• 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.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.39-70
• /
• 2017

Data-drive analytics techniques have been recently applied to public surveys. Instead of simply gathering survey results or expert opinions to research the preference for a recently launched product, enterprises need a way to collect and analyze various types of online data and then accurately figure out customer preferences. In the main concept of existing data-based survey methods, the sentiment lexicon for a particular domain is first constructed by domain experts who usually judge the positive, neutral, or negative meanings of the frequently used words from the collected text documents. In order to research the preference for a particular product, the existing approach collects (1) review posts, which are related to the product, from several product review web sites; (2) extracts sentences (or phrases) in the collection after the pre-processing step such as stemming and removal of stop words is performed; (3) classifies the polarity (either positive or negative sense) of each sentence (or phrase) based on the sentiment lexicon; and (4) estimates the positive and negative ratios of the product by dividing the total numbers of the positive and negative sentences (or phrases) by the total number of the sentences (or phrases) in the collection. Furthermore, the existing approach automatically finds important sentences (or phrases) including the positive and negative meaning to/against the product. As a motivated example, given a product like Sonata made by Hyundai Motors, customers often want to see the summary note including what positive points are in the 'car design' aspect as well as what negative points are in thesame aspect. They also want to gain more useful information regarding other aspects such as 'car quality', 'car performance', and 'car service.' Such an information will enable customers to make good choice when they attempt to purchase brand-new vehicles. In addition, automobile makers will be able to figure out the preference and positive/negative points for new models on market. In the near future, the weak points of the models will be improved by the sentiment analysis. For this, the existing approach computes the sentiment score of each sentence (or phrase) and then selects top-k sentences (or phrases) with the highest positive and negative scores. However, the existing approach has several shortcomings and is limited to apply to real applications. The main disadvantages of the existing approach is as follows: (1) The main aspects (e.g., car design, quality, performance, and service) to a product (e.g., Hyundai Sonata) are not considered. Through the sentiment analysis without considering aspects, as a result, the summary note including the positive and negative ratios of the product and top-k sentences (or phrases) with the highest sentiment scores in the entire corpus is just reported to customers and car makers. This approach is not enough and main aspects of the target product need to be considered in the sentiment analysis. (2) In general, since the same word has different meanings across different domains, the sentiment lexicon which is proper to each domain needs to be constructed. The efficient way to construct the sentiment lexicon per domain is required because the sentiment lexicon construction is labor intensive and time consuming. To address the above problems, in this article, we propose a novel product reputation mining algorithm that (1) extracts topics hidden in review documents written by customers; (2) mines main aspects based on the extracted topics; (3) measures the positive and negative ratios of the product using the aspects; and (4) presents the digest in which a few important sentences with the positive and negative meanings are listed in each aspect. Unlike the existing approach, using hidden topics makes experts construct the sentimental lexicon easily and quickly. Furthermore, reinforcing topic semantics, we can improve the accuracy of the product reputation mining algorithms more largely than that of the existing approach. In the experiments, we collected large review documents to the domestic vehicles such as K5, SM5, and Avante; measured the positive and negative ratios of the three cars; showed top-k positive and negative summaries per aspect; and conducted statistical analysis. Our experimental results clearly show the effectiveness of the proposed method, compared with the existing method.

• Progress in Medical Physics
• /
• v.14 no.1
• /
• pp.34-42
• /
• 2003

In medical imaging, three-dimensional (3D) display using Virtual Reality Modeling Language (VRML) as a portable file format can give intuitive information more efficiently on the World Wide Web (WWW). The web-based 3D visualization of functional images combined with anatomical images has not studied much in systematic ways. The goal of this study was to achieve a simultaneous observation of 3D anatomic and functional models with planar images on the WWW, providing their locational information in 3D space with a measuring implement using VRML. MRI and ictal-interictal SPECT images were obtained from one epileptic patient. Subtraction ictal SPECT co-registered to MRI (SISCOM) was performed to improve identification of a seizure focus. SISCOM image volumes were held by thresholds above one standard deviation (1-SD) and two standard deviations (2-SD). SISCOM foci and boundaries of gray matter, white matter, and cerebrospinal fluid (CSF) in the MRI volume were segmented and rendered to VRML polygonal surfaces by marching cube algorithm. Line profiles of x and y-axis that represent real lengths on an image were acquired and their maximum lengths were the same as 211.67 mm. The real size vs. the rendered VRML surface size was approximately the ratio of 1 to 605.9. A VRML measuring tool was made and merged with previous VRML surfaces. User interface tools were embedded with Java Script routines to display MRI planar images as cross sections of 3D surface models and to set transparencies of 3D surface models. When transparencies of 3D surface models were properly controlled, a fused display of the brain geometry with 3D distributions of focal activated regions provided intuitively spatial correlations among three 3D surface models. The epileptic seizure focus was in the right temporal lobe of the brain. The real position of the seizure focus could be verified by the VRML measuring tool and the anatomy corresponding to the seizure focus could be confirmed by MRI planar images crossing 3D surface models. The VRML application developed in this study may have several advantages. Firstly, 3D fused display and control of anatomic and functional image were achieved on the m. Secondly, the vector analysis of a 3D surface model was defined by the VRML measuring tool based on the real size. Finally, the anatomy corresponding to the seizure focus was intuitively detected by correlations with MRI images. Our web based visualization of 3-D fusion image and its localization will be a help to online research and education in diagnostic radiology, therapeutic radiology, and surgery applications.

