• International Journal of Computer Science & Network Security
• /
• 제23권6호
• /
• pp.1-12
• /
• 2023

With the rapid increase of user generated data on digital platforms, the task of categorizing and classifying theses huge data has become difficult. Topic modeling is an unsupervised machine learning technique that can be used to get a summary from a large collection of documents. Topic modeling has been widely used in English content, yet the application of topic modeling in Arabic language is limited. Therefore, the aim of this paper is to provide a systematic review of the application of topic modeling algorithms in Arabic content. Using a well-known and trusted databases including ScienceDirect, IEEE Xplore, Springer Link, and Google Scholar. Considering the publication date from 2012 to 2022, we got 60 papers. After refining the papers based on predefined criteria, we resulted in 32 papers. Our result show that unfortunately the application of topic modeling techniques in Arabic content is limited.

• Journal of Information Science Theory and Practice
• /
• 제9권1호
• /
• pp.35-53
• /
• 2021

The study reported in this paper aimed to evaluate the topics and opinions of COVID-19 discussion found on Twitter. It performed topic modeling and sentiment analysis of tweets posted during the COVID-19 outbreak, and compared these results over space and time. In addition, by covering a more recent and a longer period of the pandemic timeline, several patterns not previously reported in the literature were revealed. Author-pooled Latent Dirichlet Allocation (LDA) was used to generate twenty topics that discuss different aspects related to the pandemic. Time-series analysis of the distribution of tweets over topics was performed to explore how the discussion on each topic changed over time, and the potential reasons behind the change. In addition, spatial analysis of topics was performed by comparing the percentage of tweets in each topic among top tweeting countries. Afterward, sentiment analysis of tweets was performed at both temporal and spatial levels. Our intention was to analyze how the sentiment differs between countries and in response to certain events. The performance of the topic model was assessed by being compared with other alternative topic modeling techniques. The topic coherence was measured for the different techniques while changing the number of topics. Results showed that the pooling by author before performing LDA significantly improved the produced topic models.

• 산업경영시스템학회지
• /
• 제44권4호
• /
• pp.113-127
• /
• 2021

Topic modeling has been receiving much attention in academic disciplines in recent years. Topic modeling is one of the applications in machine learning and natural language processing. It is a statistical modeling procedure to discover topics in the collection of documents. Recently, there have been many attempts to find out topics in diverse fields of academic research. Although the first Department of Industrial Engineering (I.E.) was established in Hanyang university in 1958, Korean Institute of Industrial Engineers (KIIE) which is truly the most academic society was first founded to contribute to research for I.E. and promote industrial techniques in 1974. Korean Society of Industrial and Systems Engineering (KSIE) was established four years later. However, the research topics for KSIE journal have not been deeply examined up until now. Using topic modeling algorithms, we cautiously aim to detect the research topics of KSIE journal for the first half of the society history, from 1978 to 1999. We made use of titles and abstracts in research papers to find out topics in KSIE journal by conducting four algorithms, LSA, HDP, LDA, and LDA Mallet. Topic analysis results obtained by the algorithms were compared. We tried to show the whole procedure of topic analysis in detail for further practical use in future. We employed visualization techniques by using analysis result obtained from LDA. As a result of thorough analysis of topic modeling, eight major research topics were discovered including Production/Logistics/Inventory, Reliability, Quality, Probability/Statistics, Management Engineering/Industry, Engineering Economy, Human Factor/Safety/Computer/Information Technology, and Heuristics/Optimization.

• 한국IT서비스학회지
• /
• 제18권4호
• /
• pp.135-149
• /
• 2019

Recently, there are many researches for extracting meaningful information from large amount of text data. Among various applications to extract information from text, topic modeling which express latent topics as a group of keywords is mainly used. Topic modeling presents several topic keywords by term/topic weight and the quality of those keywords are usually evaluated through coherence which implies the similarity of those keywords. However, the topic quality evaluation method based only on the similarity of keywords has its limitations because it is difficult to describe the content of a topic accurately enough with just a set of similar words. In this research, therefore, we propose topic keywords reorganizing method to improve the identifiability of topics. To reorganize topic keywords, each document first needs to be labeled with one representative topic which can be extracted from traditional topic modeling. After that, classification rules for classifying each document into a corresponding label are generated, and new topic keywords are extracted based on the classification rules. To evaluated the performance our method, we performed an experiment on 1,000 news articles. From the experiment, we confirmed that the keywords extracted from our proposed method have better identifiability than traditional topic keywords.

