• Asia pacific journal of information systems
• /
• v.21 no.1
• /
• pp.103-122
• /
• 2011

Recently, numerous documents have been made available electronically. Internet search engines and digital libraries commonly return query results containing hundreds or even thousands of documents. In this situation, it is virtually impossible for users to examine complete documents to determine whether they might be useful for them. For this reason, some on-line documents are accompanied by a list of keywords specified by the authors in an effort to guide the users by facilitating the filtering process. In this way, a set of keywords is often considered a condensed version of the whole document and therefore plays an important role for document retrieval, Web page retrieval, document clustering, summarization, text mining, and so on. Since many academic journals ask the authors to provide a list of five or six keywords on the first page of an article, keywords are most familiar in the context of journal articles. However, many other types of documents could not benefit from the use of keywords, including Web pages, email messages, news reports, magazine articles, and business papers. Although the potential benefit is large, the implementation itself is the obstacle; manually assigning keywords to all documents is a daunting task, or even impractical in that it is extremely tedious and time-consuming requiring a certain level of domain knowledge. Therefore, it is highly desirable to automate the keyword generation process. There are mainly two approaches to achieving this aim: keyword assignment approach and keyword extraction approach. Both approaches use machine learning methods and require, for training purposes, a set of documents with keywords already attached. In the former approach, there is a given set of vocabulary, and the aim is to match them to the texts. In other words, the keywords assignment approach seeks to select the words from a controlled vocabulary that best describes a document. Although this approach is domain dependent and is not easy to transfer and expand, it can generate implicit keywords that do not appear in a document. On the other hand, in the latter approach, the aim is to extract keywords with respect to their relevance in the text without prior vocabulary. In this approach, automatic keyword generation is treated as a classification task, and keywords are commonly extracted based on supervised learning techniques. Thus, keyword extraction algorithms classify candidate keywords in a document into positive or negative examples. Several systems such as Extractor and Kea were developed using keyword extraction approach. Most indicative words in a document are selected as keywords for that document and as a result, keywords extraction is limited to terms that appear in the document. Therefore, keywords extraction cannot generate implicit keywords that are not included in a document. According to the experiment results of Turney, about 64% to 90% of keywords assigned by the authors can be found in the full text of an article. Inversely, it also means that 10% to 36% of the keywords assigned by the authors do not appear in the article, which cannot be generated through keyword extraction algorithms. Our preliminary experiment result also shows that 37% of keywords assigned by the authors are not included in the full text. This is the reason why we have decided to adopt the keyword assignment approach. In this paper, we propose a new approach for automatic keyword assignment namely IVSM(Inverse Vector Space Model). The model is based on a vector space model. which is a conventional information retrieval model that represents documents and queries by vectors in a multidimensional space. IVSM generates an appropriate keyword set for a specific document by measuring the distance between the document and the keyword sets. The keyword assignment process of IVSM is as follows: (1) calculating the vector length of each keyword set based on each keyword weight; (2) preprocessing and parsing a target document that does not have keywords; (3) calculating the vector length of the target document based on the term frequency; (4) measuring the cosine similarity between each keyword set and the target document; and (5) generating keywords that have high similarity scores. Two keyword generation systems were implemented applying IVSM: IVSM system for Web-based community service and stand-alone IVSM system. Firstly, the IVSM system is implemented in a community service for sharing knowledge and opinions on current trends such as fashion, movies, social problems, and health information. The stand-alone IVSM system is dedicated to generating keywords for academic papers, and, indeed, it has been tested through a number of academic papers including those published by the Korean Association of Shipping and Logistics, the Korea Research Academy of Distribution Information, the Korea Logistics Society, the Korea Logistics Research Association, and the Korea Port Economic Association. We measured the performance of IVSM by the number of matches between the IVSM-generated keywords and the author-assigned keywords. According to our experiment, the precisions of IVSM applied to Web-based community service and academic journals were 0.75 and 0.71, respectively. The performance of both systems is much better than that of baseline systems that generate keywords based on simple probability. Also, IVSM shows comparable performance to Extractor that is a representative system of keyword extraction approach developed by Turney. As electronic documents increase, we expect that IVSM proposed in this paper can be applied to many electronic documents in Web-based community and digital library.

