• Journal of the Korean Data and Information Science Society
• /
• v.27 no.4
• /
• pp.845-854
• /
• 2016

Sentiment analysis or opinion mining is a technique of text mining employed to identify subjective information or opinions of an individual from documents in blogs, reviews, articles, or social networks. In the literature, only a problem of binary classification of ratings based on review texts in an online review. However, because there can be positive or negative reviews as well as neutral reviews, a multi-class classification will be more appropriate than the binary classification. To this end, we consider the multi-class classification of ratings based on review texts. In the preprocessing stage, we extract words related with ratings using chi-square statistic. Then the extracted words are used as input variables to multi-class classifiers such as support vector machines and proportional odds model to compare their predictive performances.

• Journal of KIISE:Software and Applications
• /
• v.33 no.11
• /
• pp.986-998
• /
• 2006

There has been an increasing necessity of Semantic Web-based metadata that helps computers efficiently understand and manage an information increased with the growth of Internet. However, it seems inevitable to face some semantically ambiguous information when metadata is generated. Therefore, we need a solution to this problem. This paper proposes a new method for automated metadata generation with the help of a concept of class, in which some ambiguous words imbedded in information such as documents are semantically more related to others, by using probability model of consequent words. We considers ambiguities among defined concepts in ontology and uses the Hidden Markov Model to be aware of part of a named entity. First of all, we constrict a Markov Models a better understanding of the named entity of each class defined in ontology. Next, we generate the appropriate context from a text to understand the meaning of a semantically ambiguous word and solve the problem of ambiguities during generating metadata by searching the optimized the Markov Model corresponding to the sequence of words included in the context. We experiment with seven semantically ambiguous words that are extracted from computer science thesis. The experimental result demonstrates successful performance, the accuracy improved by about 18%, compared with SemTag, which has been known as an effective application for assigning a specific meaning to an ambiguous word based on its context.

• Language and Information
• /
• v.14 no.1
• /
• pp.165-196
• /
• 2010

The primary goal of this paper is to propose methods of enriching two heterogeneous ontologies: Sejong Semantic Classes (SJSC) and KorLexNoun 1.5 (KLN). In order to achieve this goal, this study introduces the pros and cons of two ontologies, and analyzes the error patterns found during the fine-grained manual mapping processes between them. Error patterns can be classified into four types: (1) structural defectives involved in node branching, (2) errors in assigning the semantic classes, (3) deficiency in providing linguistic information, and (4) lack of the lexical units representing specific concepts. According to these error patterns, we propose different solutions in order to correct the node branching defectives and the semantic class assignment, to complement the deficiency of linguistic information, and to increase the number of lexical units suitably allotted to their corresponding concepts. Using the results of this study, we can obtain more enriched ontologies by correcting the defects and errors in each ontology, which will lead to the enhancement of practicality for syntactic and semantic analysis.

• The Journal of the Korea Contents Association
• /
• v.15 no.6
• /
• pp.616-631
• /
• 2015

This study proposes a mobile Augmented Reality (AR)-based "word card" learning tool for children aged 3 to 5. First, this study suggests a learning structure to improve motivation and immersion of learning, Secondly, it designs and implements the user interface applying the proposed learning structure. Also, it designs a content management tool supporting the production of the content so that instructors can easily manage the contents for various learners. This study is conducted by four steps - reference research, design of "word card" learning content for the learner, design of content management tool for the instructor and the effectiveness verification of the proposed content. The proposed content was designed based on an education content architecture for enhancement of immersion and motivation to study. Moreover, it includes an 'AR content management tool for instructor' designed to easily update AR education content. The class for six children aged 3 to 5 was given to validate the enhancement of immersion to study. Experiment results showed that the proposed content enhanced the study immersion and that special interaction design for early children was necessary.

• Journal of Advanced Marine Engineering and Technology
• /
• v.39 no.3
• /
• pp.274-279
• /
• 2015

The main goal of this research is to build a sentiment analysis system which automatically determines user opinions of the Stanford Sentiment Treebank in terms of three sentiments such as positive, negative, and neutral. Firstly, sentiment sentences are POS tagged and parsed to dependency structures. All nodes of the Treebank and their polarities are automatically extracted from the Treebank. We train two Support Vector Machines models. One is for a node level classification and the other is for a sentence level. We have tried various type of features such as word lexicons, POS tags, Sentiment lexicons, head-modifier relations, and sibling relations. Though we acquired 74.2% in accuracy on the test set for 3 class node level classification and 67.0% for 3 class sentence level classification, our experimental results for 2 class classification are comparable to those of the state of art system using the same corpus.

