• Journal of Digital Convergence
• /
• v.17 no.2
• /
• pp.163-170
• /
• 2019

Over the past decade, the development of the Web explosively increased the data. Feature selection step is an important step in extracting valuable data from a large amount of data. This study proposes a novel opinion mining model based on combining feature selection (FS) methods with Word embedding to vector (Word2vec) and BOW (Bag-of-words). FS methods adopted for this study are CFS (Correlation based FS) and IG (Information Gain). To select an optimal FS method, a number of classifiers ranging from LR (logistic regression), NN (neural network), NBN (naive Bayesian network) to RF (random forest), RS (random subspace), ST (stacking). Empirical results with electronics and kitchen datasets showed that LR and ST classifiers combined with IG applied to BOW features yield best performance in opinion mining. Results with laptop and restaurant datasets revealed that the RF classifier using IG applied to Word2vec features represents best performance in opinion mining.

• Asian Journal for Public Opinion Research
• /
• v.5 no.3
• /
• pp.192-203
• /
• 2018

Alcohol consumption among soldiers impairs health status, performance, and increases the risks of injuries and violence. This study examined drinking behaviors, health problems, and violence among enlisted soldiers at Adisorn military unit in Saraburi, Thailand. Data collection using self-reported questionnaires were distributed to 256 enlisted male soldiers in May 2017. Participants were age 20-22 (93%), Buddhists (98%), high school education or lower (93%). They purchased alcohol at their own expense (46.5%). For alcohol consumption, all were lifetime drinkers (100%). The current drinking patterns were different 28.5% were current drinkers, 65.5% are currently abstaining from drinking (64.5%), and 6.6% stopped drinking permanently. The top three alcohol beverages were beer (52.3%), brandy (25.0%), and hard liquor (19.5%). Problems related to alcohol were from lost balance/falls (6.7%), illness (10.2%), driving under the influence (19.5%), and accidents (24.2%). Violence from drinking in the past month was from fighting (28.1%). This study is the first to provide information about alcohol-related problems in enlisted male soldiers. There is the need to offer straightforward advice, brief counseling, and refer soldiers to receive treatment to prevent alcohol-related problems. Online social media and web-based programs were recommended as platforms to provide preventive alcohol message to the enlisted.

• Journal of Construction Engineering and Project Management
• /
• v.1 no.3
• /
• pp.9-17
• /
• 2011

Web-based PMIS (Project Management Information System) has played significant role in construction management processes in Korea. As the use of web-based PMIS increases, regular quality assessment to identify user's requirements is necessary. However, there have been rare research efforts for quality assessment of web-based PMIS. This study aims to assess the quality of web-based PMIS, especially ASP-PMIS (Application Service Provider based PMIS) that is widely used in Korean construction industry. The assessment factors of ASP-PMIS quality were adopted from previous research and empirically confirmed using exploratory factor analysis. ISA (Importance-Satisfaction Analysis), which is a variation of original IPA (Importance-Performance Analysis), were selected for the assessment and analysis method in this research. A total of 253 completed questionnaires, composed of 23 assessment items, were collected from the ASP-PMIS users in Korea (construction managers and constructors), and they were used to analyse the quality of the systems. Some possible contributions of this research are: it introduces a simple and easy-to-use tool for assessing the quality of ASP-PMIS with a set of quality assessment factors that are selected from previous researches and empirically tested; it provides the quality assessment results of ASP-PMIS in Korea so that ASP-PMIS providers in Korea can understand the users' opinion on their systems; it also identified that the urgent factors that require immediate attention to improvement. However, further researches are to be required on the following areas: enhancing the quality assessment factors in terms of their relation to the success of ASP-PMIS and to the users' performance; assessing and analyzing the quality of individual ASP-PMIS; establishing continuous improvement systems institutionally and instrumentally.

