out in advice network than another. Second, affect- and cognition based trust positive affect WOM acceptance. Contrary to expectations, what is preconceived trust in network have a similar effect for WOM acceptance regardless of type of trust. Third, WOM acceptance positive affect WOM recommend. Fourth, affect based trust affect WOM acceptance of hedonic product rather than utilitarian product. Upon especially in friendship network terms, affect-based trust has a more effect on WOM acceptance than cognition-based trust. This study has many implications. First, it is important that trust what have an influence WOM acceptance grouped affect- and cognition based trust. Second, it confirmed that trust is antecedents of positive WOM. Third, it is important that network grouped friendship network and advice-network by trust. Fourth, it gave managerial implications that they have to supply WOM through which network by type of product. We This study classified network and trust based on previous study. Then it examined relations between WOM behaviors. Further research could do enrich various things for example various age group, valence of message, quality of information.

• Journal of Venture Innovation
• /
• v.5 no.1
• /
• pp.19-37
• /
• 2022

The purpose of this study was to find out what could be the cause of increasing the re-use intention for the continuous management of customers in terms of finding a strategic plan for the survival of Medium Sized Hospital To this end, a hypothesis for the direct effect verifying the structural relationship, a hypothesis for the mediating effect of attachment, and a hypothesis for the moderating effect on the hospital image were presented. The survey analysis results for customers who experienced the services of 5 Medium Sized Hospital in Gyeonggi-do were as follows. First, The results of analysis of the effect of Medium Sized Hospital customers' perceived value on reuse intention are as follows. all sub-factors of perceived value did not have a significant effect on reuse intention. This is significant in that it shows that the change occurred due to the involvement of attachment. Second, the results of examining the mediating effect of attachment in the relationship between the perceived value of small and medium hospital customers and their intention to reuse are as follows. Attachment to doctor's competency significantly mediated the relationship between quality value and reuse intention, emotional value and reuse intention, and social value and reuse intention. Significantly mediated the relationship between the provinces and the relationship between the price value and the intention to reuse. Third, hospital image significantly adjusted the relationship between quality value and medical technology competency. Based on the above results, it is necessary to establish a strategy of value perceived by customers as a strategy to increase the reuse intention of small and medium hospital customers. Therefore, the strategic goal setting of this value should be 'promoting attachment', and since the hospital image adjusts the perceived value and attachment of small and medium hospital customers, it is an image strategy that allows customers to appreciate their attachment to doctors and medical technology more highly. will have to establish.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.18 no.5
• /
• pp.77-90
• /
• 2023

This study aims to investigate the potential of alternative credit assessment through Social Networking Sites (SNS) as a complementary tool to conventional loan review processes. It seeks to discern the impact of SNS usage characteristics and loan product attributes on credit loan repayment. To achieve this objective, we conducted a binomial logistic regression analysis examining the influence of SNS usage patterns, loan characteristics, and personal attributes on credit loan conditions, utilizing data from Company A's credit loan program, which integrates SNS data into its actual loan review processes. Our findings reveal several noteworthy insights. Firstly, with respect to profile photos that reflect users' personalities and individual characteristics, individuals who choose to upload photos directly connected to their personal lives, such as images of themselves, their private circles (e.g., family and friends), and photos depicting social activities like hobbies, which tend to be favored by individuals with extroverted tendencies, as well as character and humor-themed photos, which are typically favored by individuals with conscientious traits, demonstrate a higher propensity for diligently repaying credit loans. Conversely, the utilization of photos like landscapes or images concealing one's identity did not exhibit a statistically significant causal relationship with loan repayment. Furthermore, a positive correlation was observed between the extent of SNS usage and the likelihood of loan repayment. However, the level of SNS interaction did not exert a significant effect on the probability of loan repayment. This observation may be attributed to the passive nature of the interaction variable, which primarily involves expressing sympathy for other users' comments rather than generating original content. The study also unveiled the statistical significance of loan duration and the number of loans, representing key characteristics of loan portfolios, in influencing credit loan repayment. This underscores the importance of considering loan duration and the quantity of loans as crucial determinants in the design of microcredit products. Among the personal characteristic variables examined, only gender emerged as a significant factor. This implies that the loan program scrutinized in this analysis does not exhibit substantial discrimination based on age and credit scores, as its customer base predominantly consists of individuals in their twenties and thirties with low credit scores, who encounter challenges in securing loans from traditional financial institutions. This research stands out from prior studies by empirically exploring the relationship between SNS usage and credit loan repayment while incorporating variables not typically addressed in existing credit rating research, such as profile pictures. It underscores the significance of harnessing subjective, unstructured information from SNS for loan screening, offering the potential to mitigate the financial disadvantages faced by borrowers with low credit scores or those ensnared in short-term liquidity constraints due to limited credit history a group often referred to as "thin filers." By utilizing such information, these individuals can potentially reduce their credit costs, whereas they are supposed to accrue a more substantial financial history through credit transactions under conventional credit assessment system.