• Journal of Intelligence and Information Systems
• /
• v.20 no.2
• /
• pp.93-107
• /
• 2014

In this paper, we report what we have observed with regard to user-perspective issue clustering based on multi-layered two-mode network analysis. This work is significant in the context of data collection by companies about customer needs. Most companies have failed to uncover such needs for products or services properly in terms of demographic data such as age, income levels, and purchase history. Because of excessive reliance on limited internal data, most recommendation systems do not provide decision makers with appropriate business information for current business circumstances. However, part of the problem is the increasing regulation of personal data gathering and privacy. This makes demographic or transaction data collection more difficult, and is a significant hurdle for traditional recommendation approaches because these systems demand a great deal of personal data or transaction logs. Our motivation for presenting this paper to academia is our strong belief, and evidence, that most customers' requirements for products can be effectively and efficiently analyzed from unstructured textual data such as Internet news text. In order to derive users' requirements from textual data obtained online, the proposed approach in this paper attempts to construct double two-mode networks, such as a user-news network and news-issue network, and to integrate these into one quasi-network as the input for issue clustering. One of the contributions of this research is the development of a methodology utilizing enormous amounts of unstructured textual data for user-oriented issue clustering by leveraging existing text mining and social network analysis. In order to build multi-layered two-mode networks of news logs, we need some tools such as text mining and topic analysis. We used not only SAS Enterprise Miner 12.1, which provides a text miner module and cluster module for textual data analysis, but also NetMiner 4 for network visualization and analysis. Our approach for user-perspective issue clustering is composed of six main phases: crawling, topic analysis, access pattern analysis, network merging, network conversion, and clustering. In the first phase, we collect visit logs for news sites by crawler. After gathering unstructured news article data, the topic analysis phase extracts issues from each news article in order to build an article-news network. For simplicity, 100 topics are extracted from 13,652 articles. In the third phase, a user-article network is constructed with access patterns derived from web transaction logs. The double two-mode networks are then merged into a quasi-network of user-issue. Finally, in the user-oriented issue-clustering phase, we classify issues through structural equivalence, and compare these with the clustering results from statistical tools and network analysis. An experiment with a large dataset was performed to build a multi-layer two-mode network. After that, we compared the results of issue clustering from SAS with that of network analysis. The experimental dataset was from a web site ranking site, and the biggest portal site in Korea. The sample dataset contains 150 million transaction logs and 13,652 news articles of 5,000 panels over one year. User-article and article-issue networks are constructed and merged into a user-issue quasi-network using Netminer. Our issue-clustering results applied the Partitioning Around Medoids (PAM) algorithm and Multidimensional Scaling (MDS), and are consistent with the results from SAS clustering. In spite of extensive efforts to provide user information with recommendation systems, most projects are successful only when companies have sufficient data about users and transactions. Our proposed methodology, user-perspective issue clustering, can provide practical support to decision-making in companies because it enhances user-related data from unstructured textual data. To overcome the problem of insufficient data from traditional approaches, our methodology infers customers' real interests by utilizing web transaction logs. In addition, we suggest topic analysis and issue clustering as a practical means of issue identification.