• Journal of Intelligence and Information Systems
• /
• v.25 no.2
• /
• pp.141-166
• /
• 2019

Recently, channels like social media and SNS create enormous amount of data. In all kinds of data, portions of unstructured data which represented as text data has increased geometrically. But there are some difficulties to check all text data, so it is important to access those data rapidly and grasp key points of text. Due to needs of efficient understanding, many studies about text summarization for handling and using tremendous amounts of text data have been proposed. Especially, a lot of summarization methods using machine learning and artificial intelligence algorithms have been proposed lately to generate summary objectively and effectively which called "automatic summarization". However almost text summarization methods proposed up to date construct summary focused on frequency of contents in original documents. Those summaries have a limitation for contain small-weight subjects that mentioned less in original text. If summaries include contents with only major subject, bias occurs and it causes loss of information so that it is hard to ascertain every subject documents have. To avoid those bias, it is possible to summarize in point of balance between topics document have so all subject in document can be ascertained, but still unbalance of distribution between those subjects remains. To retain balance of subjects in summary, it is necessary to consider proportion of every subject documents originally have and also allocate the portion of subjects equally so that even sentences of minor subjects can be included in summary sufficiently. In this study, we propose "subject-balanced" text summarization method that procure balance between all subjects and minimize omission of low-frequency subjects. For subject-balanced summary, we use two concept of summary evaluation metrics "completeness" and "succinctness". Completeness is the feature that summary should include contents of original documents fully and succinctness means summary has minimum duplication with contents in itself. Proposed method has 3-phases for summarization. First phase is constructing subject term dictionaries. Topic modeling is used for calculating topic-term weight which indicates degrees that each terms are related to each topic. From derived weight, it is possible to figure out highly related terms for every topic and subjects of documents can be found from various topic composed similar meaning terms. And then, few terms are selected which represent subject well. In this method, it is called "seed terms". However, those terms are too small to explain each subject enough, so sufficient similar terms with seed terms are needed for well-constructed subject dictionary. Word2Vec is used for word expansion, finds similar terms with seed terms. Word vectors are created after Word2Vec modeling, and from those vectors, similarity between all terms can be derived by using cosine-similarity. Higher cosine similarity between two terms calculated, higher relationship between two terms defined. So terms that have high similarity values with seed terms for each subjects are selected and filtering those expanded terms subject dictionary is finally constructed. Next phase is allocating subjects to every sentences which original documents have. To grasp contents of all sentences first, frequency analysis is conducted with specific terms that subject dictionaries compose. TF-IDF weight of each subjects are calculated after frequency analysis, and it is possible to figure out how much sentences are explaining about each subjects. However, TF-IDF weight has limitation that the weight can be increased infinitely, so by normalizing TF-IDF weights for every subject sentences have, all values are changed to 0 to 1 values. Then allocating subject for every sentences with maximum TF-IDF weight between all subjects, sentence group are constructed for each subjects finally. Last phase is summary generation parts. Sen2Vec is used to figure out similarity between subject-sentences, and similarity matrix can be formed. By repetitive sentences selecting, it is possible to generate summary that include contents of original documents fully and minimize duplication in summary itself. For evaluation of proposed method, 50,000 reviews of TripAdvisor are used for constructing subject dictionaries and 23,087 reviews are used for generating summary. Also comparison between proposed method summary and frequency-based summary is performed and as a result, it is verified that summary from proposed method can retain balance of all subject more which documents originally have.

• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.111-126
• /
• 2020

Most industries have recently become aware of the importance of customer lifetime value as they are exposed to a competitive environment. As a result, preventing customers from churn is becoming a more important business issue than securing new customers. This is because maintaining churn customers is far more economical than securing new customers, and in fact, the acquisition cost of new customers is known to be five to six times higher than the maintenance cost of churn customers. Also, Companies that effectively prevent customer churn and improve customer retention rates are known to have a positive effect on not only increasing the company's profitability but also improving its brand image by improving customer satisfaction. Predicting customer churn, which had been conducted as a sub-research area for CRM, has recently become more important as a big data-based performance marketing theme due to the development of business machine learning technology. Until now, research on customer churn prediction has been carried out actively in such sectors as the mobile telecommunication industry, the financial industry, the distribution industry, and the game industry, which are highly competitive and urgent to manage churn. In addition, These churn prediction studies were focused on improving the performance of the churn prediction model itself, such as simply comparing the performance of various models, exploring features that are effective in forecasting departures, or developing new ensemble techniques, and were limited in terms of practical utilization because most studies considered the entire customer group as a group and developed a predictive model. As such, the main purpose of the existing related research was to improve the performance of the predictive model itself, and there was a relatively lack of research to improve the overall customer churn prediction process. In fact, customers in the business have different behavior characteristics due to heterogeneous transaction patterns, and the resulting churn rate is different, so it is unreasonable to assume the entire customer as a single customer group. Therefore, it is desirable to segment customers according to customer classification criteria, such as loyalty, and to operate an appropriate churn prediction model individually, in order to carry out effective customer churn predictions in heterogeneous industries. Of course, in some studies, there are studies in which customers are subdivided using clustering techniques and applied a churn prediction model for individual customer groups. Although this process of predicting churn can produce better predictions than a single predict model for the entire customer population, there is still room for improvement in that clustering is a mechanical, exploratory grouping technique that calculates distances based on inputs and does not reflect the strategic intent of an entity such as loyalties. This study proposes a segment-based customer departure prediction process (CCP/2DL: Customer Churn Prediction based on Two-Dimensional Loyalty segmentation) based on two-dimensional customer loyalty, assuming that successful customer churn management can be better done through improvements in the overall process than through the performance of the model itself. CCP/2DL is a series of churn prediction processes that segment two-way, quantitative and qualitative loyalty-based customer, conduct secondary grouping of customer segments according to churn patterns, and then independently apply heterogeneous churn prediction models for each churn pattern group. Performance comparisons were performed with the most commonly applied the General churn prediction process and the Clustering-based churn prediction process to assess the relative excellence of the proposed churn prediction process. The General churn prediction process used in this study refers to the process of predicting a single group of customers simply intended to be predicted as a machine learning model, using the most commonly used churn predicting method. And the Clustering-based churn prediction process is a method of first using clustering techniques to segment customers and implement a churn prediction model for each individual group. In cooperation with a global NGO, the proposed CCP/2DL performance showed better performance than other methodologies for predicting churn. This churn prediction process is not only effective in predicting churn, but can also be a strategic basis for obtaining a variety of customer observations and carrying out other related performance marketing activities.

• Journal of the Korean association of regional geographers
• /
• v.16 no.3
• /
• pp.275-294
• /
• 2010

In recent years, international migration of professional workers is significantly increasing as globalization has been deepened more and more. South Korea is not an exception for this case. Immigration of professional workers have steadily increased since 2000 in Korea, and the number reached approximately to 50,000 in 2009. In addition, it is a major trend that immigrants of short-sojourn are decreasing and ones of long-sojourn increasing. Our research shows that foreign language instructor has the greatest number of foreign professional immigrants. The next is professional immigrants related to business-activities. There are considerably entertainers, but they have greatly decreased since 2003. Majority of foreign professional immigrants settle down in a few metropolises. Especially, they reside in Seoul Metropolitan Area and Southeast coastal region. Professional immigrants trend to do with Korean on the base of their offices rather than residental communities in terms of adaptation, and they do not have strong will to reside permanently in Korea. Moreover, they are located at a blind spot of Korean government's foreign immigrant policy, comparing to foreign workers and female marriage immigrants.

