• Journal of Intelligence and Information Systems
• /
• v.21 no.4
• /
• pp.37-51
• /
• 2015

Due to the development of internet technology and the rapid increase of internet data, various studies are actively conducted on how to use and analyze internet data for various purposes. In particular, in recent years, a number of studies have been performed on the applications of text mining techniques in order to overcome the limitations of the current application of structured data. Especially, there are various studies on sentimental analysis to score opinions based on the distribution of polarity such as positivity or negativity of vocabularies or sentences of the texts in documents. As a part of such studies, this study tries to predict ups and downs of stock prices of companies by performing sentimental analysis on news contexts of the particular companies in the Internet. A variety of news on companies is produced online by different economic agents, and it is diffused quickly and accessed easily in the Internet. So, based on inefficient market hypothesis, we can expect that news information of an individual company can be used to predict the fluctuations of stock prices of the company if we apply proper data analysis techniques. However, as the areas of corporate management activity are different, an analysis considering characteristics of each company is required in the analysis of text data based on machine-learning. In addition, since the news including positive or negative information on certain companies have various impacts on other companies or industry fields, an analysis for the prediction of the stock price of each company is necessary. Therefore, this study attempted to predict changes in the stock prices of the individual companies that applied a sentimental analysis of the online news data. Accordingly, this study chose top company in KOSPI 200 as the subjects of the analysis, and collected and analyzed online news data by each company produced for two years on a representative domestic search portal service, Naver. In addition, considering the differences in the meanings of vocabularies for each of the certain economic subjects, it aims to improve performance by building up a lexicon for each individual company and applying that to an analysis. As a result of the analysis, the accuracy of the prediction by each company are different, and the prediction accurate rate turned out to be 56% on average. Comparing the accuracy of the prediction of stock prices on industry sectors, 'energy/chemical', 'consumer goods for living' and 'consumer discretionary' showed a relatively higher accuracy of the prediction of stock prices than other industries, while it was found that the sectors such as 'information technology' and 'shipbuilding/transportation' industry had lower accuracy of prediction. The number of the representative companies in each industry collected was five each, so it is somewhat difficult to generalize, but it could be confirmed that there was a difference in the accuracy of the prediction of stock prices depending on industry sectors. In addition, at the individual company level, the companies such as 'Kangwon Land', 'KT & G' and 'SK Innovation' showed a relatively higher prediction accuracy as compared to other companies, while it showed that the companies such as 'Young Poong', 'LG', 'Samsung Life Insurance', and 'Doosan' had a low prediction accuracy of less than 50%. In this paper, we performed an analysis of the share price performance relative to the prediction of individual companies through the vocabulary of pre-built company to take advantage of the online news information. In this paper, we aim to improve performance of the stock prices prediction, applying online news information, through the stock price prediction of individual companies. Based on this, in the future, it will be possible to find ways to increase the stock price prediction accuracy by complementing the problem of unnecessary words that are added to the sentiment dictionary.

• Journal of Intelligence and Information Systems
• /
• v.21 no.2
• /
• pp.93-112
• /
• 2015