• Journal of Intelligence and Information Systems
• /
• v.21 no.1
• /
• pp.119-142
• /
• 2015

With the explosive growth in the volume of information, Internet users are experiencing considerable difficulties in obtaining necessary information online. Against this backdrop, ever-greater importance is being placed on a recommender system that provides information catered to user preferences and tastes in an attempt to address issues associated with information overload. To this end, a number of techniques have been proposed, including content-based filtering (CBF), demographic filtering (DF) and collaborative filtering (CF). Among them, CBF and DF require external information and thus cannot be applied to a variety of domains. CF, on the other hand, is widely used since it is relatively free from the domain constraint. The CF technique is broadly classified into memory-based CF, model-based CF and hybrid CF. Model-based CF addresses the drawbacks of CF by considering the Bayesian model, clustering model or dependency network model. This filtering technique not only improves the sparsity and scalability issues but also boosts predictive performance. However, it involves expensive model-building and results in a tradeoff between performance and scalability. Such tradeoff is attributed to reduced coverage, which is a type of sparsity issues. In addition, expensive model-building may lead to performance instability since changes in the domain environment cannot be immediately incorporated into the model due to high costs involved. Cumulative changes in the domain environment that have failed to be reflected eventually undermine system performance. This study incorporates the Markov model of transition probabilities and the concept of fuzzy clustering with CBCF to propose predictive clustering-based CF (PCCF) that solves the issues of reduced coverage and of unstable performance. The method improves performance instability by tracking the changes in user preferences and bridging the gap between the static model and dynamic users. Furthermore, the issue of reduced coverage also improves by expanding the coverage based on transition probabilities and clustering probabilities. The proposed method consists of four processes. First, user preferences are normalized in preference clustering. Second, changes in user preferences are detected from review score entries during preference transition detection. Third, user propensities are normalized using patterns of changes (propensities) in user preferences in propensity clustering. Lastly, the preference prediction model is developed to predict user preferences for items during preference prediction. The proposed method has been validated by testing the robustness of performance instability and scalability-performance tradeoff. The initial test compared and analyzed the performance of individual recommender systems each enabled by IBCF, CBCF, ICFEC and PCCF under an environment where data sparsity had been minimized. The following test adjusted the optimal number of clusters in CBCF, ICFEC and PCCF for a comparative analysis of subsequent changes in the system performance. The test results revealed that the suggested method produced insignificant improvement in performance in comparison with the existing techniques. In addition, it failed to achieve significant improvement in the standard deviation that indicates the degree of data fluctuation. Notwithstanding, it resulted in marked improvement over the existing techniques in terms of range that indicates the level of performance fluctuation. The level of performance fluctuation before and after the model generation improved by 51.31% in the initial test. Then in the following test, there has been 36.05% improvement in the level of performance fluctuation driven by the changes in the number of clusters. This signifies that the proposed method, despite the slight performance improvement, clearly offers better performance stability compared to the existing techniques. Further research on this study will be directed toward enhancing the recommendation performance that failed to demonstrate significant improvement over the existing techniques. The future research will consider the introduction of a high-dimensional parameter-free clustering algorithm or deep learning-based model in order to improve performance in recommendations.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.1-17
• /
• 2023

With the recent rapid development of ICT(Information and Communication Technology) and the popularization of digital devices, the size of the online market continues to grow. As a result, we live in a flood of information. Thus, customers are facing information overload problems that require a lot of time and money to select products. Therefore, a personalized recommender system has become an essential methodology to address such issues. Collaborative Filtering(CF) is the most widely used recommender system. Traditional recommender systems mainly utilize quantitative data such as rating values, resulting in poor recommendation accuracy. Quantitative data cannot fully reflect the user's preference. To solve such a problem, studies that reflect qualitative data, such as review contents, are being actively conducted these days. To quantify user review contents, text mining was used in this study. The general CF consists of the following three steps: user-item matrix generation, Top-N neighborhood group search, and Top-K recommendation list generation. In this study, we propose a recommendation algorithm that applies an extended similarity measure, which utilize quantified review contents in addition to user rating values. After calculating review similarity by applying TF-IDF, Word2Vec, and Doc2Vec techniques to review content, extended similarity is created by combining user rating similarity and quantified review contents. To verify this, we used user ratings and review data from the e-commerce site Amazon's "Health and Personal Care". The proposed recommendation model using extended similarity measure showed superior performance to the traditional recommendation model using only user rating value-based similarity measure. In addition, among the various text mining techniques, the similarity obtained using the TF-IDF technique showed the best performance when used in the neighbor group search and recommendation list generation step.