• Management & Information Systems Review
• /
• v.33 no.2
• /
• pp.225-239
• /
• 2014

An effect of reward program related to promotional activity has the limitation of being concentrated on a short-term performance or of inducing temporary re-purchase. Accordingly, this study verified the influence of reward method upon consumers' response recovery centering on interactive effects of reward timing and reward intensity, in order to expand a research of dissatisfaction situation. As for the objective of this study, first, the aim is to verify the difference in the influence of economic, non-economic, and combined rewards, which are reward methods of dissatisfaction situation, upon consumers' cognitive response recovery and emotional response recovery. Second, the aim is to confirm a moderating role of reward timing and reward intensity in the effect of consumers' response recovery according to reward methods. To design a research, the perfect factor design between subjects in 3X2X2 was used. As a result of major research, first, there was a difference in the influence upon consumers' response recovery depending on reward methods. Second, the influence of reward method upon consumers' response recovery had a difference depending on reward timing. Third, the influence of reward method upon consumers' response recovery had a difference depending on reward intensity. Consumers' response recovery level was confirmed to have the greatest influence in the combined reward. This study has a significance in newly applying the reward timing, in the dissatisfaction situation which is addressed in the general reward program. Through this study, the aim was to support the empirically analytical results of prior researches and to expand its role in several angles.

• The Journal of the Korea Contents Association
• /
• v.14 no.4
• /
• pp.110-122
• /
• 2014

Korea's film industry has been growing over the last 10 years, and there has been much attention to the antecedents of film box office sales both academic and business communities. So far, previous research which explained success factors of film or movie mainly focused on 3 stages, production, distribution and screening. However, these 3 steps are heavily vertically integrated in Korea's firm industry unlike United States. Almost 130% of movie theaters are multiplex chain and operated by film production companies such as CJ and Lotte Entertainment In this situation, film sales are likely to he affected by movie theaters own facilities or location factors rather than movie contents. Based. on resource-based view and S-C-P paradigm, the authors examined "whether movie theater's facilities factors and trade area factors such as accessibility, competitive situation, and population have effect to movie theater's sales revenues. The results showed that the average occupancy of theater is the most important factor to movie theaters sales in both large and small cities. In large cities, movie theater's facilities factors which included vibration seat special sound system, premium movie theater, VIP lounge are relatively important than trade area factors. In contrast, in small cities, location factors and accessibility are the most important factors to movie theaters sales. We discuss the managerial and theoretical implication for the results and the specific limitations are suggested at the end of the paper.

• International Commerce and Information Review
• /
• v.18 no.4
• /
• pp.55-78
• /
• 2016

In this study, service quality attributes of uTradeHub were classified based on the Kano model, and quality attributes that should be managed in priority to improve the service quality of uTradeHub were investigated using Timko's customer satisfaction coefficient(CSC) and average satisfaction coefficient(ASC). The results of the study are summarized as follows. First, as a result of classifying service quality attributes based on Kano model, 12 one dimensional qualities, 5 must-be qualities, 2 indifferent qualities were deducted, and many quality attributes of uTradeHub service were confirmed to be one dimensional quality to which is needed to be paid attention and paid more detailed attention to enhance service quality. Second, in the analysis result using Timko's customer satisfaction coefficient, "post processing for problems and complaints", "cost reduction", "efficiency of business processing" were ranked in the top of satisfaction coefficient, and they found to be quality attributes that customer satisfaction increases when service quality was satisfied. While, "post processing for problems and complaints", "interaction", "ability to respond promptly when problems occur" were ranked in the top of unsatisfaction coefficient, and they were analysed to be quality attributes that customer complaints increase when service quality was unsatisfied. Third, in the result of analyzing the quality attributes that should be managed in priority to improve the service quality of uTradeHub based on the average satisfaction coefficient(ASC), "post processing for problems and complaints", "cost reduction", "useful information" were ranked in the top 3, and they were classified as quality attributes that the satisfaction level increases more when they are improved than now, but the satisfaction level decreases when they are worsen.