• Journal of Intelligence and Information Systems
• /
• v.18 no.3
• /
• pp.79-96
• /
• 2012

As the pace of competition dramatically accelerates and the complexity of change grows, a variety of research have been conducted to improve firms' short-term performance and to enhance firms' long-term survival. In particular, researchers and practitioners have paid their attention to identify promising technologies that lead competitive advantage to a firm. Discovery of promising technology depends on how a firm evaluates the value of technologies, thus many evaluating methods have been proposed. Experts' opinion based approaches have been widely accepted to predict the value of technologies. Whereas this approach provides in-depth analysis and ensures validity of analysis results, it is usually cost-and time-ineffective and is limited to qualitative evaluation. Considerable studies attempt to forecast the value of technology by using patent information to overcome the limitation of experts' opinion based approach. Patent based technology evaluation has served as a valuable assessment approach of the technological forecasting because it contains a full and practical description of technology with uniform structure. Furthermore, it provides information that is not divulged in any other sources. Although patent information based approach has contributed to our understanding of prediction of promising technologies, it has some limitations because prediction has been made based on the past patent information, and the interpretations of patent analyses are not consistent. In order to fill this gap, this study proposes a technology forecasting methodology by integrating patent information approach and artificial intelligence method. The methodology consists of three modules : evaluation of technologies promising, implementation of technologies value prediction model, and recommendation of promising technologies. In the first module, technologies promising is evaluated from three different and complementary dimensions; impact, fusion, and diffusion perspectives. The impact of technologies refers to their influence on future technologies development and improvement, and is also clearly associated with their monetary value. The fusion of technologies denotes the extent to which a technology fuses different technologies, and represents the breadth of search underlying the technology. The fusion of technologies can be calculated based on technology or patent, thus this study measures two types of fusion index; fusion index per technology and fusion index per patent. Finally, the diffusion of technologies denotes their degree of applicability across scientific and technological fields. In the same vein, diffusion index per technology and diffusion index per patent are considered respectively. In the second module, technologies value prediction model is implemented using artificial intelligence method. This studies use the values of five indexes (i.e., impact index, fusion index per technology, fusion index per patent, diffusion index per technology and diffusion index per patent) at different time (e.g., t-n, t-n-1, t-n-2, ${\cdots}$) as input variables. The out variables are values of five indexes at time t, which is used for learning. The learning method adopted in this study is backpropagation algorithm. In the third module, this study recommends final promising technologies based on analytic hierarchy process. AHP provides relative importance of each index, leading to final promising index for technology. Applicability of the proposed methodology is tested by using U.S. patents in international patent class G06F (i.e., electronic digital data processing) from 2000 to 2008. The results show that mean absolute error value for prediction produced by the proposed methodology is lower than the value produced by multiple regression analysis in cases of fusion indexes. However, mean absolute error value of the proposed methodology is slightly higher than the value of multiple regression analysis. These unexpected results may be explained, in part, by small number of patents. Since this study only uses patent data in class G06F, number of sample patent data is relatively small, leading to incomplete learning to satisfy complex artificial intelligence structure. In addition, fusion index per technology and impact index are found to be important criteria to predict promising technology. This study attempts to extend the existing knowledge by proposing a new methodology for prediction technology value by integrating patent information analysis and artificial intelligence network. It helps managers who want to technology develop planning and policy maker who want to implement technology policy by providing quantitative prediction methodology. In addition, this study could help other researchers by proving a deeper understanding of the complex technological forecasting field.

• Journal of Intelligence and Information Systems
• /
• v.22 no.3
• /
• pp.165-183
• /
• 2016