• Journal of Intelligence and Information Systems
• /
• v.19 no.3
• /
• pp.1-23
• /
• 2013

To discover significant social issues such as unemployment, economy crisis, social welfare etc. that are urgent issues to be solved in a modern society, in the existing approach, researchers usually collect opinions from professional experts and scholars through either online or offline surveys. However, such a method does not seem to be effective from time to time. As usual, due to the problem of expense, a large number of survey replies are seldom gathered. In some cases, it is also hard to find out professional persons dealing with specific social issues. Thus, the sample set is often small and may have some bias. Furthermore, regarding a social issue, several experts may make totally different conclusions because each expert has his subjective point of view and different background. In this case, it is considerably hard to figure out what current social issues are and which social issues are really important. To surmount the shortcomings of the current approach, in this paper, we develop a prototype system that semi-automatically detects social issue keywords representing social issues and problems from about 1.3 million news articles issued by about 10 major domestic presses in Korea from June 2009 until July 2012. Our proposed system consists of (1) collecting and extracting texts from the collected news articles, (2) identifying only news articles related to social issues, (3) analyzing the lexical items of Korean sentences, (4) finding a set of topics regarding social keywords over time based on probabilistic topic modeling, (5) matching relevant paragraphs to a given topic, and (6) visualizing social keywords for easy understanding. In particular, we propose a novel matching algorithm relying on generative models. The goal of our proposed matching algorithm is to best match paragraphs to each topic. Technically, using a topic model such as Latent Dirichlet Allocation (LDA), we can obtain a set of topics, each of which has relevant terms and their probability values. In our problem, given a set of text documents (e.g., news articles), LDA shows a set of topic clusters, and then each topic cluster is labeled by human annotators, where each topic label stands for a social keyword. For example, suppose there is a topic (e.g., Topic1 = {(unemployment, 0.4), (layoff, 0.3), (business, 0.3)}) and then a human annotator labels "Unemployment Problem" on Topic1. In this example, it is non-trivial to understand what happened to the unemployment problem in our society. In other words, taking a look at only social keywords, we have no idea of the detailed events occurring in our society. To tackle this matter, we develop the matching algorithm that computes the probability value of a paragraph given a topic, relying on (i) topic terms and (ii) their probability values. For instance, given a set of text documents, we segment each text document to paragraphs. In the meantime, using LDA, we can extract a set of topics from the text documents. Based on our matching process, each paragraph is assigned to a topic, indicating that the paragraph best matches the topic. Finally, each topic has several best matched paragraphs. Furthermore, assuming there are a topic (e.g., Unemployment Problem) and the best matched paragraph (e.g., Up to 300 workers lost their jobs in XXX company at Seoul). In this case, we can grasp the detailed information of the social keyword such as "300 workers", "unemployment", "XXX company", and "Seoul". In addition, our system visualizes social keywords over time. Therefore, through our matching process and keyword visualization, most researchers will be able to detect social issues easily and quickly. Through this prototype system, we have detected various social issues appearing in our society and also showed effectiveness of our proposed methods according to our experimental results. Note that you can also use our proof-of-concept system in http://dslab.snu.ac.kr/demo.html.

• Journal of Intelligence and Information Systems
• /
• v.23 no.4
• /
• pp.77-110
• /
• 2017

Recently, the diversification and individualization of consumption patterns through the web and mobile devices based on the Internet have been rapid. As this happens, the efficient operation of the offline store, which is a traditional distribution channel, has become more important. In order to raise both the sales and profits of stores, stores need to supply and sell the most attractive products to consumers in a timely manner. However, there is a lack of research on which SKUs, out of many products, can increase sales probability and reduce inventory costs. In particular, if a company sells products through multiple in-store stores across multiple locations, it would be helpful to increase sales and profitability of stores if SKUs appealing to customers are recommended. In this study, the recommender system (recommender system such as collaborative filtering and hybrid filtering), which has been used for personalization recommendation, is suggested by SKU recommendation method of a store unit of a distribution company that handles a homogeneous brand through a plurality of sales stores by country and region. We calculated the similarity of each store by using the purchase data of each store's handling items, filtering the collaboration according to the sales history of each store by each SKU, and finally recommending the individual SKU to the store. In addition, the store is classified into four clusters through PCA (Principal Component Analysis) and cluster analysis (Clustering) using the store profile data. The recommendation system is implemented by the hybrid filtering method that applies the collaborative filtering in each cluster and measured the performance of both methods based on actual sales data. Most of the existing recommendation systems have been studied by recommending items such as movies and music to the users. In practice, industrial applications have also become popular. In the meantime, there has been little research on recommending SKUs for each store by applying these recommendation systems, which have been mainly dealt with in the field of personalization services, to the store units of distributors handling similar brands. If the recommendation method of the existing recommendation methodology was 'the individual field', this study expanded the scope of the store beyond the individual domain through a plurality of sales stores by country and region and dealt with the store unit of the distribution company handling the same brand SKU while suggesting a recommendation method. In addition, if the existing recommendation system is limited to online, it is recommended to apply the data mining technique to develop an algorithm suitable for expanding to the store area rather than expanding the utilization range offline and analyzing based on the existing individual. The significance of the results of this study is that the personalization recommendation algorithm is applied to a plurality of sales outlets handling the same brand. A meaningful result is derived and a concrete methodology that can be constructed and used as a system for actual companies is proposed. It is also meaningful that this is the first attempt to expand the research area of the academic field related to the existing recommendation system, which was focused on the personalization domain, to a sales store of a company handling the same brand. From 05 to 03 in 2014, the number of stores' sales volume of the top 100 SKUs are limited to 52 SKUs by collaborative filtering and the hybrid filtering method SKU recommended. We compared the performance of the two recommendation methods by totaling the sales results. The reason for comparing the two recommendation methods is that the recommendation method of this study is defined as the reference model in which offline collaborative filtering is applied to demonstrate higher performance than the existing recommendation method. The results of this model are compared with the Hybrid filtering method, which is a model that reflects the characteristics of the offline store view. The proposed method showed a higher performance than the existing recommendation method. The proposed method was proved by using actual sales data of large Korean apparel companies. In this study, we propose a method to extend the recommendation system of the individual level to the group level and to efficiently approach it. In addition to the theoretical framework, which is of great value.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.85-109
• /
• 2018