• Journal of the Korean Dietetic Association
• /
• v.9 no.3
• /
• pp.248-258
• /
• 2003

This study was conducted to identify dietitians' position and role by assessing the present condition on management of human resources in contracted foodservice management company. Questionnaires were distributed to 79 contracted companies (eight large-size, 48 mid-size, 23 small-size companies) from March to May in 2002. Statistical analysis was performed with SPSSwin (version 8.0). The data were analyzed in group comparisons using frequencies and percentage for every item in the questionnaires, $x^2$-test, and oneway ANOVA. About eighty-five percent of contracted foodservice companies employed the new dietitians as full time employees, and seventy-five percent of them were promoted the dietitians by evaluation after a given period of time. As a starting payment for university graduates, large-size companies payed an average of 16,260,000 won/year, which was significantly higher (p<0.01) than those of mid-sized (11,320,000 won/year) and small-sized companies (11,620,000 won/year). The mean lengths of dietitians' service were 33.5 months in large-size companies, 26.5 months in mid-sized companies, 26.0 months in small-sized companies. It was less than 3 years in all companies (avg. 26.9 months). Fifty-four companies (68.4%) employed dietitians in each foodservice contract, whereas 25 companies didn't employ dietitians. The ratios of dietitians out of employees in each department of the companies were 42.6% in the department of contracted foodservice management, 19.9% in the department of menu development, 18.1% in the department of food safety, 8.7% in the department of distribution and purchase, 4.2% in the department of business, and 3.9% in the department of customer satisfaction. The dietitians' positions were directors in two companies (2.5%), general managers in two companies (2.5%), deputy managers in seven companies (8.9%), managers in twenty-nine companies (36.7%), assistant managers/chief clerks in twenty-four companies (30.4%), and chiefs in twenty-five companies (31.6%). The frequencies of training for dietitians were 6.2 times/year for the food safety training, 5.8 times/year for the cooking training, 4.8 times/year for nutrition-related training, and 4.7 times/year for service training.

• Journal of Digital Convergence
• /
• v.11 no.5
• /
• pp.119-133
• /
• 2013

This study aims to provide power generating plants with eco-efficiency information. To implement the purposes, of study, both DEA(Data, Envelopment Analysis) model and interview were incorporated in terms of methodologies. To analyze the managerial efficiency, total labor cost and number of employees were considered as input factors. CO2, NOx, and water also were considered as input factors to analyze eco-efficiency. Both annual total power product and annual total revenue were used as output factors. CRS(Constant Return to Scale) and VRS(Variable Return to) model were facilitated in this analysis. According to the findings, most of the power plants were evaluated as 'Efficient'' taking into consideration of average value, both 0.928 from CCR model and 0.969 from VRS model. 7 DMUs including DMU3 and DMU12 are efficient out of 35 DMUs relatively, other DMUs are inefficient. For results of inefficient output factors distribution, it was found that inefficiency for NOx was marked relatively higher than CO2. In order to improve the eco-efficiency in the power plants in the long term, the target amount of Co2 as well as NOx reduction needs to be properly proposed in consideration of particularity of power plants. In the long run, renewable energy, alternative fuels should be adapted to reduce the eco-inefficient.

• Korean Chemical Engineering Research
• /
• v.52 no.6
• /
• pp.807-813
• /
• 2014

The Ag-impregnated activated carbon was produced from bamboo activated carbon by soaking method of silver nitrate solution. The carbonization and activation of raw material was conducted at $900^{\circ}C$. Soaking conditions are the variation of silver nitrate solution concentration (0.002~0.1 mol/L) and soaking time (maximum 24 h). The specific surface area and pore size distribution of the prepared activated carbons were measured. Also, NO and activated carbon reaction were conducted in a thermogravimetric analyzer in order to use for de-NOx agents of used activated carbon. Carbon-NO reactions were carried out with respect to reaction temperature ($20{\sim}850^{\circ}C$) and NO gas partial pressure (0.1~1.8 kPa). As results, Ag amounts are saturated within 2h, Ag amounts increased 1.95 mg Ag/g (0.2%)~ 88.70 mg Ag/g (8.87%) with the concentration of silver nitrate solution in the range of 0.002~0.1 mol/L. The specific volume and surface area of bamboo activated carbon of impregnated with 0.2% silver were maximum, but decreased with increasing Ag amounts of activated carbon due to pore blocking. In NO reaction, the reaction rate of impregnated bamboo activated carbon was retarded as compare with that of bamboo activated carbon. Measured reaction orders of NO concentration and activation energy were 0.63[BA], 0.69l[BA(Ag)] and 80.5 kJ/mol[BA], 66.4 kJ/mol[BA(Ag)], respectively.