• Journal of Intelligence and Information Systems
• /
• v.19 no.3
• /
• pp.113-125
• /
• 2013

Every company wants to know customer's requirement and makes an effort to meet them. Cause that, communication between customer and company became core competition of business and that important is increasing continuously. There are several strategies to find customer's needs, but VOC (Voice of customer) is one of most powerful communication tools and VOC gathering by several channels as telephone, post, e-mail, website and so on is so meaningful. So, almost company is gathering VOC and operating VOC system. VOC is important not only to business organization but also public organization such as government, education institute, and medical center that should drive up public service quality and customer satisfaction. Accordingly, they make a VOC gathering and analyzing System and then use for making a new product and service, and upgrade. In recent years, innovations in internet and ICT have made diverse channels such as SNS, mobile, website and call-center to collect VOC data. Although a lot of VOC data is collected through diverse channel, the proper utilization is still difficult. It is because the VOC data is made of very emotional contents by voice or text of informal style and the volume of the VOC data are so big. These unstructured big data make a difficult to store and analyze for use by human. So that, the organization need to automatic collecting, storing, classifying and analyzing system for unstructured big VOC data. This study propose an intelligent VOC analyzing system based on opinion mining to classify the unstructured VOC data automatically and determine the polarity as well as the type of VOC. And then, the basis of the VOC opinion analyzing system, called domain-oriented sentiment dictionary is created and corresponding stages are presented in detail. The experiment is conducted with 4,300 VOC data collected from a medical website to measure the effectiveness of the proposed system and utilized them to develop the sensitive data dictionary by determining the special sentiment vocabulary and their polarity value in a medical domain. Through the experiment, it comes out that positive terms such as "칭찬, 친절함, 감사, 무사히, 잘해, 감동, 미소" have high positive opinion value, and negative terms such as "퉁명, 뭡니까, 말하더군요, 무시하는" have strong negative opinion. These terms are in general use and the experiment result seems to be a high probability of opinion polarity. Furthermore, the accuracy of proposed VOC classification model has been compared and the highest classification accuracy of 77.8% is conformed at threshold with -0.50 of opinion classification of VOC. Through the proposed intelligent VOC analyzing system, the real time opinion classification and response priority of VOC can be predicted. Ultimately the positive effectiveness is expected to catch the customer complains at early stage and deal with it quickly with the lower number of staff to operate the VOC system. It can be made available human resource and time of customer service part. Above all, this study is new try to automatic analyzing the unstructured VOC data using opinion mining, and shows that the system could be used as variable to classify the positive or negative polarity of VOC opinion. It is expected to suggest practical framework of the VOC analysis to diverse use and the model can be used as real VOC analyzing system if it is implemented as system. Despite experiment results and expectation, this study has several limits. First of all, the sample data is only collected from a hospital web-site. It means that the sentimental dictionary made by sample data can be lean too much towards on that hospital and web-site. Therefore, next research has to take several channels such as call-center and SNS, and other domain like government, financial company, and education institute.

• Journal of the Korean Society for Library and Information Science
• /
• v.48 no.3
• /
• pp.137-168
• /
• 2014

This study proposed to seek the future development direction of policy information service in Korea by identifying users' needs for policy information and analyzing policy information users' behavior. For this purpose, we analyzed policy information users' needs and behavior through survey and interview methods, and the results are as follows. First, the most common purpose of policy information use was figuring out policy trends, and the Internet was the most common search method used in investigating policy information. Second, electronic resources showed a high rate of use, but the domestic material utilization ratio was higher, and the U.S. resources usage of overseas data was the highest. Third, users most often used materials produced within the last 2-5 years, and Web DB (journals, academic articles, etc.) and reports were the most used material types. Fourth, in the survey of opinion about methods for improving policy information utilization efficiency, cooperation between government agencies' libraries, cooperation between agencies producing the policy information resources, and the overall national collection of policy information were rated the highest.

• Spatial Information Research
• /
• v.17 no.2
• /
• pp.159-169
• /
• 2009

As public participation in the community issues have expanded, an urban planning paradigm has been changed to the planning with public participation. The role of GIS also expanded to support decision making process for the public in addition to supporting that of decision-makers. Residential Environment Improvement, which is the improvement method of an undeveloped urban area, is to regenerate a community based on public participation. However, the current process of public participation is formal. Therefore the purpose of this study is to lead the public a positive participation in Residential Environment Improvement using GIS. We proposed a web_based PPGIS model including project information service, public opinion expression service, two-way communication service and GIS services, and developed a prototype. This model can be a useful tool to make decision makers, experts and the public share their ideas and communicate each other, and to increase the public participation in planning process.

