• The Journal of the Korea Contents Association
• /
• v.15 no.11
• /
• pp.571-581
• /
• 2015

In the field of Korean medicine (KM), KM terms has been mixed used for a long period. After the Society of KM had systematically organized the KM terms used in our country, the book for the Korean medical standard terminologies was published. In this study, we developed an online service based on the book. The online service provides various useful functions for searching the terms and their commentary and collecting users' opinions. Users can also compare the standard terms with their semantic search results and naver's knowledge search results within our system. By analyzing logs of our system, we suggested several directions for future development, including the improvement of search functions, advertisements, and the provision of open APIs. In the future, our online service might provide the important information on clinics, academic researches, and international standards.

• Proceedings of the Korean Information Science Society Conference
• /
• 2010.06c
• /
• pp.285-290
• /
• 2010

인터넷이 대중화됨에 따라 누구나 쉽게 자신의 의견을 온라인상에 표현할 수 있게 되었다. 그 결과 생각이나 느낌을 나타내는 의견 데이터들의 양이 급속도로 방대해졌으며, 이러한 데이터들을 이용한 여러 응용 사례들의 등장으로, 효율적인 검색 및 자동 분류 기술이 요구되고 있다. 이런 기술적 흐름에 맞추어 의견 데이터 분류에 관한 여러 연구들이 이루어져 왔다. 이러한 의견 분류에 대한 연구들을 살펴보면, 분류를 위해 자질(Feature)로서 사용한 단일어(Single word)가 아닌 2개 이상의 N-gram 단어, 어휘 구문 패턴 및 통사 구문 패턴 등을 사용한다. 특히, 패턴은 단일어나 N-gram 단어에 비해 유연하고, 언어학적으로 풍부한 정보를 표현할 수 있기 때문에 이를 주요 연구 주제로 사용되었다. 그럼에도 불구하고, 이러한 연구들은 주로 영어에 대한 연구들이었으며, 한국어에 패턴을 적용하여 주관성을 갖는 문장을 분류하거나, 극성을 분류하는 연구들은 아직 미비하다. 한국어의 특색으로 한국어는 용언의 활용이 발달되어 있어, 어미의 변화가 다양하며, 그 변화에 따라 의미가 미묘하게 변화한다. 그러나 기존 한국어에 대한 의견 분류 연구들은 단어의 핵심 의미만을 파악하기 위해 어미 부분을 제거하고 어간만을 취해서 처리하여 어미에 대한 의미변화를 고려하지 못하므로 분류 정확도가 영어권에 연구 결과에 비해 떨어진다. 그래서 본 연구는 영어에 적용된 패턴을 이용한 기존 방법들을 정리하고, 그 방법들 중에서 극성을 지닌 문장성분 패턴을 한국어에 적용하였다. 그리고 어미의 변화에 대한 패턴을 추출하여 이 변화가 의견 분류의 성능에 미치는 영향을 분석하였다.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.9
• /
• pp.39-47
• /
• 2012

The opinion of user on a certain product is expressed in positive/negative sentiments for specific features of it. In some cases, they are expressed for a holistic part of homogeneous specific features, or expressed for product itself. Therefore, in the area of opinion mining, name of opinion features to be extracted are specific feature names, holonyms for theses specific features, and product names. However, when the opinion target is described with product name or holonym, sometimes it may not match feature name of opinion sentence to true opinion target intended by the reviewer. In this paper, we present a method to extract opinion targets from opinion sentences. Most importantly, we propose a method to extract true target from the feature names mismatched to a intended target. First, we extract candidate opinion pairs using dependency relation between words, and then select feature names frequently mismatched to opinion target. Each selected opinion feature name is replaced to a specific feature intended by the reviewer. Finally, in order to extract relevant opinion features from the whole candidate opinion pairs including modified opinion feature names, candidate opinion pairs are rearranged by the order of user's interest.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.8 no.3
• /
• pp.879-886
• /
• 2018

The basic search engine on Twitter shows not only tweets that contain search keywords, but also all articles written by users with nicknames containing search keywords. Since the tweets unrelated to the search keyword are exposed as search results, it is inconvenient to many users who want to search only tweets that include the keyword. To solve this inconvenience, this study improved the search function of Twitter by developing an algorithm that searches only tweets that contain search keywords. The improved functionality is implemented as a Web service using ASP.NET MVC5 and is available to many users. We used a powerful collection method in C# to retrieve the results of an object, and it was also possible to output them according to the number of 'retweets' or 'favorites'. If the number of retrieved numbers is less than a given number, we also added an exclusion filter function. Thus, sorting search results by the number of retweets or favorites, user can quickly search for opinions that are of interest to many users. It is expected that many users and data analysts will find the developed function convenient to search on Twitter.

• The Journal of Korean Association of Computer Education
• /
• v.7 no.4
• /
• pp.131-140
• /
• 2004

In the latest school spot, practical use about web based multimedia is increasing very greatly. Accordingly, various meta-data element definition to search multimedia data easy is appearing but international standard is presented as the main-stream. Opinion of domestic spot teachers is hardly reflected. Hereupon, in this study, wish to searches multimedia data that is included inside web page reflecting opinion of domestic spot teachers efficiently, defines meta-data element and designs XML DTD for actuality practical use. This study finding sees that can raise public ownership and practical use of multimedia data.