• 지능정보연구
• /
• 제28권1호
• /
• pp.131-154
• /
• 2022

최근 방대한 양의 텍스트 데이터에 대한 분석을 통해 유용한 지식을 창출하는 시도가 꾸준히 증가하고 있으며, 특히 토픽 모델링(Topic Modeling)을 통해 다양한 분야의 여러 이슈를 발견하기 위한 연구가 활발히 이루어지고 있다. 초기의 토픽 모델링은 토픽의 발견 자체에 초점을 두었지만, 점차 시기의 변화에 따른 토픽의 변화를 고찰하는 방향으로 연구의 흐름이 진화하고 있다. 특히 토픽 자체의 내용, 즉 토픽을 구성하는 키워드의 변화를 수용한 다이내믹 토픽 모델링(Dynamic Topic Modeling)에 대한 관심이 높아지고 있지만, 다이내믹 토픽 모델링은 분석 결과의 직관적인 이해가 어렵고 키워드의 변화가 토픽의 의미에 미치는 영향을 나타내지 못한다는 한계를 갖는다. 본 논문에서는 이러한 한계를 극복하기 위해 다이내믹 토픽 모델링과 워드 임베딩(Word Embedding)을 활용하여 토픽의 변화 및 토픽 간 관계를 직관적으로 해석할 수 있는 방안을 제시한다. 구체적으로 본 연구에서는 다이내믹 토픽 모델링 결과로부터 각 시기별 토픽의 상위 키워드와 해당 키워드의 토픽 가중치를 도출하여 정규화하고, 사전 학습된 워드 임베딩 모델을 활용하여 각 토픽 키워드의 벡터를 추출한 후 각 토픽에 대해 키워드 벡터의 가중합을 산출하여 각 토픽의 의미를 벡터로 나타낸다. 또한 이렇게 도출된 각 토픽의 의미 벡터를 2차원 평면에 시각화하여 토픽의 변화 양상 및 토픽 간 관계를 표현하고 해석한다. 제안 방법론의 실무 적용 가능성을 평가하기 위해 DBpia에 2016년부터 2021년까지 공개된 논문 중 '인공지능' 관련 논문 1,847건에 대한 실험을 수행하였으며, 실험 결과 제안 방법론을 통해 다양한 토픽이 시간의 흐름에 따라 변화하는 양상을 직관적으로 파악할 수 있음을 확인하였다.

• International Journal of Computer Science & Network Security
• /
• 제21권9호
• /
• pp.155-162
• /
• 2021

The expansion of the world wide web has led to a huge amount of user generated content over different forums and social media platforms, these rich data resources offer the opportunity to reflect, and track changing public sentiments and help to develop proactive reactions strategies for decision and policy makers. Analysis of public emotions and opinions towards events and sentimental trends can help to address unforeseen areas of public concerns. The need of developing systems to analyze these sentiments and the topics behind them has emerged tremendously. While most existing works reported in the literature have been carried out in English, this paper, in contrast, aims to review recent research works in Arabic language in the field of thematic sentiment analysis and which techniques they have utilized to accomplish this task. The findings show that the prevailing techniques in Arabic topic-based sentiment analysis are based on traditional approaches and machine learning methods. In addition, it has been found that considerably limited recent studies have utilized deep learning approaches to build high performance models.

• 한국정보시스템학회지:정보시스템연구
• /
• 제31권4호
• /
• pp.25-45
• /
• 2022

Purpose In this paper, we propose the method to extend topic modeling techniques in order to derive data-based research hypotheses when establishing research hypotheses for social sciences, As a concept in contrast to the existing deductive hypothesis establishment methodology for the social science research, the topic modeling technique was expanded to enable the so-called inductive hypothesis establishment methodology, and an analysis case of the Seongsan Ilchulbong online review based on the proposed methodology was presented. Design/methodology/approach In this paper, an extension architecture and extension algorithm in the form of extending the existing topic modeling were proposed. The extended architecture and algorithm include data processing method based on topic ratio in document, correlation analysis and regression analysis of processed data for topics derived by existing topic modeling. In addition, in this paper, an analysis case of the online review of Seongsan Ilchulbong Peak was presented by applying the extended topic modeling algorithm. An exploratory analysis was performed on the Seongsan Ilchulbong online reviews through the basic text analysis. The data was transformed into 5-point scale to enable correlation and regression analysis based on the topic ratio in each online review. A regression analysis was performed using the derived topics as the independent variable and the review rating as the dependent variable, and hypotheses could be derived based on this, which enable the so-called inductive hypothesis establishment. Findings This paper is meaningful in that it confirmed the possibility of deriving a causal model and setting an inductive hypothesis through an extended analysis of topic modeling.

