• Journal of Intelligence and Information Systems
• /
• v.21 no.2
• /
• pp.1-18
• /
• 2015

Collaborative filtering(CF) algorithm has been popularly used for recommender systems in both academic and practical applications. A general CF system compares users based on how similar they are, and creates recommendation results with the items favored by other people with similar tastes. Thus, it is very important for CF to measure the similarities between users because the recommendation quality depends on it. In most cases, users' explicit numeric ratings of items(i.e. quantitative information) have only been used to calculate the similarities between users in CF. However, several studies indicated that qualitative information such as user's reviews on the items may contribute to measure these similarities more accurately. Considering that a lot of people are likely to share their honest opinion on the items they purchased recently due to the advent of the Web 2.0, user's reviews can be regarded as the informative source for identifying user's preference with accuracy. Under this background, this study proposes a new hybrid recommender system that combines with users' review mining. Our proposed system is based on conventional memory-based CF, but it is designed to use both user's numeric ratings and his/her text reviews on the items when calculating similarities between users. In specific, our system creates not only user-item rating matrix, but also user-item review term matrix. Then, it calculates rating similarity and review similarity from each matrix, and calculates the final user-to-user similarity based on these two similarities(i.e. rating and review similarities). As the methods for calculating review similarity between users, we proposed two alternatives - one is to use the frequency of the commonly used terms, and the other one is to use the sum of the importance weights of the commonly used terms in users' review. In the case of the importance weights of terms, we proposed the use of average TF-IDF(Term Frequency - Inverse Document Frequency) weights. To validate the applicability of the proposed system, we applied it to the implementation of a recommender system for smartphone applications (hereafter, app). At present, over a million apps are offered in each app stores operated by Google and Apple. Due to this information overload, users have difficulty in selecting proper apps that they really want. Furthermore, app store operators like Google and Apple have cumulated huge amount of users' reviews on apps until now. Thus, we chose smartphone app stores as the application domain of our system. In order to collect the experimental data set, we built and operated a Web-based data collection system for about two weeks. As a result, we could obtain 1,246 valid responses(ratings and reviews) from 78 users. The experimental system was implemented using Microsoft Visual Basic for Applications(VBA) and SAS Text Miner. And, to avoid distortion due to human intervention, we did not adopt any refining works by human during the user's review mining process. To examine the effectiveness of the proposed system, we compared its performance to the performance of conventional CF system. The performances of recommender systems were evaluated by using average MAE(mean absolute error). The experimental results showed that our proposed system(MAE = 0.7867 ~ 0.7881) slightly outperformed a conventional CF system(MAE = 0.7939). Also, they showed that the calculation of review similarity between users based on the TF-IDF weights(MAE = 0.7867) leaded to better recommendation accuracy than the calculation based on the frequency of the commonly used terms in reviews(MAE = 0.7881). The results from paired samples t-test presented that our proposed system with review similarity calculation using the frequency of the commonly used terms outperformed conventional CF system with 10% statistical significance level. Our study sheds a light on the application of users' review information for facilitating electronic commerce by recommending proper items to users.

• Journal of KIISE
• /
• v.44 no.5
• /
• pp.553-558
• /
• 2017

With the rapid growth of Big Data, research on extracting meaningful information is being pursued by both academia and industry. Especially, data characteristics derived from analysis, and researcher intention are key factors for search algorithms to obtain accurate output. Therefore, reflecting both data characteristics and researcher intention properly is the final goal of data analysis research. The data analyzed properly can help users to increase loyalty to the service provided by company, and to utilize information more effectively and efficiently. In this paper, we explore various methods of document-evaluation, so that we can improve the accuracy of searching article one of the most frequently searches used in real life. We also analyze the experiment result, and suggest the proper manners to use various methods.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.34 no.4
• /
• pp.159-169
• /
• 2020