• Annual Conference on Human and Language Technology
• /
• 2010.10a
• /
• pp.179-182
• /
• 2010

트위터, 페이스북 등의 소설 네트워크가 이슈가 되는 사건에 의견을 표시하는 수단으로 많이 활용되고 있다. 본 논문에서는 이슈 키워드 추출 및 트위터와 유투브에 기반한 실시간 검색 시스템을 구현한다. 본 시스템에서는 가장 최근 신문 기사들의 제목과 스니핏을 이용하여 이슈가 되는 키워드를 실시간으로 추출하여 사용자들에게 보여주고 트위터와 유투브 OpenAPI를 이용하여 추출된 키워드에 대한 컨텐츠들을 실시간으로 사용자들에게 보여준다, 본 시스템을 통해서 이슈가 되는 사건에 대한 실시간 반응을 찾을 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.1160-1161
• /
• 2013

현대에 이르러 개인의 힘으로는 해결하기 난해한 문제들이 갈수록 많아지고 있다. 따라서 문제를 해결하기 위한 정보의 유통 구조도 기존의 수직적이고 단방향적인 구조에서 수평적이고 양방향적인 구조로 변화하고 있다. 이에 맞추어 웹 2.0 플랫폼이 대두되었고 위키피디아, 지식 검색 등 집단의 힘을 빌려 문제를 해결하는 방법들이 주목을 받고 있다. 하지만 집단의 힘에 기대어 정보를 생산하는 것이 언제나 옳고 효율적이라고 말할 수 없다. 누구든 참여할 수 있다는 특징으로 인해 악용되는 부작용도 있을뿐더러 전문적인 의견이 필요한 영역의 경우에는 일반 지식의 힘이 도움이 못 되는 경우도 발생할 수 있다. 따라서 본 연구에서는 대중들에게 쉽게 사용되고 있는 검색 사이트와 집단 지성의 대표 사례 중 하나인 위키 피디아를 통해 집단 지성의 힘이 충분히 발휘될 수 있는 문제의 영역에 대해 탐색하고자 한다.

• Journal of Korean Society of Archives and Records Management
• /
• v.23 no.2
• /
• pp.117-135
• /
• 2023

The National Archives of Korea (NAK) operates the NAK Portal as a record search system. However, user search satisfaction is too low, and the number of visitors to the portal is gradually decreasing. This study identifies the portal's issues, proposes feasible improvements, and constructs a pilot system to validate the solutions. The preliminary assessment revealed six major issues, such as poor search tool performance and the lack of consistency in search results. After clarifying the improvement measures, a pilot system was established and compared with the National Records Portal. The evaluation showed significant performance improvements in the pilot system, such as Precision, Recall, and Mean Reciprocal Rank (MRR).

• Journal of Korean Library and Information Science Society
• /
• v.50 no.4
• /
• pp.539-559
• /
• 2019

One of the fundamental roles of libraries is to provide users with efficient and easy retrieval of materials. Various discussions have been made at domestic and abroad to improve the accessibility of materials by category, user, and collection, and at the center of this is the issue of improving classification and cataloging systems. However, there are few studies in this area dealing with the data accessibility of the DLS catalog, which is a central tool for accessing domestic school library materials. This study started from the appeal of school library users to the difficulty of searching and accessing books, especially literature. This study is an exploratory study that attempts to derive problems by finding the causes of there difficulties from various aspects. To this study, we surveyed and analyzed the current status of school library collections, the data registration of the school library support system DLS, the subject accessibility of catalog records produced through this, and the recognition and opinions of school library professionals. As a result, school library collections were highly concentrated in the literature field, and it was found that there was not enough catalog bibliographic records to provide efficient access to these collections. In addition, it was found to be somewhat lacking through the DLS search function to compensate for this. Surveys of school librarians and librarians have also identified this problem, and a rich topic index and search keyword assignments have been drawn to the majority of opinions as a way to improve access to materials in school library catalogs. As a continuous discussion on this subject, the plan for improving access to school library materials will be more concrete through future user studies and new challenges for bookshelf classification.

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.3
• /
• pp.121-128
• /
• 2015

A given product's online product reviews build up to form largely positive or negative reviews or mixed reviews that include both the positive and negative reviews. While the homogeneously positive or negative reviews help readers identify the generally praised or criticized product, the mixed reviews with minority opinions potentially contain valuable information about the product. We present a method of retrieving minority opinions from the online product reviews using the skewness of positive/negative reviews. The proposed method first classifies the positive/negative product reviews using a sentiment dictionary and then calculates the skewness of the classified results to identify minority reviews. Minority review retrieval experiments were conducted on smartphone and movie reviews, and the F1-measures were 24.6% (smartphone) and 15.9% (movie) and the accuracies were 56.8% and 46.8% when the individual reviews' sentiment classification accuracies were 85.3% and 78.8%. The theoretical performance of minority review retrieval is also discussed.