• Journal of KIISE
• /
• v.44 no.11
• /
• pp.1138-1148
• /
• 2017

Topic extraction is a technology that automatically extracts a set of topics from a set of documents, and this has been a major research topic in the area of natural language processing. Representative topic extraction methods include Latent Dirichlet Allocation (LDA) and word clustering-based methods. However, there are problems with these methods, such as repeated topics and mixed topics. The problem of repeated topics is one in which a specific topic is extracted as several topics, while the problem of mixed topic is one in which several topics are mixed in a single extracted topic. To solve these problems, this study proposes a method to extract topics using an LDA that is robust against the problem of repeated topic, going through the steps of separating and merging the topics using the similarity between words to correct the extracted topics. As a result of the experiment, the proposed method showed better performance than the conventional LDA method.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06c
• /
• pp.240-243
• /
• 2011

웹 문서를 비롯한 여러 가지 문서의 양이 급증함에 따라, 문서로부터 주요정보를 얻거나 자동으로 요약하는 연구들이 진행되어왔다. 특히, 문서를 요약하는 연구들은 문서에 존재하는 문장을 추출하는 방법과 요약문을 새롭게 생성하는 방법, 이렇게 크게 두 가지 방법으로 진행되었다. 이 연구에서는, 잠재 토픽 모델을 통하여 얻어낸 각 문장의 토픽 순열을 이용하여 문서를 대표하는 문장, 즉 요약문으로서 적합한 문장들을 추출하는 새로운 기법을 소개한다. 특히, 잠재 토픽 모델이 일반적으로 가지고 있는 속성인 토픽 순열의 교환성(exchangeability)을 배제하고 토픽의 순열을 이용하여 요약문을 추출해내므로 이 기법을 통하여 문서 혹은 문장의 구조를 반영한 요약문을 만들 수 있다.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.164-169
• /
• 2022

토픽 모델링은 비즈니스 분석이나 기술 동향 파악 등 다방면에서 많이 사용되고 있는 기술이다. 하지만 대표적인 방법인 LDA와 같은 비지도학습의 경우, 그 알고리즘 구조상 문서의 수가 많을 때 토픽 모델링이 가능하다. 본 논문에서는 문서의 수가 적은 경우도, 키워드 및 키프레이즈를 이용한 군집화를 통해 토픽 모델링을 하고 감성분석을 통해 토픽에 대한 분석도 제시하였다. 이에 필요한 데이터 제작 및 키워드 추출, 키워드 기반 감성분석, 키워드 임베딩 및 군집화를 구현하였고, 결과를 정성적으로 보았을 때 유의미한 분석이 되는 것을 확인하였다.

• Journal of Digital Convergence
• /
• v.18 no.5
• /
• pp.75-87
• /
• 2020

The present study determined new value that can be created through the convergence between artificial intelligence technology (AIT) and all industries by deriving and thoroughly analyzing major issues related to artificial intelligence (AI). This study analyzes domestic articles related to AI using topic modeling method based on LDA algorithm. Keywords were extracted from 3,889 articles of eleven metropolitan newspapers, eight business newspapers and major broadcasting companies; articles were selected by searching for the keyword "artificial intelligence". Keywords were extracted by optimizing the relevance parameter λ to improve the measure of pointwise mutual information (PMI), which shows the association among the keywords of each topic, and topic names were inferred from keywords based on valid evidence. The extracted topics widely showed changes occurring throughout society, economy, industries, culture, and the support policy and vision of the government.

• Information and Communications Magazine
• /
• v.34 no.6
• /
• pp.43-50
• /
• 2017

본고에서는 소셜 빅데이터에서 공공안전에 위협되고 사회적으로 이슈가 되는 재난사건을 추출하기 위한 방법으로 소셜 네트워크상에서 사용자 행동 분석과 시간분석을 반영한 토픽 모델링 기법을 알아본다. 소셜 사용자의 글 수, 리트윗 반응, 활동주기, 팔로워 수, 팔로잉 수 등 사용자의 행동 분석을 통하여 활동적이고 신뢰성 있는 사용자를 분류함으로써 트윗에서 스팸성과 광고성을 제외하고 이슈에 대해 신뢰성 높은 사용자가 쓴 트윗을 중요하게 반영한다. 또한, 트위터 데이터에서 새로운 이슈가 발생한 것을 탐지하기 위해 시간별 핵심어휘 빈도의 분포 변화를 측정하고, 이슈 트윗에 대해 감성 표현 분석을 통해 핵심이슈에 대해 사건 어휘를 추출한다. 소셜 빅데이터의 특성상 같은 날짜에 여러 이슈에 대한 트윗이 많이 생성될 수 있기 때문에, 트윗들을 토픽별로 그룹핑하는 것이 필요하므로, 최근 많이 사용되고 있는 LDA 토픽모델링 기법에 시간 특성과 사용자 특성을 분석한 시간상에서의 중요한 사건 어휘를 반영하고, 해당이슈에 대한 신뢰성 있는 사용자가 쓴 트윗을 중요시 반영하도록 토픽모델링 기법을 개선한 소셜 사건 탐지 방법에 대해 알아본다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.5
• /
• pp.207-214
• /
• 2020