• 한국응급구조학회지
• /
• 제26권2호
• /
• pp.19-35
• /
• 2022

Purpose: This study aimed to identify research topics in the emergency medical technician (EMT) field and examine research trends. Methods: In this study, 261 research papers published between January 2000 and May 2022 were collected, and EMT research topics and trends were analyzed using topic modeling techniques. This study used a text mining technique and was conducted using data collection flow, keyword preprocessing, and analysis. Keyword preprocessing and data analysis were done with the RStudio Version 4.0.0 program. Results: Keywords were derived through topic modeling analysis, and eight topics were ultimately identified: patient treatment, various roles, the performance of duties, cardiopulmonary resuscitation, triage systems, job stress, disaster management, and education programs. Conclusion: Based on the research results, it is believed that a study on the development and application of education programs that can successfully increase the emergency care capabilities of EMTs is needed.

• 정보관리학회지
• /
• 제38권4호
• /
• pp.129-152
• /
• 2021

본 연구는 토픽 모델링 및 네트워크 분석 기법을 활용하여 여대생들의 웨어러블 디바이스에 대한 인식 및 선호도 분석, 건강관리에 대한 요구를 분석함으로써 여대생에게 맞는 웨어러블 디바이스 개발 방안을 제시하였다. 이를 위하여 S여자대학교 재학생들이 사용하는 커뮤니티에서 건강관리 및 웨어러블 디바이스와 관련된 게시글 2,457건을 수집하였고. 수집된 게시글과 댓글 데이터를 전처리한 뒤 LDA 기반의 토픽 모델링을 실시하였다. 토픽 모델링 기법을 통해 건강관리 및 웨어러블 디바이스와 관련하여 여대생들의 주요 쟁점들을 도출하고, 관련 키워드가 포함된 포스팅에 대해 바이그램 분석과 네트워크 분석을 수행하여 여대생들이 웨어러블 기기에 대해 가지고 있는 견해를 파악하고자 한다.

• 지능정보연구
• /
• 제23권3호
• /
• pp.69-94
• /
• 2017

최근 빅데이터 분석 수요의 지속적 증가와 함께 관련 기법 및 도구의 비약적 발전이 이루어지고 있으며, 이에 따라 빅데이터 분석은 소수 전문가에 의한 독점이 아닌 개별 사용자의 자가 수행 형태로 변모하고 있다. 또한 전통적 방법으로는 분석이 어려웠던 비정형 데이터의 활용 방안에 대한 관심이 증가하고 있으며, 대표적으로 방대한 양의 텍스트에서 주제를 도출해내는 토픽 모델링(Topic Modeling)에 대한 연구가 활발히 진행되고 있다. 전통적인 토픽 모델링은 전체 문서에 걸친 주요 용어의 분포에 기반을 두고 수행되기 때문에, 각 문서의 토픽 식별에는 전체 문서에 대한 일괄 분석이 필요하다. 이로 인해 대용량 문서의 토픽 모델링에는 오랜 시간이 소요되며, 이 문제는 특히 분석 대상 문서가 복수의 시스템 또는 지역에 분산 저장되어 있는 경우 더욱 크게 작용한다. 따라서 이를 극복하기 위해 대량의 문서를 하위 군집으로 분할하고, 각 군집별 분석을 통해 토픽을 도출하는 방법을 생각할 수 있다. 하지만 이 경우 각 군집에서 도출한 지역 토픽은 전체 문서로부터 도출한 전역 토픽과 상이하게 나타나므로, 각 문서와 전역 토픽의 대응 관계를 식별할 수 없다. 따라서 본 연구에서는 전체 문서를 하위 군집으로 분할하고, 각 하위 군집에서 대표 문서를 추출하여 축소된 전역 문서 집합을 구성하고, 대표 문서를 매개로 하위 군집에서 도출한 지역 토픽으로부터 전역 토픽의 성분을 도출하는 방안을 제시한다. 또한 뉴스 기사 24,000건에 대한 실험을 통해 제안 방법론의 실무 적용 가능성을 평가하였으며, 이와 함께 제안 방법론에 따른 분할 정복(Divide and Conquer) 방식과 전체 문서에 대한 일괄 수행 방식의 토픽 분석 결과를 비교하였다.