Depending on the change in consumer's consumption pattern, existing retail shop has evolved in hypermarket or convenience store offering grocery and daily products mostly. Therefore, it is important to maintain the inventory levels and proper product configuration for effectively utilize the limited space in the retail store and increasing sales. Accordingly, this study proposed proper product configuration and inventory level strategy based on RFM(Recency, Frequency, Monetary) model and SOM(self-organizing map) for manage the retail shop effectively. RFM model is analytic model to analyze customer behaviors based on the past customer's buying activities. And it can differentiates important customers from large data by three variables. R represents recency, which refers to the last purchase of commodities. The latest consuming customer has bigger R. F represents frequency, which refers to the number of transactions in a particular period and M represents monetary, which refers to consumption money amount in a particular period. Thus, RFM method has been known to be a very effective model for customer segmentation. In this study, using a normalized value of the RFM variables, SOM cluster analysis was performed. SOM is regarded as one of the most distinguished artificial neural network models in the unsupervised learning tool space. It is a popular tool for clustering and visualization of high dimensional data in such a way that similar items are grouped spatially close to one another. In particular, it has been successfully applied in various technical fields for finding patterns. In our research, the procedure tries to find sales patterns by analyzing product sales records with Recency, Frequency and Monetary values. And to suggest a business strategy, we conduct the decision tree based on SOM results. To validate the proposed procedure in this study, we adopted the M-mart data collected between 2014.01.01~2014.12.31. Each product get the value of R, F, M, and they are clustered by 9 using SOM. And we also performed three tests using the weekday data, weekend data, whole data in order to analyze the sales pattern change. In order to propose the strategy of each cluster, we examine the criteria of product clustering. The clusters through the SOM can be explained by the characteristics of these clusters of decision trees. As a result, we can suggest the inventory management strategy of each 9 clusters through the suggested procedures of the study. The highest of all three value(R, F, M) cluster's products need to have high level of the inventory as well as to be disposed in a place where it can be increasing customer's path. In contrast, the lowest of all three value(R, F, M) cluster's products need to have low level of inventory as well as to be disposed in a place where visibility is low. The highest R value cluster's products is usually new releases products, and need to be placed on the front of the store. And, manager should decrease inventory levels gradually in the highest F value cluster's products purchased in the past. Because, we assume that cluster has lower R value and the M value than the average value of good. And it can be deduced that product are sold poorly in recent days and total sales also will be lower than the frequency. The procedure presented in this study is expected to contribute to raising the profitability of the retail store. The paper is organized as follows. The second chapter briefly reviews the literature related to this study. The third chapter suggests procedures for research proposals, and the fourth chapter applied suggested procedure using the actual product sales data. Finally, the fifth chapter described the conclusion of the study and further research.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.101-124
• /
• 2018

Recently, most of the technologies have been developed in various forms through the advancement of single technology or interaction with other technologies. Particularly, these technologies have the characteristic of the convergence caused by the interaction between two or more techniques. In addition, efforts in responding to technological changes by advance are continuously increasing through forecasting promising convergence technologies that will emerge in the near future. According to this phenomenon, many researchers are attempting to perform various analyses about forecasting promising convergence technologies. A convergence technology has characteristics of various technologies according to the principle of generation. Therefore, forecasting promising convergence technologies is much more difficult than forecasting general technologies with high growth potential. Nevertheless, some achievements have been confirmed in an attempt to forecasting promising technologies using big data analysis and social network analysis. Studies of convergence technology through data analysis are actively conducted with the theme of discovering new convergence technologies and analyzing their trends. According that, information about new convergence technologies is being provided more abundantly than in the past. However, existing methods in analyzing convergence technology have some limitations. Firstly, most studies deal with convergence technology analyze data through predefined technology classifications. The technologies appearing recently tend to have characteristics of convergence and thus consist of technologies from various fields. In other words, the new convergence technologies may not belong to the defined classification. Therefore, the existing method does not properly reflect the dynamic change of the convergence phenomenon. Secondly, in order to forecast the promising convergence technologies, most of the existing analysis method use the general purpose indicators in process. This method does not fully utilize the specificity of convergence phenomenon. The new convergence technology is highly dependent on the existing technology, which is the origin of that technology. Based on that, it can grow into the independent field or disappear rapidly, according to the change of the dependent technology. In the existing analysis, the potential growth of convergence technology is judged through the traditional indicators designed from the general purpose. However, these indicators do not reflect the principle of convergence. In other words, these indicators do not reflect the characteristics of convergence technology, which brings the meaning of new technologies emerge through two or more mature technologies and grown technologies affect the creation of another technology. Thirdly, previous studies do not provide objective methods for evaluating the accuracy of models in forecasting promising convergence technologies. In the studies of convergence technology, the subject of forecasting promising technologies was relatively insufficient due to the complexity of the field. Therefore, it is difficult to find a method to evaluate the accuracy of the model that forecasting promising convergence technologies. In order to activate the field of forecasting promising convergence technology, it is important to establish a method for objectively verifying and evaluating the accuracy of the model proposed by each study. To overcome these limitations, we propose a new method for analysis of convergence technologies. First of all, through topic modeling, we derive a new technology classification in terms of text content. It reflects the dynamic change of the actual technology market, not the existing fixed classification standard. In addition, we identify the influence relationships between technologies through the topic correspondence weights of each document, and structuralize them into a network. In addition, we devise a centrality indicator (PGC, potential growth centrality) to forecast the future growth of technology by utilizing the centrality information of each technology. It reflects the convergence characteristics of each technology, according to technology maturity and interdependence between technologies. Along with this, we propose a method to evaluate the accuracy of forecasting model by measuring the growth rate of promising technology. It is based on the variation of potential growth centrality by period. In this paper, we conduct experiments with 13,477 patent documents dealing with technical contents to evaluate the performance and practical applicability of the proposed method. As a result, it is confirmed that the forecast model based on a centrality indicator of the proposed method has a maximum forecast accuracy of about 2.88 times higher than the accuracy of the forecast model based on the currently used network indicators.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.97-117
• /
• 2020

