• Journal of the Korea Society of Computer and Information
• /
• v.13 no.7
• /
• pp.59-66
• /
• 2008

This paper describes a novel method for identifying the main topic and detecting topic changes in a text-based dialogue as in Instant Messaging (IM). Compared to other forms of text, dialogues are uniquely characterized with the short length of text with small number of words, two or more participants, and existence of a history that affects the current utterance. Noting the characteristics, our method detects the main topic of a dialogue by considering the keywords not only the utterances of the user but also the dialogue system's responses. Dialogue histories are also considered in the detection process to increase accuracy. For topic change detection, the similarity between the former utterance's topic and the current utterance's topic is calculated. If the similarity is smaller than a certain threshold, our system judges that the topic has been changed from the current utterance. We obtained 88.2% and 87.4% accuracy in topic detection and topic change detection, respectively.

• Journal of the Korean Society for information Management
• /
• v.22 no.1 s.55
• /
• pp.191-208
• /
• 2005

This study utilizes various approaches for new topic detection in the process of assigning and updating descriptors, which is a representation method of the knowledge structure. Particularly in the case of occurring changes on the knowledge structure due to the appearance and development of new topics in specific study areas, new topic detection can be applied to solving the impossibility or limitation of the existing index terms in representing subject concepts. This study confirms that the majority of newly developing topics in information science are closely associated with each other and are simultaneously in the phase of growth and development. Also, this study shows the possibility that the use of candidate descriptor lists generated by new topic detection methods can be an effective tool in assisting indexers. In particular. the provision of candidate descriptor lists to help assignment of appropriate descriptors will contribute to the improvement of the effectiveness and accuracy of indexing.

• The Journal of Society for e-Business Studies
• /
• v.14 no.4
• /
• pp.59-73
• /
• 2009

Keyword extraction is an important and essential technique for text mining applications such as information retrieval, text categorization, summarization and topic detection. A set of keywords extracted from a large-scale electronic document data are used for significant features for text mining algorithms and they contribute to improve the performance of document browsing, topic detection, and automated text classification. This paper presents a keyword extraction technique that can be used to detect topics for each news domain from a large document collection of internet news portal sites. Basically, we have used six variants of traditional TF-IDF weighting model. On top of the TF-IDF model, we propose a word filtering technique called 'cross-domain comparison filtering'. To prove effectiveness of our method, we have analyzed usefulness of keywords extracted from Korean news articles and have presented changes of the keywords over time of each news domain.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.12A
• /
• pp.1171-1180
• /
• 2010

In wireless sensor networks, reliable event detection is one of the most important research issues. For the reliable event detection, previous works usually assume the events are only individual objects such as tanks and soldiers. Recently, many researches focus on detection of continuous objects such as wild fire and bio-chemical material, but they merely aim at methods to reduce communication costs. Hence, we propose a reliable continuous object detection scheme. However, it might not be trivial. Unlike individual objects that could be referred as a point, a continuous object is shown in a dynamic two-dimensional diagram since it may cover a wide area and it could dynamically alter its own shape according to physical environments, e.g. geographical conditions, wind, and so on. Hence, the continuous object detection reliability can not be estimated by the indicator for individual objects. This paper newly defines the reliability indicator for continuous object detection and proposes an error recovery mechanism relying on the estimation result from the new indicator.

• Journal of Korean Library and Information Science Society
• /
• v.46 no.1
• /
• pp.321-344
• /
• 2015

This paper presents a fusion approach to sentiment detection that combines multiple sources of evidence to retrieve blogs that contain opinions on a specific topic. Our approach to finding opinionated blogs on topic consists of first applying traditional information retrieval methods to retrieve blogs on a given topic and then boosting the ranks of opinionated blogs based on the opinion scores computed by multiple sentiment detection methods. Our sentiment detection strategy, whose central idea is to rely on a variety of complementary evidences rather than trying to optimize the utilization of a single source of evidence, includes High Frequency module, which identifies opinions based on the frequency of opinion terms (i.e., terms that occur frequently in opinionated documents), Low Frequency module, which makes use of uncommon/rare terms (e.g., "sooo good") that express strong sentiments, IU Module, which leverages n-grams with IU (I and you) anchor terms (e.g., I believe, You will love), Wilson's lexicon module, which uses a collection-independent opinion lexicon constructed from Wilson's subjectivity terms, and Opinion Acronym module, which utilizes a small set of opinion acronyms (e.g., imho). The results of our study show that combining multiple sources of opinion evidence is an effective method for improving opinion detection performance.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2016.07a
• /
• pp.95-96
• /
• 2016