• Journal of The Korean Association of Information Education
• /
• v.8 no.2
• /
• pp.191-201
• /
• 2004

In accordance with wide spread of personal computer and the expansion of network access, the use of internet has been popular and communication by text message is much more normal than that of voice and image. Accordingly, the side effect of communication language brings about gap between diverse social class, the isolation of communication between generations, abusive expressions, obstacles of juvenile mental development and so on. It appears by the form of slang and vulgar word and has a negative effect on education of mother tongue and usage of children's real language. To deal with these problems, we developed new web-based education system through the analysis of learners' requirement; "Barun Mal, Goeun Mal class". So we verified its efficiency to apply to real class. We also found that this system increased the learners' interest and educational effectiveness. Also, this system contributed to the proper use of language.

• Journal of the Korean Institute of Educational Facilities
• /
• v.27 no.3
• /
• pp.33-39
• /
• 2020

The purpose of this study is to understand the classroom facilities of England and USA in the 19th century. This kind of study can provide the meaning of past, present, and future on classroom facilities. The results of the study are as follows. First, England classroom in the 19th century was made up of a large space, a gallery, that could teach a large number of students at the same time. Second, the classroom facilities of USA in the 19th century were developed by reformers for the purpose of training the labor force of educational thought and industrial development. Third, some characteristics of classroom facilities of England and USA in the 19th century were also found in school facilities of Korea at the same time. Fourth, large gallery classes began to disappear in the mid-19th century and were transformed into small 'class' facilities to improve efficiency. Fifth, the word 'class' did not appear as a substitute for the school, but as a meaning of subdividing within the school. Sixth, these classrooms consisted of smaller classes, and they began to create and teach common and unified curriculums to harmonize the differences between classes and to manage all students efficiently and effectively. Seventh, the basis of the classroom of England and USA in the 19th century was the design of one teacher to efficiently teach a large number of students, and there was a difference in size, but the current classroom facilities have been maintained to some extent. Eighth, since the end of the 19th century, the compulsory education system has been discussed and gradually introduced, requiring more schools and classroom facilities, and labor and capital have been emphasized by the development of industrialization. Ninth, follow-up studies are needed to analyze how classroom facilities have been universally transformed since then, based on class facilities in the 19th century, and what educational, social and political contexts have been added in the process.

• The Journal of the Korea Contents Association
• /
• v.6 no.6
• /
• pp.64-73
• /
• 2006

In this paper, I explored the direction of ICT used learning that can improve the access ability of e-learning to activate a neglected class's lifelong education by e-learning. I had a good grasp of a neglected class's actual condition of the access ability of e-learning and presented the direction of basic ICT used learning for the adults that can improve the access ability for the lifelong education by e-learning. According to the result of this research, it was found that the adult learners had a considerable disparity by age group. Therefore, it is desirable that they had to learn ICT used learning with considering the actual condition by age. Teenagers and 20 years of age need to be learned in order of an Internet club, word processor, moving picture and etc. It needs to be teamed for the $30{\sim}40$ age bracket lil order of a chat, an Internet club, searching engines and etc and for the $30{\sim}40$ age bracket in order of a chat, an Internet club and moving picture and etc. And also it needs to induce a neglected class to develope participation abilities for themselves by activating an internet club activity.

• Journal of The Korean Association For Science Education
• /
• v.10 no.2
• /
• pp.67-72
• /
• 1990

Correct comprehension of the scientific terms is the bottom of understanding the general concepts contained is them. Therefore a study is required to analyze whether the students correctly understand the scientific terms. The associative method was used to evaluate the comprehensibility of the terms. The scientific terms in this study are selected in the textbook of science in the junior high school were selected. The frequency of the same associative word responsed and the frequency of no response from the selected students for given scientific terms were measured for 9 different groups. The terms which are not used in the daily life, especially for the terms with chinese character or abstract terms turn out to be difficult for the students to understand. It is purposed that the instructor should remember the importance of understanding the scientific term and carefully explain them to the science class.

• Speech Sciences
• /
• v.12 no.1
• /
• pp.123-134
• /
• 2005

Confidence measure (CM) is used for the rejection of mis-recognized words in an automatic speech recognition (ASR) system. Rahim, Lee, Juang and Cho's confidence measure (RLJC-CM) is one of the widely-used CMs [1]. The RLJC-CM is calculated by averaging phone-level CMs. An extension of the RLJC-CM was achieved by Kim et al [2]. They devised the normalized CM (NCM), which is a statistically normalized version of the RLJC-CM by using the tri-phone based CM normalization. In this paper we verify the NCM by generalizing tri-phone to n-phone unit. To apply various units for the normalization, mono-phone, tri-phone, quin-phone and $\infty$-phone are tested. By the experiments in the domain of the isolated word recognition we show that tri-phone based normalization is sufficient enough to enhance the rejection performance of the ASR system. Also we explain the NCM in regard to two class pattern classification problems.