Over the past decade, there has been a rapid diffusion of technological devices and a rising number of various devices, resulting in an escalation of virtual reality technology. Technological market has rapidly been changed from smartphone to wearable devices based on virtual reality. Virtual reality can make users feel real situation through sensing interaction, voice, motion capture and so on. Facebook.com, Google, Samsung, LG, Sony and so on have investigated developing platform of virtual reality. the pricing of virtual reality devices also had decreased into 30% from their launched period. Thus market infrastructure in virtual reality have rapidly been developed to crease marketplace. However, most consumers recognize that virtual reality is not ease to purchase or use. That could not lead consumers to positive attitude for devices and purchase the related devices in the early market. Through previous studies related to virtual reality, there are few studies focusing on why the devices for virtual reality stayed in early stage in adoption & diffusion context in the market. Almost previous studies considered the reasons of hard adoption for innovative products in the viewpoints of Typology of Innovation Resistance, MIR(Management of Innovation Resistant), UTAUT & UTAUT2. However, product-based antecedents also important to increase user intention to purchase and use products in the technological market. In this study, we focus on user acceptance and resistance for increasing purchase and usage promotions of wearable devices related to virtual reality based on headgear products like Galaxy Gear. Especially, we added a variables like attitude confidence as a dimension for user resistance. The research questions of this study are follows. First, how attitude confidence and innovativeness resistance affect user intention to use? Second, What factors related to content and brand contexts can affect user intention to use? This research collected data from the participants who have experiences using virtual rality headgears aged between 20s to 50s located in South Korea. In order to collect data, this study used a pilot test and through making face-to-face interviews on three specialists, face validity and content validity were evaluated for the questionnaire validity. Cleansing the data, we dropped some outliers and data of irrelevant papers. Totally, 156 responses were used for testing the suggested hypotheses. Through collecting data, demographics and the relationships among variables were analyzed through conducting structural equation modeling by PLS. The data showed that the sex of respondents who have experience using social commerce sites (male=86(55.1%), female=70(44.9%). The ages of respondents are mostly from 20s (74.4%) to 30s (16.7%). 126 respondents (80.8%) have used virtual reality devices. The results of our model estimation are as follows. With the exception of Hypothesis 1 and 7, which deals with the two relationships between brand awareness to attitude confidence, and quality of content to perceived enjoyment, all of our hypotheses were supported. In compliance with our hypotheses, perceived ease of use (H2) and use innovativeness (H3) were supported with its positively influence for the attitude confidence. This finding indicates that the more ease of use and innovativeness for devices increased, the more users' attitude confidence increased. Perceived price (H4), enjoyment (H5), Quantity of contents (H6) significantly increase user resistance. However, perceived price positively affect user innovativeness resistance meanwhile perceived enjoyment and quantity of contents negatively affect user innovativeness resistance. In addition, aesthetic exterior (H6) was also positively associated with perceived price (p<0.01). Also projection quality (H8) can increase perceived enjoyment (p<0.05). Finally, attitude confidence (H10) increased user intention to use virtual reality devices. however user resistance (H11) negatively affect user intention to use virtual reality devices. The findings of this study show that attitude confidence and user innovativeness resistance differently influence customer intention for using virtual reality devices. There are two distinct characteristic of attitude confidence: perceived ease of use and user innovativeness. This study identified the antecedents of different roles of perceived price (aesthetic exterior) and perceived enjoyment (quality of contents & projection quality). The findings indicated that brand awareness and quality of contents for virtual reality is not formed within virtual reality market yet. Therefore, firms should developed brand awareness for their product in the virtual market to increase market share.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.47-73
• /
• 2020

KTX rolling stocks are a system consisting of several machines, electrical devices, and components. The maintenance of the rolling stocks requires considerable expertise and experience of maintenance workers. In the event of a rolling stock failure, the knowledge and experience of the maintainer will result in a difference in the quality of the time and work to solve the problem. So, the resulting availability of the vehicle will vary. Although problem solving is generally based on fault manuals, experienced and skilled professionals can quickly diagnose and take actions by applying personal know-how. Since this knowledge exists in a tacit form, it is difficult to pass it on completely to a successor, and there have been studies that have developed a case-based rolling stock expert system to turn it into a data-driven one. Nonetheless, research on the most commonly used KTX rolling stock on the main-line or the development of a system that extracts text meanings and searches for similar cases is still lacking. Therefore, this study proposes an intelligence supporting system that provides an action guide for emerging failures by using the know-how of these rolling stocks maintenance experts as an example of problem solving. For this purpose, the case base was constructed by collecting the rolling stocks failure data generated from 2015 to 2017, and the integrated dictionary was constructed separately through the case base to include the essential terminology and failure codes in consideration of the specialty of the railway rolling stock sector. Based on a deployed case base, a new failure was retrieved from past cases and the top three most similar failure cases were extracted to propose the actual actions of these cases as a diagnostic guide. In this study, various dimensionality reduction measures were applied to calculate similarity by taking into account the meaningful relationship of failure details in order to compensate for the limitations of the method of searching cases by keyword matching in rolling stock failure expert system studies using case-based reasoning in the precedent case-based expert system studies, and their usefulness was verified through experiments. Among the various dimensionality reduction techniques, similar cases were retrieved by applying three algorithms: Non-negative Matrix Factorization(NMF), Latent Semantic Analysis(LSA), and Doc2Vec to extract the characteristics of the failure and measure the cosine distance between the vectors. The precision, recall, and F-measure methods were used to assess the performance of the proposed actions. To compare the performance of dimensionality reduction techniques, the analysis of variance confirmed that the performance differences of the five algorithms were statistically significant, with a comparison between the algorithm that randomly extracts failure cases with identical failure codes and the algorithm that applies cosine similarity directly based on words. In addition, optimal techniques were derived for practical application by verifying differences in performance depending on the number of dimensions for dimensionality reduction. The analysis showed that the performance of the cosine similarity was higher than that of the dimension using Non-negative Matrix Factorization(NMF) and Latent Semantic Analysis(LSA) and the performance of algorithm using Doc2Vec was the highest. Furthermore, in terms of dimensionality reduction techniques, the larger the number of dimensions at the appropriate level, the better the performance was found. Through this study, we confirmed the usefulness of effective methods of extracting characteristics of data and converting unstructured data when applying case-based reasoning based on which most of the attributes are texted in the special field of KTX rolling stock. Text mining is a trend where studies are being conducted for use in many areas, but studies using such text data are still lacking in an environment where there are a number of specialized terms and limited access to data, such as the one we want to use in this study. In this regard, it is significant that the study first presented an intelligent diagnostic system that suggested action by searching for a case by applying text mining techniques to extract the characteristics of the failure to complement keyword-based case searches. It is expected that this will provide implications as basic study for developing diagnostic systems that can be used immediately on the site.