• International Journal of Knowledge Content Development & Technology
• /
• v.9 no.4
• /
• pp.95-114
• /
• 2019

The digitization of traditional medical knowledge in Tanzania will greatly enhance its preservation and dissemination. This is especially important given the challenges facing the current methods of preserving and managing such knowledge. This study presents the requirements engineering approaches and requirements for a web-mobile application that would successfully digitize indigenous knowledge of phytomedicine and relevant practitioners licensing and registration processes. To establish the requirements of such a digital system application, the study sought the opinion of 224 stakeholders whose suggestions were used to analyze and model the requirements for designing such a web-mobile tool. The study was carried out in Arusha, Kagera and Dar es Salaam regions of Tanzania which involved ethnobotanical researchers, herb practitioners, curators from herbaria and registrar officers from Traditional and Alternatives Health Practice Council. Structured interview, survey, observation and document review were employed to find out the basic functional and non-functional requirements for possible designing and implementation a web-mobile application that would digitize indigenous knowledge of medicinal plants. The requirements were modelled using the use case and context diagrams. Finally, the study came up with a list of items for both functional and non-functional requirements that can be used as guidelines to develop a web-mobile application that will capture and document traditional medical knowledge of medicinal plants in Tanzania and, enabling relevant authorities to regulate and manage stakeholders.

• Korean Journal of Health Education and Promotion
• /
• v.24 no.2
• /
• pp.15-28
• /
• 2007

Objectives: In this paper, the survey on internet usage patterns of health consumers was conducted and analyzed in order to determine internet health information assessment criteria for providing correct consumer health information on web-sites. Methods: By using a survey questionnaire with 16 questions on general information and 20 questions on internet health information, data were collected from September 16 to 25, 2005 from 476 participants through an internet web site, http://www.hp.go.kr. Frequency analysis, t-test, and multiple regression were used in order to analyze the difference in assessment criteria, factors influencing assessment criteria, factors influencing user satisfaction, etc. Results: General characteristics of the study population were: the persons over age 40 were the smallest age group; women were accounted for 74.2%; and the persons with average income were the largest income group; and the persons with average health status were the largest health group. Most widely used health information were: exercise, disease, and diet, in order. There was significant difference(p=.001) in importance of assessment criteria between the persons in medical institutions and the persons not in medical institutions. There was no significant difference in other assessment criteria. We also found that contents of websites and easy to use were more important factors than elucidation of information providers and information sources including speciality of information in quality assessment criteria of internet health information. Discussion and Conclusion: Results of this paper were compared with the previous studies from the literatures. Contrary to the previous studies in the literature, there was significant difference in importance of assessment criteria between the persons in medical institutions and the persons not in medical institutions. In order to apply the study results to develop health contents for consumer, there is a need for further upgrade the proposed assessment criteria based on expert opinion.

• Journal of Intelligence and Information Systems
• /
• v.20 no.4
• /
• pp.89-105
• /
• 2014

