• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1581-1584
• /
• 2015

최근 소셜 네트워크 서비스상의 데이터를 실시간으로 분석하여 의미있는 정보를 찾아내기 위한 연구가 활발하게 진행되고 있다. 특히, 스마트폰과 같은 스마트 디바이스를 이용하는 많은 사용자들이 실시간으로 발생하는 이벤트를 소셜 네트워크상에 게재하고 서로 공유하면서, 대중들이 관심을 가지는 토픽의 경우 굉장히 빠르게 확산되는 경향을 보이고 있다. 본 논문에서는 이러한 SNS의 특성을 토대로 트위터상의 트윗을 분석하여 여러 분야의 토픽들을 카테고리별로 분류하고, 카테고리별 트렌드를 추출하여 실시간으로 시각화하는 기법을 제안한다. 이를 위해, 트위터를 기반으로 SVM 분류 알고리즘과 Twitter-LDA를 통하여 트윗을 분야별로 분류하고, 각각의 트렌드를 이루는 대표적인 키워드를 선출하여 이를 기반으로 실시간 트렌드를 추출한다. 제안하는 기법의 성능을 평가하기 위해, 분류 특징 선택의 신뢰도를 측정한다.

• Journal of The Korean Association For Science Education
• /
• v.42 no.2
• /
• pp.185-200
• /
• 2022

The purpose of this study is to understand the trends and changes of the articles publishing the Journal of the Korean Association for Science Education(JKASE) in the past forty-four years. To this end, Latent Dirichlet Allocation(LDA) topic modeling analysis was performed on a total of 2,115 English abstracts of papers published in the JKASE from 1978 to 2021. As a result of LDA topic modeling analysis, a total of 23 topics were extracted, and each topic was presented with its related keywords and articles. Next, in order to examine how these topics have changed over time, we visualized the average weights of each topic for a 4-year cycle by using heatmaps. The topics that have risen or fallen were identified. The results of this study provide new insights into science education research in Korea in terms of revealing not only traditional research topics that have been consistently studied but also the topics that have changed in response to the development of educational philosophy or research methods, social or policy demands related to science education.

• Journal of Korean Elementary Science Education
• /
• v.41 no.2
• /
• pp.356-372
• /
• 2022

This study examined the topics that have appeared in the "Journal of Korean Elementary Science Education" over the past 50 years to identify the changes that have occurred in the Korean Society of Elementary Science Education. Latent Dirichlet allocation topic modeling was applied to 1,065 English abstracts from the first issue (1983) to 2021, from which 14 main topics were extracted. The meaning of each topic was then analyzed from its keywords and documents. Subsequently, to elucidate the topic trends, the topics' increase or decrease every three years was statistically examined through linear regression analysis. Based on the results, implications for developing and supporting elementary science education research in the future were discussed.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.1
• /
• pp.13-18
• /
• 2019

In this study, we investigate important keywords and their relationships among the keywords for social issues, and analyze topics to find subjects of the social issues. In particular, we collected twitter data with the keyword 'metoo' which has attracted much attention in these days, and perform keyword analysis and topic modeling. First, we preprocess the twitter data, identified important keywords, and analyzed the relatedness of the keywords. After then, topic modeling is performed to find subjects related to 'metoo'. Our experimental results showed that relatedness of keywords and subjects on social issues in twitter are well identified based on keyword analysis and topic modeling.

• Journal of KIISE:Software and Applications
• /
• v.31 no.5
• /
• pp.595-604
• /
• 2004

Automatic analysis of concepts or semantic relations from text documents enables not only an efficient acquisition of relevant information, but also a comparison of documents in the concept level. We present a multiple cause model-based approach to text analysis, where latent topics are automatically extracted from document sets and similarity between documents is measured by semantic kernels constructed from the extracted topics. In our approach, a document is assumed to be generated by various combinations of underlying topics. A topic is defined by a set of words that are related to the same topic or cooccur frequently within a document. In a network representing a multiple-cause model, each topic is identified by a group of words having high connection weights from a latent node. In order to facilitate teaming and inferences in multiple-cause models, some approximation methods are required and we utilize an approximation by Helmholtz machines. In an experiment on TDT-2 data set, we extract sets of meaningful words where each set contains some theme-specific terms. Using semantic kernels constructed from latent topics extracted by multiple cause models, we also achieve significant improvements over the basic vector space model in terms of retrieval effectiveness.

• Journal of Korean Library and Information Science Society
• /
• v.54 no.1
• /
• pp.143-165
• /
• 2023

This study aims to propose a scaffolding strategy that can be applied to the information search process by using Kuhlthau's ISP model, which presented a design and implementation strategy for the mediation role in the learning process. To this end, the relevant literature was reviewed to categorize scaffolding strategies, and impressions were collected from the students surveys after providing 150 middle school students in the Daejeon area with the project class to which the scaffolding strategy based on the ISP model was applied. The collected data were processed into a form suitable for analysis through data preprocessing for word frequencies to be extracted, and topic analysis was performed using STM (Structural Topic Modeling). First, after determining the optimal number of topics and extracting topics for each stage of the ISP model, the extracted topics were classified into three types: cognitive domain-macro perspective, cognitive domain-micro perspective, and emotional domain perspective. In this process, we focused on cognitive verbs and emotional verbs among words extracted through text mining, and presented a scaffolding strategy model related to each topic by reviewing representative document cases. Based on the results of this study, if an appropriate scaffolding strategy is provided at the ISP model stage, a positive effect on learners' self-directed task solving can be expected.