Product evaluation criteria is an indicator describing attributes or values of products, which enable users or manufacturers measure and understand the products. When companies analyze their products or compare them with competitors, appropriate criteria must be selected for objective evaluation. The criteria should show the features of products that consumers considered when they purchased, used and evaluated the products. However, current evaluation criteria do not reflect different consumers' opinion from product to product. Previous studies tried to used online reviews from e-commerce sites that reflect consumer opinions to extract the features and topics of products and use them as evaluation criteria. However, there is still a limit that they produce irrelevant criteria to products due to extracted or improper words are not refined. To overcome this limitation, this research suggests LDA-k-NN model which extracts possible criteria words from online reviews by using LDA and refines them with k-nearest neighbor. Proposed approach starts with preparation phase, which is constructed with 6 steps. At first, it collects review data from e-commerce websites. Most e-commerce websites classify their selling items by high-level, middle-level, and low-level categories. Review data for preparation phase are gathered from each middle-level category and collapsed later, which is to present single high-level category. Next, nouns, adjectives, adverbs, and verbs are extracted from reviews by getting part of speech information using morpheme analysis module. After preprocessing, words per each topic from review are shown with LDA and only nouns in topic words are chosen as potential words for criteria. Then, words are tagged based on possibility of criteria for each middle-level category. Next, every tagged word is vectorized by pre-trained word embedding model. Finally, k-nearest neighbor case-based approach is used to classify each word with tags. After setting up preparation phase, criteria extraction phase is conducted with low-level categories. This phase starts with crawling reviews in the corresponding low-level category. Same preprocessing as preparation phase is conducted using morpheme analysis module and LDA. Possible criteria words are extracted by getting nouns from the data and vectorized by pre-trained word embedding model. Finally, evaluation criteria are extracted by refining possible criteria words using k-nearest neighbor approach and reference proportion of each word in the words set. To evaluate the performance of the proposed model, an experiment was conducted with review on '11st', one of the biggest e-commerce companies in Korea. Review data were from 'Electronics/Digital' section, one of high-level categories in 11st. For performance evaluation of suggested model, three other models were used for comparing with the suggested model; actual criteria of 11st, a model that extracts nouns by morpheme analysis module and refines them according to word frequency, and a model that extracts nouns from LDA topics and refines them by word frequency. The performance evaluation was set to predict evaluation criteria of 10 low-level categories with the suggested model and 3 models above. Criteria words extracted from each model were combined into a single words set and it was used for survey questionnaires. In the survey, respondents chose every item they consider as appropriate criteria for each category. Each model got its score when chosen words were extracted from that model. The suggested model had higher scores than other models in 8 out of 10 low-level categories. By conducting paired t-tests on scores of each model, we confirmed that the suggested model shows better performance in 26 tests out of 30. In addition, the suggested model was the best model in terms of accuracy. This research proposes evaluation criteria extracting method that combines topic extraction using LDA and refinement with k-nearest neighbor approach. This method overcomes the limits of previous dictionary-based models and frequency-based refinement models. This study can contribute to improve review analysis for deriving business insights in e-commerce market.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.111-124
• /
• 2018