본 논문에서는 디리클레 분포와 베이즈 추론 모델을 활용하여 전자우편을 분류하고 정리하는 방법을 제안한다. 과거 원치 않는 광고성 이메일인 스팸 탐지에서 시작한 전자우편 분류는 지속적인 송수신 량의 증가와 내용의 다양화로 인해 광고성과 정보성의 판단 기준이 모호해진 상태이다. 스팸 탐지와 같은 이분법적 분류 방식이 아닌 내용의 주제 별로 자동 분류할 수 있는 방법이 필요하다. 본 논문에서 다루는 제안 기법은 전자우편의 내용에서 다뤄질 수 있는 주제의 종류를 예측하기 위한 방법을 제공한다. 발신하거나 수신된 전자우편이 속한 주제를 자동으로 정할 수 있다. 본 제안 기법의 활용을 통해 전자우편의 분류만이 아닌 업무 및 시장 동향 분석과 정보보안 분야에서는 악성코드 분류에 사용될 수 있을 것으로 기대된다.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.48 no.5
• /
• pp.45-51
• /
• 2011

In this paper, we propose an unsupervised learning method for modeling motion trajectory patterns effectively. In our approach, observations of an object on a trajectory are treated as words in a document for latent dirichlet allocation algorithm which is used for clustering words on the topic in natural language process. This allows clustering topics (e.g. go straight, turn left, turn right) effectively in complex scenes, such as crossroads. After this procedure, we learn patterns of word sequences in each cluster using Baum-Welch algorithm used to find the unknown parameters in a hidden markov model. Evaluation of abnormality can be done using forward algorithm by comparing learned sequence and input sequence. Results of experiments show that modeling of semantic region is robust against noise in various scene.

• Journal of the Korean Society for information Management
• /
• v.25 no.4
• /
• pp.227-243
• /
• 2008

This study investigates an event detection method with the aim of generating an event-focused news summary from a set of news articles on a certain event using a multi-document summarization technique. The event detection method first classifies news articles into the event related topic categories by employing a SVM classifier and then creates event clusters containing news articles on an event by a modified single pass clustering algorithm. The clustering algorithm applies a time penalty function as well as cluster partitioning to enhance the clustering performance. It was found that the event detection method proposed in this study showed a satisfactory performance in terms of both the F-measure and the detection cost.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.590-593
• /
• 2022

최근 코로나바이러스감염증-19(COVID-19)로 인해서 다양한 비대면 서비스가 증가하고 있는데 그 중에서 사람과 인공지능 간 의사소통하여 정보를 얻는 대화 시스템이 대표적인 서비스이다. 대화 시스템은 입력되는 단일 문장에 대한 정보만을 응답하기 때문에 이전 대화의 정보를 알기 위해서는 질문했던 내용을 다시 입력해야 하는 문제점이 있다. 이런 문제를 해결하고 대화 진행에 도움을 주기 위해서 본 논문에서는 대화 내 문장들의 다중 의도 탐지를 통한 공통 대화 주제 식별 시스템을 제안한다.

• 한국IT서비스학회:학술대회논문집
• /
• 2008.05a
• /
• pp.594-599
• /
• 2008

침입탐지에 있어서 사용자 로그 분석은 중요한 주제로서, 기존의 연구들에서 클러스터링 기법들을 사용하여 저장된 사용자 로그들을 분석해왔다. 하지만, 이러한 방법은 고정된 사용자 패턴 분석에는 효율적이지만, 로그 스트림과 같이 무한히 생성되어 사용자 패턴이 변화하는 경우 변화하는 패턴을 분석할 수 없다. 본 연구에서는 무한히 생성되는 사용자 로그 스트림을 대상으로 실시간 침입탐지 방법을 제시한다. 사용자로그의 정보는 사용자 행동에 대한 특성값으로 표현되어, 이러한 특성값들에 대해 실시간 데이터 스트림 클러스터링을 수행하여 이들을 클러스터로 분류한다. 각 클러스터는 사용자의 정상로그에 대한 특성값을 반영하게 되며, 그 결과 과거 사용자 로그에 대한 저장없이 새로운 로그 스트림을 지속적으로 분석할 수 있다. 결과적으로 사용자의 비정상행동을 실시간으로 탐지할 수 있으며, 이를 실험을 통해 평가하였다.