Shanghanlun (Treatise on Cold Damage Diseases) is the oldest document in the literature on clinical records of Traditional Asian medicine (TAM), on which TAM theories about symptoms-herbs relationships are based. In this study, we aim to quantitatively explore the relationships between symptoms and herbs in Shanghanlun. The text in Shanghanlun was converted into structured data. Using the structured data, Term Frequency - Inverse Document Frequency (TF-IDF) scores of symptoms and herbs were calculated from each chapter to derive the major symptoms and herbs in each chapter. To understand the structure of the entire document, principal component analysis (PCA) was performed for the 6-dimensional chapter space. Bipartite network analysis was conducted focusing on Jaccard scores between symptoms and herbs and eigenvector centralities of nodes. TF-IDF scores showed the characteristics of each chapter through major symptoms and herbs. Principal components drawn by PCA suggested the entire structure of Shanghanlun. The network analysis revealed a 'multi herbs - multi symptoms' relationship. Common symptoms and herbs were drawn from high eigenvector centralities of their nodes, while specific symptoms and herbs were drawn from low centralities. Symptoms expected to be treated by herbs were derived, respectively. Using measurable metrics, we conducted a computational study on patterns of Shanghanlun. Quantitative researches on TAM theories will contribute to improving the clarity of TAM theories.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.4
• /
• pp.1400-1418
• /
• 2020

In the development of commercial promotion, chatbot is known as one of significant skill by application of natural language processing (NLP). Conventional design methods are using bag-of-words model (BOW) alone based on Google database and other online corpus. For one thing, in the bag-of-words model, the vectors are Irrelevant to one another. Even though this method is friendly to discrete features, it is not conducive to the machine to understand continuous statements due to the loss of the connection between words in the encoded word vector. For other thing, existing methods are used to test in state-of-the-art online corpus but it is hard to apply in real applications such as telemarketing data. In this paper, we propose an improved chatbot design way using hybrid bag-of-words model and skip-gram model based on the real telemarketing data. Specifically, we first collect the real data in the telemarketing field and perform data cleaning and data classification on the constructed corpus. Second, the word representation is adopted hybrid bag-of-words model and skip-gram model. The skip-gram model maps synonyms in the vicinity of vector space. The correlation between words is expressed, so the amount of information contained in the word vector is increased, making up for the shortcomings caused by using bag-of-words model alone. Third, we use the term frequency-inverse document frequency (TF-IDF) weighting method to improve the weight of key words, then output the final word expression. At last, the answer is produced using hybrid retrieval model and generate model. The retrieval model can accurately answer questions in the field. The generate model can supplement the question of answering the open domain, in which the answer to the final reply is completed by long-short term memory (LSTM) training and prediction. Experimental results show which the hybrid word vector expression model can improve the accuracy of the response and the whole system can communicate with humans.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.10a
• /
• pp.382-385
• /
• 2016

본 논문은 현재 영역 별로 파편화된 여러 O2O(Online to Offline) 서비스들을 통합적으로 제공하기 위해 자연어를 통한 NUI(Natural User Interface)를 개발하여 사용자가 명시한 상품 정보의 항목을 자동으로 분류하고자 한다. 이를 위해 e-commerce 도메인 정보 학습에 적합한 나이브 베이즈 분류(Naive Bayes Classifier) 알고리즘을 사용한다. 학습에는 미국 e-commerce 사이트 Groupon의 상품 정보와 분류 체계를 사용하며, 학습 데이터의 특징을 분석하여 상품 정보에 특화된 학습 데이터 정제 및 TF-IDF(Term Frequency-Inverse Document Frequency)를 통한 단어 별 가중치를 적용하여 알고리즘의 정확도를 향상시킨다.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.30 no.1
• /
• pp.187-198
• /
• 2005

The structure of a Web site can prevent the search robots or crawling agents from confusion in the midst of huge forest of the Web pages. We formalize the view on the World Wide Web and generalize it as a hierarchy of Web objects such as the Web as a set of Web sites, and a Web site as a directed graph with Web nodes and Web edges. Our approach results in the optimal hierarchical structure that can maximize the weight, tf-idf (term frequency and inverse document frequency), that is one of the most widely accepted content centric measures in the information retrieval community, so that the measure can be used to embody the semantics of search query. The experimental results represent that the optimization model is an effective alternative in the dynamically changing Web environment by replacing conventional heuristic approaches.