This study aims to develop a classification model for predicting the occurrence of hyperlipidemia, one of the chronic diseases. Prior studies applying data mining techniques for predicting disease can be classified into a model design study for predicting cardiovascular disease and a study comparing disease prediction research results. In the case of foreign literatures, studies predicting cardiovascular disease were predominant in predicting disease using data mining techniques. Although domestic studies were not much different from those of foreign countries, studies focusing on hypertension and diabetes were mainly conducted. Since hypertension and diabetes as well as chronic diseases, hyperlipidemia, are also of high importance, this study selected hyperlipidemia as the disease to be analyzed. We also developed a model for predicting hyperlipidemia using SVM and meta learning algorithms, which are already known to have excellent predictive power. In order to achieve the purpose of this study, we used data set from Korea Health Panel 2012. The Korean Health Panel produces basic data on the level of health expenditure, health level and health behavior, and has conducted an annual survey since 2008. In this study, 1,088 patients with hyperlipidemia were randomly selected from the hospitalized, outpatient, emergency, and chronic disease data of the Korean Health Panel in 2012, and 1,088 nonpatients were also randomly extracted. A total of 2,176 people were selected for the study. Three methods were used to select input variables for predicting hyperlipidemia. First, stepwise method was performed using logistic regression. Among the 17 variables, the categorical variables(except for length of smoking) are expressed as dummy variables, which are assumed to be separate variables on the basis of the reference group, and these variables were analyzed. Six variables (age, BMI, education level, marital status, smoking status, gender) excluding income level and smoking period were selected based on significance level 0.1. Second, C4.5 as a decision tree algorithm is used. The significant input variables were age, smoking status, and education level. Finally, C4.5 as a decision tree algorithm is used. In SVM, the input variables selected by genetic algorithms consisted of 6 variables such as age, marital status, education level, economic activity, smoking period, and physical activity status, and the input variables selected by genetic algorithms in artificial neural network consist of 3 variables such as age, marital status, and education level. Based on the selected parameters, we compared SVM, meta learning algorithm and other prediction models for hyperlipidemia patients, and compared the classification performances using TP rate and precision. The main results of the analysis are as follows. First, the accuracy of the SVM was 88.4% and the accuracy of the artificial neural network was 86.7%. Second, the accuracy of classification models using the selected input variables through stepwise method was slightly higher than that of classification models using the whole variables. Third, the precision of artificial neural network was higher than that of SVM when only three variables as input variables were selected by decision trees. As a result of classification models based on the input variables selected through the genetic algorithm, classification accuracy of SVM was 88.5% and that of artificial neural network was 87.9%. Finally, this study indicated that stacking as the meta learning algorithm proposed in this study, has the best performance when it uses the predicted outputs of SVM and MLP as input variables of SVM, which is a meta classifier. The purpose of this study was to predict hyperlipidemia, one of the representative chronic diseases. To do this, we used SVM and meta-learning algorithms, which is known to have high accuracy. As a result, the accuracy of classification of hyperlipidemia in the stacking as a meta learner was higher than other meta-learning algorithms. However, the predictive performance of the meta-learning algorithm proposed in this study is the same as that of SVM with the best performance (88.6%) among the single models. The limitations of this study are as follows. First, various variable selection methods were tried, but most variables used in the study were categorical dummy variables. In the case with a large number of categorical variables, the results may be different if continuous variables are used because the model can be better suited to categorical variables such as decision trees than general models such as neural networks. Despite these limitations, this study has significance in predicting hyperlipidemia with hybrid models such as met learning algorithms which have not been studied previously. It can be said that the result of improving the model accuracy by applying various variable selection techniques is meaningful. In addition, it is expected that our proposed model will be effective for the prevention and management of hyperlipidemia.