Recommender system recommends the items expected to be purchased by a customer in the future according to his or her previous purchase behaviors. It has been served as a tool for realizing one-to-one personalization for an e-commerce service company. Traditional recommender systems, especially the recommender systems based on collaborative filtering (CF), which is the most popular recommendation algorithm in both academy and industry, are designed to generate the items list for recommendation by using 'overall rating' - a single criterion. However, it has critical limitations in understanding the customers' preferences in detail. Recently, to mitigate these limitations, some leading e-commerce companies have begun to get feedback from their customers in a form of 'multicritera ratings'. Multicriteria ratings enable the companies to understand their customers' preferences from the multidimensional viewpoints. Moreover, it is easy to handle and analyze the multidimensional ratings because they are quantitative. But, the recommendation using multicritera ratings also has limitation that it may omit detail information on a user's preference because it only considers three-to-five predetermined criteria in most cases. Under this background, this study proposes a novel hybrid recommendation system, which selectively uses the results from 'traditional CF' and 'CF using multicriteria ratings'. Our proposed system is based on the premise that some people have holistic preference scheme, whereas others have composite preference scheme. Thus, our system is designed to use traditional CF using overall rating for the users with holistic preference, and to use CF using multicriteria ratings for the users with composite preference. To validate the usefulness of the proposed system, we applied it to a real-world dataset regarding the recommendation for POI (point-of-interests). Providing personalized POI recommendation is getting more attentions as the popularity of the location-based services such as Yelp and Foursquare increases. The dataset was collected from university students via a Web-based online survey system. Using the survey system, we collected the overall ratings as well as the ratings for each criterion for 48 POIs that are located near K university in Seoul, South Korea. The criteria include 'food or taste', 'price' and 'service or mood'. As a result, we obtain 2,878 valid ratings from 112 users. Among 48 items, 38 items (80%) are used as training dataset, and the remaining 10 items (20%) are used as validation dataset. To examine the effectiveness of the proposed system (i.e. hybrid selective model), we compared its performance to the performances of two comparison models - the traditional CF and the CF with multicriteria ratings. The performances of recommender systems were evaluated by using two metrics - average MAE(mean absolute error) and precision-in-top-N. Precision-in-top-N represents the percentage of truly high overall ratings among those that the model predicted would be the N most relevant items for each user. The experimental system was developed using Microsoft Visual Basic for Applications (VBA). The experimental results showed that our proposed system (avg. MAE = 0.584) outperformed traditional CF (avg. MAE = 0.591) as well as multicriteria CF (avg. AVE = 0.608). We also found that multicriteria CF showed worse performance compared to traditional CF in our data set, which is contradictory to the results in the most previous studies. This result supports the premise of our study that people have two different types of preference schemes - holistic and composite. Besides MAE, the proposed system outperformed all the comparison models in precision-in-top-3, precision-in-top-5, and precision-in-top-7. The results from the paired samples t-test presented that our proposed system outperformed traditional CF with 10% statistical significance level, and multicriteria CF with 1% statistical significance level from the perspective of average MAE. The proposed system sheds light on how to understand and utilize user's preference schemes in recommender systems domain.

• 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.