• The Journal of Korean Medicine
• /
• v.43 no.1
• /
• pp.73-86
• /
• 2022

Objectives: In the health care industry, the influence of online reviews is growing. As medical services are provided mainly by providers, those services have been managed by hospitals and clinics. However, direct promotions of medical services by providers are legally forbidden. Due to this reason, consumers, like patients and clients, search a lot of reviews on the Internet to get any information about hospitals, treatments, prices, etc. It can be determined that online reviews indicate the quality of hospitals, and that analysis should be done for sustainable hospital marketing. Method: Using a Python-based crawler, we collected reviews, written by real patients, who had experienced Korean medicine, about more than 14,000 reviews. To extract the most representative words, reviews were divided by positive and negative; after that reviews were pre-processed to get only nouns and adjectives to get TF(Term Frequency), DF(Document Frequency), and TF-IDF(Term Frequency - Inverse Document Frequency). Finally, to get some topics about reviews, aggregations of extracted words were analyzed by using LDA(Latent Dirichlet Allocation) methods. To avoid overlap, the number of topics is set by Davis visualization. Results and Conclusions: 6 and 3 topics extracted in each positive/negative review, analyzed by LDA Topic Model. The main factors, consisting of topics were 1) Response to patients and customers. 2) Customized treatment (consultation) and management. 3) Hospital/Clinic's environments.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.49 no.5
• /
• pp.79-96
• /
• 2021

Green infrastructure planning represents landscape planning measures to reduce particulate matter. This study aimed to derive factors that may be used in planning green infrastructure for particulate matter reduction using text mining techniques. A range of analyses were carried out by focusing on keywords such as 'particulate matter reduction plan' and 'green infrastructure planning elements'. The analyses included Term Frequency-Inverse Document Frequency (TF-IDF) analysis, centrality analysis, related word analysis, and topic modeling analysis. These analyses were carried out via text mining by collecting information on previous related research, policy reports, and laws. Initially, TF-IDF analysis results were used to classify major keywords relating to particulate matter and green infrastructure into three groups: (1) environmental issues (e.g., particulate matter, environment, carbon, and atmosphere), target spaces (e.g., urban, park, and local green space), and application methods (e.g., analysis, planning, evaluation, development, ecological aspect, policy management, technology, and resilience). Second, the centrality analysis results were found to be similar to those of TF-IDF; it was confirmed that the central connectors to the major keywords were 'Green New Deal' and 'Vacant land'. The results from the analysis of related words verified that planning green infrastructure for particulate matter reduction required planning forests and ventilation corridors. Additionally, moisture must be considered for microclimate control. It was also confirmed that utilizing vacant space, establishing mixed forests, introducing particulate matter reduction technology, and understanding the system may be important for the effective planning of green infrastructure. Topic analysis was used to classify the planning elements of green infrastructure based on ecological, technological, and social functions. The planning elements of ecological function were classified into morphological (e.g., urban forest, green space, wall greening) and functional aspects (e.g., climate control, carbon storage and absorption, provision of habitats, and biodiversity for wildlife). The planning elements of technical function were classified into various themes, including the disaster prevention functions of green infrastructure, buffer effects, stormwater management, water purification, and energy reduction. The planning elements of the social function were classified into themes such as community function, improving the health of users, and scenery improvement. These results suggest that green infrastructure planning for particulate matter reduction requires approaches related to key concepts, such as resilience and sustainability. In particular, there is a need to apply green infrastructure planning elements in order to reduce exposure to particulate matter.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.237-262
• /
• 2022