• Journal of Intelligence and Information Systems
• /
• v.20 no.3
• /
• pp.93-108
• /
• 2014

To support business decision making, interests and efforts to analyze and use transaction data in different perspectives are increasing. Such efforts are not only limited to customer management or marketing, but also used for monitoring and detecting fraud transactions. Fraud transactions are evolving into various patterns by taking advantage of information technology. To reflect the evolution of fraud transactions, there are many efforts on fraud detection methods and advanced application systems in order to improve the accuracy and ease of fraud detection. As a case of fraud detection, this study aims to provide effective fraud detection methods for auction exception agricultural products in the largest Korean agricultural wholesale market. Auction exception products policy exists to complement auction-based trades in agricultural wholesale market. That is, most trades on agricultural products are performed by auction; however, specific products are assigned as auction exception products when total volumes of products are relatively small, the number of wholesalers is small, or there are difficulties for wholesalers to purchase the products. However, auction exception products policy makes several problems on fairness and transparency of transaction, which requires help of fraud detection. In this study, to generate fraud detection rules, real huge agricultural products trade transaction data from 2008 to 2010 in the market are analyzed, which increase more than 1 million transactions and 1 billion US dollar in transaction volume. Agricultural transaction data has unique characteristics such as frequent changes in supply volumes and turbulent time-dependent changes in price. Since this was the first trial to identify fraud transactions in this domain, there was no training data set for supervised learning. So, fraud detection rules are generated using outlier detection approach. We assume that outlier transactions have more possibility of fraud transactions than normal transactions. The outlier transactions are identified to compare daily average unit price, weekly average unit price, and quarterly average unit price of product items. Also quarterly averages unit price of product items of the specific wholesalers are used to identify outlier transactions. The reliability of generated fraud detection rules are confirmed by domain experts. To determine whether a transaction is fraudulent or not, normal distribution and normalized Z-value concept are applied. That is, a unit price of a transaction is transformed to Z-value to calculate the occurrence probability when we approximate the distribution of unit prices to normal distribution. The modified Z-value of the unit price in the transaction is used rather than using the original Z-value of it. The reason is that in the case of auction exception agricultural products, Z-values are influenced by outlier fraud transactions themselves because the number of wholesalers is small. The modified Z-values are called Self-Eliminated Z-scores because they are calculated excluding the unit price of the specific transaction which is subject to check whether it is fraud transaction or not. To show the usefulness of the proposed approach, a prototype of fraud transaction detection system is developed using Delphi. The system consists of five main menus and related submenus. First functionalities of the system is to import transaction databases. Next important functions are to set up fraud detection parameters. By changing fraud detection parameters, system users can control the number of potential fraud transactions. Execution functions provide fraud detection results which are found based on fraud detection parameters. The potential fraud transactions can be viewed on screen or exported as files. The study is an initial trial to identify fraud transactions in Auction Exception Agricultural Products. There are still many remained research topics of the issue. First, the scope of analysis data was limited due to the availability of data. It is necessary to include more data on transactions, wholesalers, and producers to detect fraud transactions more accurately. Next, we need to extend the scope of fraud transaction detection to fishery products. Also there are many possibilities to apply different data mining techniques for fraud detection. For example, time series approach is a potential technique to apply the problem. Even though outlier transactions are detected based on unit prices of transactions, however it is possible to derive fraud detection rules based on transaction volumes.