Nowadays, the use of smart phones and various electronic devices is increasing, the Internet and SNS are activated, and we live in the flood of information. The amount of information has grown exponentially, making it difficult to look at a lot of information, and more and more people want to see only key keywords in a document, and the importance of research to extract topics that are the core of information is increasing. In addition, it is also an important issue to extract the topic and compare it with the past to infer the current trend. Topic modeling techniques can be used to extract topics from a large volume of documents, and these extracted topics can be used in various fields such as trend prediction and data analysis. In this paper, we inquire the topic of the three-year papers of 2016, 2017, and 2018 in the field of computing using the LDA algorithm, one of Probabilistic Topic Model Techniques, in order to analyze the rapidly changing trends and keep pace with the times. Then we analyze trends and flows of research.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.11
• /
• pp.521-526
• /
• 2016

As on-line informal text data have massive in its volume and have unstructured characteristics in nature, there are limitations in applying traditional relational data model technologies for data storage and data analysis jobs. Moreover, using dynamically generating massive social data, social user's real-time reaction analysis tasks is hard to accomplish. In the paper, to capture easily the semantics of massive and informal on-line documents with unsupervised learning mechanism, we design and implement automatic topic extraction systems according to the mass of the words that consists a document. The input data set to the proposed system are generated first, using N-gram algorithm to build multiple words to capture the meaning of the sentences precisely, and Hadoop and Spark (In-memory distributed computing framework) are adopted to run topic model. In the experiment phases, TB level input data are processed for data preprocessing and proposed topic extraction steps are applied. We conclude that the proposed system shows good performance in extracting meaningful topics in time as the intermediate results come from main memories directly instead of an HDD reading.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.55-65
• /
• 2023

In this paper, we apply KeyBERT(Keyword extraction with Bidirectional Encoder Representations of Transformers) algorithm-driven topic extraction and topic frequency analysis to deep learning and reinforcement learning research to discover the rapidly changing trends in them. First, we crawled abstracts of research papers on deep learning and reinforcement learning, and temporally divided them into two groups. After pre-processing the crawled data, we extracted topics using KeyBERT algorithm, and then analyzed the extracted topics in terms of topic occurrence frequency. This analysis reveals that there are distinct trends in research work of all analyzed algorithms and applications, and we can clearly tell which topics are gaining more interest. The analysis also proves the effectiveness of the utilized topic extraction and topic frequency analysis in research trend analysis, and this trend analysis scheme is expected to be used for research trend analysis in other research fields. In addition, the analysis can provide insight into how deep learning will evolve in the near future, and provide guidance for select research topics and methodologies by informing researchers of research topics and methodologies which are recently attracting attention.

• KIISE Transactions on Computing Practices
• /
• v.23 no.4
• /
• pp.217-225
• /
• 2017

Recently, the interest in predicting hot topics has grown significantly as it has become more important to find and analyze meaningful information from a large amount of data flowing in social networking services. Existing hot topic detection schemes do not consider a temporal property, so they are not suitable to predict hot topics that are rapidly issued in a changing society. This paper proposes a hot topic prediction scheme that uses a modified TF-IDF in social networking environments. The modified TF-IDF extracts a candidate set of keywords that are momentarily issued. The proposed scheme then calculates the hot topic prediction scores by assigning weights considering user influence and professionality to extract the candidate keywords. The superiority of the proposed scheme is shown by comparing it to an existing detection scheme. In addition, to show whether or not it predicts hot topics correctly, we evaluate its quality with Korean news articles from Naver.

• The Journal of the Korea Contents Association
• /
• v.22 no.6
• /
• pp.1-14
• /
• 2022

This study aims to identify topics in newspaper articles related to fine particle matter and to investigate the characteristics and time series trend of each topic. Related national newspaper articles during 1990 and 2021 were collected from Bigkinds. A total of 18 topics have been discovered using LDA, and 11 clusters deduced from clustering. Hot topics include related products/residence, overseas cause(China), power plant as a domestic cause, nationwide emergency reduction measures, international cooperation, political issues, current situation & countermeasure in other countries, and consumption patterns. Cold topics include the concentration standard and indoor air quality improvement. These findings would be useful in inferring the political direction and strategies. In particular, the consumer protection policy should be expanded as the related market is growing. It will also be necessary to pursue policies that will promote public safety and health, and that will enhance public consensus and international cooperation.