• Journal of Intelligence and Information Systems
• /
• v.25 no.4
• /
• pp.141-154
• /
• 2019

Rapid growth of internet technology and social media is progressing. Data mining technology has evolved to enable unstructured document representations in a variety of applications. Sentiment analysis is an important technology that can distinguish poor or high-quality content through text data of products, and it has proliferated during text mining. Sentiment analysis mainly analyzes people's opinions in text data by assigning predefined data categories as positive and negative. This has been studied in various directions in terms of accuracy from simple rule-based to dictionary-based approaches using predefined labels. In fact, sentiment analysis is one of the most active researches in natural language processing and is widely studied in text mining. When real online reviews aren't available for others, it's not only easy to openly collect information, but it also affects your business. In marketing, real-world information from customers is gathered on websites, not surveys. Depending on whether the website's posts are positive or negative, the customer response is reflected in the sales and tries to identify the information. However, many reviews on a website are not always good, and difficult to identify. The earlier studies in this research area used the reviews data of the Amazon.com shopping mal, but the research data used in the recent studies uses the data for stock market trends, blogs, news articles, weather forecasts, IMDB, and facebook etc. However, the lack of accuracy is recognized because sentiment calculations are changed according to the subject, paragraph, sentiment lexicon direction, and sentence strength. This study aims to classify the polarity analysis of sentiment analysis into positive and negative categories and increase the prediction accuracy of the polarity analysis using the pretrained IMDB review data set. First, the text classification algorithm related to sentiment analysis adopts the popular machine learning algorithms such as NB (naive bayes), SVM (support vector machines), XGboost, RF (random forests), and Gradient Boost as comparative models. Second, deep learning has demonstrated discriminative features that can extract complex features of data. Representative algorithms are CNN (convolution neural networks), RNN (recurrent neural networks), LSTM (long-short term memory). CNN can be used similarly to BoW when processing a sentence in vector format, but does not consider sequential data attributes. RNN can handle well in order because it takes into account the time information of the data, but there is a long-term dependency on memory. To solve the problem of long-term dependence, LSTM is used. For the comparison, CNN and LSTM were chosen as simple deep learning models. In addition to classical machine learning algorithms, CNN, LSTM, and the integrated models were analyzed. Although there are many parameters for the algorithms, we examined the relationship between numerical value and precision to find the optimal combination. And, we tried to figure out how the models work well for sentiment analysis and how these models work. This study proposes integrated CNN and LSTM algorithms to extract the positive and negative features of text analysis. The reasons for mixing these two algorithms are as follows. CNN can extract features for the classification automatically by applying convolution layer and massively parallel processing. LSTM is not capable of highly parallel processing. Like faucets, the LSTM has input, output, and forget gates that can be moved and controlled at a desired time. These gates have the advantage of placing memory blocks on hidden nodes. The memory block of the LSTM may not store all the data, but it can solve the CNN's long-term dependency problem. Furthermore, when LSTM is used in CNN's pooling layer, it has an end-to-end structure, so that spatial and temporal features can be designed simultaneously. In combination with CNN-LSTM, 90.33% accuracy was measured. This is slower than CNN, but faster than LSTM. The presented model was more accurate than other models. In addition, each word embedding layer can be improved when training the kernel step by step. CNN-LSTM can improve the weakness of each model, and there is an advantage of improving the learning by layer using the end-to-end structure of LSTM. Based on these reasons, this study tries to enhance the classification accuracy of movie reviews using the integrated CNN-LSTM model.