There has been a growing interest in IPOs (Initial Public Offerings) due to the profitable returns that IPO stocks can offer to investors. However, IPOs can be speculative investments that may involve substantial risk as well because shares tend to be volatile, and the supply of IPO shares is often highly limited. Therefore, it is crucially important that IPO investors are well informed of the issuing firms and the market before deciding whether to invest or not. Unlike institutional investors, individual investors are at a disadvantage since there are few opportunities for individuals to obtain information on the IPOs. In this regard, the purpose of this study is to provide individual investors with the information they may consider when making an IPO investment decision. This study presents a model that uses machine learning and text analysis to predict whether an IPO stock price would move up or down after the first 5 trading days. Our sample includes 691 Korean IPOs from June 2009 to December 2020. The input variables for the prediction are three tone variables created from IPO prospectuses and quantitative variables that are either firm-specific, issue-specific, or market-specific. The three prospectus tone variables indicate the percentage of positive, neutral, and negative sentences in a prospectus, respectively. We considered only the sentences in the Risk Factors section of a prospectus for the tone analysis in this study. All sentences were classified into 'positive', 'neutral', and 'negative' via text analysis using TF-IDF (Term Frequency - Inverse Document Frequency). Measuring the tone of each sentence was conducted by machine learning instead of a lexicon-based approach due to the lack of sentiment dictionaries suitable for Korean text analysis in the context of finance. For this reason, the training set was created by randomly selecting 10% of the sentences from each prospectus, and the sentence classification task on the training set was performed after reading each sentence in person. Then, based on the training set, a Support Vector Machine model was utilized to predict the tone of sentences in the test set. Finally, the machine learning model calculated the percentages of positive, neutral, and negative sentences in each prospectus. To predict the price movement of an IPO stock, four different machine learning techniques were applied: Logistic Regression, Random Forest, Support Vector Machine, and Artificial Neural Network. According to the results, models that use quantitative variables using technical analysis and prospectus tone variables together show higher accuracy than models that use only quantitative variables. More specifically, the prediction accuracy was improved by 1.45% points in the Random Forest model, 4.34% points in the Artificial Neural Network model, and 5.07% points in the Support Vector Machine model. After testing the performance of these machine learning techniques, the Artificial Neural Network model using both quantitative variables and prospectus tone variables was the model with the highest prediction accuracy rate, which was 61.59%. The results indicate that the tone of a prospectus is a significant factor in predicting the price movement of an IPO stock. In addition, the McNemar test was used to verify the statistically significant difference between the models. The model using only quantitative variables and the model using both the quantitative variables and the prospectus tone variables were compared, and it was confirmed that the predictive performance improved significantly at a 1% significance level.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.12
• /
• pp.511-522
• /
• 2014

During the development of the software, a variety of bugs are reported. Several bug tracking systems, such as, Bugzilla, MantisBT, Trac, JIRA, are used to deal with reported bug information in many open source development projects. Bug reports in bug tracking system would be triaged to manage bugs and determine developer who is responsible for resolving the bug report. As the size of the software is increasingly growing and bug reports tend to be duplicated, bug triage becomes more and more complex and difficult. In this paper, we present an approach to assign bug reports to appropriate developers, which is a main part of bug triage task. At first, words which have been included the resolved bug reports are classified according to each developer. Second, words in newly bug reports are selected. After first and second steps, vectors whose items are the selected words are generated. At the third step, TF-IDF(Term frequency - Inverse document frequency) of the each selected words are computed, which is the weight value of each vector item. Finally, the developers are recommended based on the similarity between the developer's word vector and the vector of new bug report. We conducted an experiment on Eclipse JDT and CDT project to show the applicability of the proposed approach. We also compared the proposed approach with an existing study which is based on machine learning. The experimental results show that the proposed approach is superior to existing method.