After emergence of Internet, social media with highly interactive Web 2.0 applications has provided very user friendly means for consumers and companies to communicate with each other. Users have routinely published contents involving their opinions and interests in social media such as blogs, forums, chatting rooms, and discussion boards, and the contents are released real-time in the Internet. For that reason, many researchers and marketers regard social media contents as the source of information for business analytics to develop business insights, and many studies have reported results on mining business intelligence from Social media content. In particular, opinion mining and sentiment analysis, as a technique to extract, classify, understand, and assess the opinions implicit in text contents, are frequently applied into social media content analysis because it emphasizes determining sentiment polarity and extracting authors' opinions. A number of frameworks, methods, techniques and tools have been presented by these researchers. However, we have found some weaknesses from their methods which are often technically complicated and are not sufficiently user-friendly for helping business decisions and planning. In this study, we attempted to formulate a more comprehensive and practical approach to conduct opinion mining with visual deliverables. First, we described the entire cycle of practical opinion mining using Social media content from the initial data gathering stage to the final presentation session. Our proposed approach to opinion mining consists of four phases: collecting, qualifying, analyzing, and visualizing. In the first phase, analysts have to choose target social media. Each target media requires different ways for analysts to gain access. There are open-API, searching tools, DB2DB interface, purchasing contents, and so son. Second phase is pre-processing to generate useful materials for meaningful analysis. If we do not remove garbage data, results of social media analysis will not provide meaningful and useful business insights. To clean social media data, natural language processing techniques should be applied. The next step is the opinion mining phase where the cleansed social media content set is to be analyzed. The qualified data set includes not only user-generated contents but also content identification information such as creation date, author name, user id, content id, hit counts, review or reply, favorite, etc. Depending on the purpose of the analysis, researchers or data analysts can select a suitable mining tool. Topic extraction and buzz analysis are usually related to market trends analysis, while sentiment analysis is utilized to conduct reputation analysis. There are also various applications, such as stock prediction, product recommendation, sales forecasting, and so on. The last phase is visualization and presentation of analysis results. The major focus and purpose of this phase are to explain results of analysis and help users to comprehend its meaning. Therefore, to the extent possible, deliverables from this phase should be made simple, clear and easy to understand, rather than complex and flashy. To illustrate our approach, we conducted a case study on a leading Korean instant noodle company. We targeted the leading company, NS Food, with 66.5% of market share; the firm has kept No. 1 position in the Korean "Ramen" business for several decades. We collected a total of 11,869 pieces of contents including blogs, forum contents and news articles. After collecting social media content data, we generated instant noodle business specific language resources for data manipulation and analysis using natural language processing. In addition, we tried to classify contents in more detail categories such as marketing features, environment, reputation, etc. In those phase, we used free ware software programs such as TM, KoNLP, ggplot2 and plyr packages in R project. As the result, we presented several useful visualization outputs like domain specific lexicons, volume and sentiment graphs, topic word cloud, heat maps, valence tree map, and other visualized images to provide vivid, full-colored examples using open library software packages of the R project. Business actors can quickly detect areas by a swift glance that are weak, strong, positive, negative, quiet or loud. Heat map is able to explain movement of sentiment or volume in categories and time matrix which shows density of color on time periods. Valence tree map, one of the most comprehensive and holistic visualization models, should be very helpful for analysts and decision makers to quickly understand the "big picture" business situation with a hierarchical structure since tree-map can present buzz volume and sentiment with a visualized result in a certain period. This case study offers real-world business insights from market sensing which would demonstrate to practical-minded business users how they can use these types of results for timely decision making in response to on-going changes in the market. We believe our approach can provide practical and reliable guide to opinion mining with visualized results that are immediately useful, not just in food industry but in other industries as well.

• Asian Journal for Public Opinion Research
• /
• v.12 no.1
• /
• pp.53-74
• /
• 2024

The proliferation of health misinformation gained momentum amidst the outbreak of the novel coronavirus disease 2019 (COVID-19). People stuck in their homes, without work pressure, regardless of health concerns towards personal, family, or peer groups, consistently demanded information. People became engaged with misinformation while attempting to find health information content. This study used the content analysis method and analyzed 1,154 misinformation stories from four prominent signatories of the International Fact-Checking Network during the pandemic. The study finds the five main categories of misinformation related to the COVID-19 pandemic. These are 1) the severity of the virus, 2) cure, prevention, and treatment, 3) myths and rumors about vaccines, 4) health authorities' guidelines, and 5) personal and social impacts. Various sub-categories supported the content characteristics of these categories. The study also analyzed the emotional valence of health misinformation. It was found that misinformation containing negative sentiments got higher engagement during the pandemic. Positive and neutral sentiment misinformation has less reach. Surprise, fear, and anger/aggressive emotions highly affected people during the pandemic; in general, people and social media users warning people to safeguard themselves from COVID-19 and creating a confusing state were found as the primary motivation behind the propagation of misinformation. The present study offers valuable perspectives on the mechanisms underlying the spread of health-related misinformation amidst the COVID-19 outbreak. It highlights the significance of discerning the accuracy of information and the feelings it conveys in minimizing the adverse effects on the well-being of public health.