• Journal of Intelligence and Information Systems
• /
• v.20 no.1
• /
• pp.49-65
• /
• 2014

Word of Mouth (WOM) is a behavior used by consumers to transfer or communicate their product or service experience to other consumers. Due to the popularity of social media such as Facebook, Twitter, blogs, and online communities, electronic WOM (e-WOM) has become important to the success of products or services. As a result, most enterprises pay close attention to e-WOM for their products or services. This is especially important for movies, as these are experiential products. This paper aims to identify the network factors of an online movie community that impact box office revenue using social network analysis. In addition to traditional WOM factors (volume and valence of WOM), network centrality measures of the online community are included as influential factors in box office revenue. Based on previous research results, we develop five hypotheses on the relationships between potential influential factors (WOM volume, WOM valence, degree centrality, betweenness centrality, closeness centrality) and box office revenue. The first hypothesis is that the accumulated volume of WOM in online product communities is positively related to the total revenue of movies. The second hypothesis is that the accumulated valence of WOM in online product communities is positively related to the total revenue of movies. The third hypothesis is that the average of degree centralities of reviewers in online product communities is positively related to the total revenue of movies. The fourth hypothesis is that the average of betweenness centralities of reviewers in online product communities is positively related to the total revenue of movies. The fifth hypothesis is that the average of betweenness centralities of reviewers in online product communities is positively related to the total revenue of movies. To verify our research model, we collect movie review data from the Internet Movie Database (IMDb), which is a representative online movie community, and movie revenue data from the Box-Office-Mojo website. The movies in this analysis include weekly top-10 movies from September 1, 2012, to September 1, 2013, with in total. We collect movie metadata such as screening periods and user ratings; and community data in IMDb including reviewer identification, review content, review times, responder identification, reply content, reply times, and reply relationships. For the same period, the revenue data from Box-Office-Mojo is collected on a weekly basis. Movie community networks are constructed based on reply relationships between reviewers. Using a social network analysis tool, NodeXL, we calculate the averages of three centralities including degree, betweenness, and closeness centrality for each movie. Correlation analysis of focal variables and the dependent variable (final revenue) shows that three centrality measures are highly correlated, prompting us to perform multiple regressions separately with each centrality measure. Consistent with previous research results, our regression analysis results show that the volume and valence of WOM are positively related to the final box office revenue of movies. Moreover, the averages of betweenness centralities from initial community networks impact the final movie revenues. However, both of the averages of degree centralities and closeness centralities do not influence final movie performance. Based on the regression results, three hypotheses, 1, 2, and 4, are accepted, and two hypotheses, 3 and 5, are rejected. This study tries to link the network structure of e-WOM on online product communities with the product's performance. Based on the analysis of a real online movie community, the results show that online community network structures can work as a predictor of movie performance. The results show that the betweenness centralities of the reviewer community are critical for the prediction of movie performance. However, degree centralities and closeness centralities do not influence movie performance. As future research topics, similar analyses are required for other product categories such as electronic goods and online content to generalize the study results.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.219-240
• /
• 2018