• Journal of Internet Computing and Services
• /
• v.25 no.3
• /
• pp.27-33
• /
• 2024

The environment of academic research is continuously changing due to the increase of information, which raises the need for an effective way to analyze and organize large amounts of documents. In this paper, we propose Performance Improvement of Topic Modeling using BART(Bidirectional and Auto-Regressive Transformers) based Document Summarization. The proposed method uses BART-based document summary model to extract the core content and improve topic modeling performance using LDA(Latent Dirichlet Allocation) algorithm. We suggest an approach to improve the performance and efficiency of LDA topic modeling through document summarization and validate it through experiments. The experimental results show that the BART-based model for summarizing article data captures the important information of the original articles with F1-Scores of 0.5819, 0.4384, and 0.5038 in Rouge-1, Rouge-2, and Rouge-L performance evaluations, respectively. In addition, topic modeling using summarized documents performs about 8.08% better than topic modeling using full text in the performance comparison using the Perplexity metric. This contributes to the reduction of data throughput and improvement of efficiency in the topic modeling process.

• Journal of the Korean Society for information Management
• /
• v.39 no.3
• /
• pp.99-132
• /
• 2022

The purpose of this study is to propose AET (Augmented and Extended Topics), a novel method of synthesizing both LDA and BERTopic results, and to analyze the recently published LIS articles as an experimental approach. To achieve the purpose of this study, 55,442 abstracts from 85 LIS journals within the WoS database, which spans from January 2001 to October 2021, were analyzed. AET first constructs a WORD2VEC-based cosine similarity matrix between LDA and BERTopic results, extracts AT (Augmented Topics) by repeating the matrix reordering and segmentation procedures as long as their semantic relations are still valid, and finally determines ET (Extended Topics) by removing any LDA related residual subtopics from the matrix and ordering the rest of them by F₁ (BERTopic topic size rank, Inverse cosine similarity rank). AET, by comparing with the baseline LDA result, shows that AT has effectively concretized the original LDA topic model and ET has discovered new meaningful topics that LDA didn't. When it comes to the qualitative performance evaluation, AT performs better than LDA while ET shows similar performances except in a few cases.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.131-154
• /
• 2022

Recently, researches on unstructured data analysis have been actively conducted with the development of information and communication technology. In particular, topic modeling is a representative technique for discovering core topics from massive text data. In the early stages of topic modeling, most studies focused only on topic discovery. As the topic modeling field matured, studies on the change of the topic according to the change of time began to be carried out. Accordingly, interest in dynamic topic modeling that handle changes in keywords constituting the topic is also increasing. Dynamic topic modeling identifies major topics from the data of the initial period and manages the change and flow of topics in a way that utilizes topic information of the previous period to derive further topics in subsequent periods. However, it is very difficult to understand and interpret the results of dynamic topic modeling. The results of traditional dynamic topic modeling simply reveal changes in keywords and their rankings. However, this information is insufficient to represent how the meaning of the topic has changed. Therefore, in this study, we propose a method to visualize topics by period by reflecting the meaning of keywords in each topic. In addition, we propose a method that can intuitively interpret changes in topics and relationships between or among topics. The detailed method of visualizing topics by period is as follows. In the first step, dynamic topic modeling is implemented to derive the top keywords of each period and their weight from text data. In the second step, we derive vectors of top keywords of each topic from the pre-trained word embedding model. Then, we perform dimension reduction for the extracted vectors. Then, we formulate a semantic vector of each topic by calculating weight sum of keywords in each vector using topic weight of each keyword. In the third step, we visualize the semantic vector of each topic using matplotlib, and analyze the relationship between or among the topics based on the visualized result. The change of topic can be interpreted in the following manners. From the result of dynamic topic modeling, we identify rising top 5 keywords and descending top 5 keywords for each period to show the change of the topic. Existing many topic visualization studies usually visualize keywords of each topic, but our approach proposed in this study differs from previous studies in that it attempts to visualize each topic itself. To evaluate the practical applicability of the proposed methodology, we performed an experiment on 1,847 abstracts of artificial intelligence-related papers. The experiment was performed by dividing abstracts of artificial intelligence-related papers into three periods (2016-2017, 2018-2019, 2020-2021). We selected seven topics based on the consistency score, and utilized the pre-trained word embedding model of Word2vec trained with 'Wikipedia', an Internet encyclopedia. Based on the proposed methodology, we generated a semantic vector for each topic. Through this, by reflecting the meaning of keywords, we visualized and interpreted the themes by period. Through these experiments, we confirmed that the rising and descending of the topic weight of a keyword can be usefully used to interpret the semantic change of the corresponding topic and to grasp the relationship among topics. In this study, to overcome the limitations of dynamic topic modeling results, we used word embedding and dimension reduction techniques to visualize topics by era. The results of this study are meaningful in that they broadened the scope of topic understanding through the visualization of dynamic topic modeling results. In addition, the academic contribution can be acknowledged in that it laid the foundation for follow-up studies using various word embeddings and dimensionality reduction techniques to improve the performance of the proposed methodology.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.6
• /
• pp.640-645
• /
• 2014

Many people use social network services as to communicate, to share an information and to build social relationships between others on the Internet. Twitter is such a representative service, where millions of tweets are posted a day and a huge amount of data collection has been being accumulated. Social mining that extracts the meaningful information from the massive data has been intensively studied. Typically, Twitter easily can deliver and retweet the contents using the following-follower relationships. Topic modeling in tweet data is a good tool for issue tracking in social media. To overcome the restrictions of short contents in tweets, we introduce a notion of reply graph which is constructed as a graph structure of which nodes correspond to users and of which edges correspond to existence of reply and retweet messages between the users. The LDA topic model, which is a typical method of topic modeling, is ineffective for short textual data. This paper introduces a topic modeling method that uses reply graph to reduce the number of short documents and to improve the quality of mining results. The proposed model uses the LDA model as the topic modeling framework for tweet issue tracking. Some experimental results of the proposed method are presented for a collection of Twitter data of 7 days.