Sentiment analysis, which is one of the text mining techniques, is a method for extracting subjective content embedded in text documents. Recently, the sentiment analysis methods have been widely used in many fields. As good examples, data-driven surveys are based on analyzing the subjectivity of text data posted by users and market researches are conducted by analyzing users' review posts to quantify users' reputation on a target product. The basic method of sentiment analysis is to use sentiment dictionary (or lexicon), a list of sentiment vocabularies with positive, neutral, or negative semantics. In general, the meaning of many sentiment words is likely to be different across domains. For example, a sentiment word, 'sad' indicates negative meaning in many fields but a movie. In order to perform accurate sentiment analysis, we need to build the sentiment dictionary for a given domain. However, such a method of building the sentiment lexicon is time-consuming and various sentiment vocabularies are not included without the use of general-purpose sentiment lexicon. In order to address this problem, several studies have been carried out to construct the sentiment lexicon suitable for a specific domain based on 'OPEN HANGUL' and 'SentiWordNet', which are general-purpose sentiment lexicons. However, OPEN HANGUL is no longer being serviced and SentiWordNet does not work well because of language difference in the process of converting Korean word into English word. There are restrictions on the use of such general-purpose sentiment lexicons as seed data for building the sentiment lexicon for a specific domain. In this article, we construct 'KNU Korean Sentiment Lexicon (KNU-KSL)', a new general-purpose Korean sentiment dictionary that is more advanced than existing general-purpose lexicons. The proposed dictionary, which is a list of domain-independent sentiment words such as 'thank you', 'worthy', and 'impressed', is built to quickly construct the sentiment dictionary for a target domain. Especially, it constructs sentiment vocabularies by analyzing the glosses contained in Standard Korean Language Dictionary (SKLD) by the following procedures: First, we propose a sentiment classification model based on Bidirectional Long Short-Term Memory (Bi-LSTM). Second, the proposed deep learning model automatically classifies each of glosses to either positive or negative meaning. Third, positive words and phrases are extracted from the glosses classified as positive meaning, while negative words and phrases are extracted from the glosses classified as negative meaning. Our experimental results show that the average accuracy of the proposed sentiment classification model is up to 89.45%. In addition, the sentiment dictionary is more extended using various external sources including SentiWordNet, SenticNet, Emotional Verbs, and Sentiment Lexicon 0603. Furthermore, we add sentiment information about frequently used coined words and emoticons that are used mainly on the Web. The KNU-KSL contains a total of 14,843 sentiment vocabularies, each of which is one of 1-grams, 2-grams, phrases, and sentence patterns. Unlike existing sentiment dictionaries, it is composed of words that are not affected by particular domains. The recent trend on sentiment analysis is to use deep learning technique without sentiment dictionaries. The importance of developing sentiment dictionaries is declined gradually. However, one of recent studies shows that the words in the sentiment dictionary can be used as features of deep learning models, resulting in the sentiment analysis performed with higher accuracy (Teng, Z., 2016). This result indicates that the sentiment dictionary is used not only for sentiment analysis but also as features of deep learning models for improving accuracy. The proposed dictionary can be used as a basic data for constructing the sentiment lexicon of a particular domain and as features of deep learning models. It is also useful to automatically and quickly build large training sets for deep learning models.

• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.1-25
• /
• 2020

Sentiment Analysis (SA) is a Natural Language Processing (NLP) task that analyzes the sentiments consumers or the public feel about an arbitrary object from written texts. Furthermore, Aspect-Based Sentiment Analysis (ABSA) is a fine-grained analysis of the sentiments towards each aspect of an object. Since having a more practical value in terms of business, ABSA is drawing attention from both academic and industrial organizations. When there is a review that says "The restaurant is expensive but the food is really fantastic", for example, the general SA evaluates the overall sentiment towards the 'restaurant' as 'positive', while ABSA identifies the restaurant's aspect 'price' as 'negative' and 'food' aspect as 'positive'. Thus, ABSA enables a more specific and effective marketing strategy. In order to perform ABSA, it is necessary to identify what are the aspect terms or aspect categories included in the text, and judge the sentiments towards them. Accordingly, there exist four main areas in ABSA; aspect term extraction, aspect category detection, Aspect Term Sentiment Classification (ATSC), and Aspect Category Sentiment Classification (ACSC). It is usually conducted by extracting aspect terms and then performing ATSC to analyze sentiments for the given aspect terms, or by extracting aspect categories and then performing ACSC to analyze sentiments for the given aspect category. Here, an aspect category is expressed in one or more aspect terms, or indirectly inferred by other words. In the preceding example sentence, 'price' and 'food' are both aspect categories, and the aspect category 'food' is expressed by the aspect term 'food' included in the review. If the review sentence includes 'pasta', 'steak', or 'grilled chicken special', these can all be aspect terms for the aspect category 'food'. As such, an aspect category referred to by one or more specific aspect terms is called an explicit aspect. On the other hand, the aspect category like 'price', which does not have any specific aspect terms but can be indirectly guessed with an emotional word 'expensive,' is called an implicit aspect. So far, the 'aspect category' has been used to avoid confusion about 'aspect term'. From now on, we will consider 'aspect category' and 'aspect' as the same concept and use the word 'aspect' more for convenience. And one thing to note is that ATSC analyzes the sentiment towards given aspect terms, so it deals only with explicit aspects, and ACSC treats not only explicit aspects but also implicit aspects. This study seeks to find answers to the following issues ignored in the previous studies when applying the BERT pre-trained language model to ACSC and derives superior ACSC models. First, is it more effective to reflect the output vector of tokens for aspect categories than to use only the final output vector of [CLS] token as a classification vector? Second, is there any performance difference between QA (Question Answering) and NLI (Natural Language Inference) types in the sentence-pair configuration of input data? Third, is there any performance difference according to the order of sentence including aspect category in the QA or NLI type sentence-pair configuration of input data? To achieve these research objectives, we implemented 12 ACSC models and conducted experiments on 4 English benchmark datasets. As a result, ACSC models that provide performance beyond the existing studies without expanding the training dataset were derived. In addition, it was found that it is more effective to reflect the output vector of the aspect category token than to use only the output vector for the [CLS] token as a classification vector. It was also found that QA type input generally provides better performance than NLI, and the order of the sentence with the aspect category in QA type is irrelevant with performance. There may be some differences depending on the characteristics of the dataset, but when using NLI type sentence-pair input, placing the sentence containing the aspect category second seems to provide better performance. The new methodology for designing the ACSC model used in this study could be similarly applied to other studies such as ATSC.

• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.23-46
• /
• 2021

Collaborative filtering, which is often used in personalization recommendations, is recognized as a very useful technique to find similar customers and recommend products to them based on their purchase history. However, the traditional collaborative filtering technique has raised the question of having difficulty calculating the similarity for new customers or products due to the method of calculating similaritiesbased on direct connections and common features among customers. For this reason, a hybrid technique was designed to use content-based filtering techniques together. On the one hand, efforts have been made to solve these problems by applying the structural characteristics of social networks. This applies a method of indirectly calculating similarities through their similar customers placed between them. This means creating a customer's network based on purchasing data and calculating the similarity between the two based on the features of the network that indirectly connects the two customers within this network. Such similarity can be used as a measure to predict whether the target customer accepts recommendations. The centrality metrics of networks can be utilized for the calculation of these similarities. Different centrality metrics have important implications in that they may have different effects on recommended performance. In this study, furthermore, the effect of these centrality metrics on the performance of recommendation may vary depending on recommender algorithms. In addition, recommendation techniques using network analysis can be expected to contribute to increasing recommendation performance even if they apply not only to new customers or products but also to entire customers or products. By considering a customer's purchase of an item as a link generated between the customer and the item on the network, the prediction of user acceptance of recommendation is solved as a prediction of whether a new link will be created between them. As the classification models fit the purpose of solving the binary problem of whether the link is engaged or not, decision tree, k-nearest neighbors (KNN), logistic regression, artificial neural network, and support vector machine (SVM) are selected in the research. The data for performance evaluation used order data collected from an online shopping mall over four years and two months. Among them, the previous three years and eight months constitute social networks composed of and the experiment was conducted by organizing the data collected into the social network. The next four months' records were used to train and evaluate recommender models. Experiments with the centrality metrics applied to each model show that the recommendation acceptance rates of the centrality metrics are different for each algorithm at a meaningful level. In this work, we analyzed only four commonly used centrality metrics: degree centrality, betweenness centrality, closeness centrality, and eigenvector centrality. Eigenvector centrality records the lowest performance in all models except support vector machines. Closeness centrality and betweenness centrality show similar performance across all models. Degree centrality ranking moderate across overall models while betweenness centrality always ranking higher than degree centrality. Finally, closeness centrality is characterized by distinct differences in performance according to the model. It ranks first in logistic regression, artificial neural network, and decision tree withnumerically high performance. However, it only records very low rankings in support vector machine and K-neighborhood with low-performance levels. As the experiment results reveal, in a classification model, network centrality metrics over a subnetwork that connects the two nodes can effectively predict the connectivity between two nodes in a social network. Furthermore, each metric has a different performance depending on the classification model type. This result implies that choosing appropriate metrics for each algorithm can lead to achieving higher recommendation performance. In general, betweenness centrality can guarantee a high level of performance in any model. It would be possible to consider the introduction of proximity centrality to obtain higher performance for certain models.