• Title/Summary/Keyword: WORD2VEC

Search Result 224, Processing Time 0.034 seconds

Understanding the semantic change of Hangeul using word embedding (단어 임베딩 기법을 이용한 한글의 의미 변화 파악)

  • Sun, Hyunseok;Lee, Yung-Seop;Lim, Changwon
    • The Korean Journal of Applied Statistics
    • /
    • v.34 no.3
    • /
    • pp.295-308
    • /
    • 2021
  • In recent years, as many people post their interests on social media or store documents in digital form due to the development of the internet and computer technologies, the amount of text data generated has exploded. Accordingly, the demand for technology to create valuable information from numerous document data is also increasing. In this study, through statistical techniques, we investigate how the meanings of Korean words change over time by using the presidential speech records and newspaper articles public data. Using this, we present a strategy that can be utilized in the study of the synchronic change of Hangeul. The purpose of this study is to deviate from the study of the theoretical language phenomenon of Hangeul, which was studied by the intuition of existing linguists or native speakers, to derive numerical values through public documents that can be used by anyone, and to explain the phenomenon of changes in the meaning of words.

Structuring of Unstructured SNS Messages on Rail Services using Deep Learning Techniques

  • Park, JinGyu;Kim, HwaYeon;Kim, Hyoung-Geun;Ahn, Tae-Ki;Yi, Hyunbean
    • Journal of the Korea Society of Computer and Information
    • /
    • v.23 no.7
    • /
    • pp.19-26
    • /
    • 2018
  • This paper presents a structuring process of unstructured social network service (SNS) messages on rail services. We crawl messages about rail services posted on SNS and extract keywords indicating date and time, rail operating company, station name, direction, and rail service types from each message. Among them, the rail service types are classified by machine learning according to predefined rail service types, and the rest are extracted by regular expressions. Words are converted into vector representations using Word2Vec and a conventional Convolutional Neural Network (CNN) is used for training and classification. For performance measurement, our experimental results show a comparison with a TF-IDF and Support Vector Machine (SVM) approach. This structured information in the database and can be easily used for services for railway users.

Design and implementation of a satisfaction and category classifier for game reviews based on deep learning (딥러닝 기반 게임 리뷰 만족도 및 카테고리 분류 시스템 설계 및 개발)

  • Yang, Yu-Jeong;Lee, Bo-Hyun;Kim, Jin-Sil;Lee, Ki Yong
    • Annual Conference of KIPS
    • /
    • 2018.10a
    • /
    • pp.729-732
    • /
    • 2018
  • 모바일 게임 산업의 발달로 많은 사용자들이 게임을 이용하면서, 그들의 만족감을 사용리뷰를 통해 드러낸다. 실제로 각 리뷰의 범주가 모두 다르지만 현재 구글 플레이 앱스토어(Google Play App Store)의 게임 리뷰 범주는 3가지로 매우 제한적이다. 따라서 본 연구에서는 빠르고 정확한 고객의 요구를 필요로 하는 게임 소프트웨어의 특성을 고려하여 게임 리뷰를 입력했을 때, 게임의 운영 및 시스템에 맞도록 리뷰의 카테고리를 세분화하고 만족도를 분석하는 시스템을 개발한다. 제안 시스템은 인공신경망 모델인 CNN을 평점을 기반으로 훈련시켜 리뷰에 대한 만족도를 도출한다. 또한 Word2Vec을 이용해 단어들 간의 유사도를 구하고, 이를 활용한 단어 배열을 이용하여 가장 스코어가 높은 카테고리로 배정한다. 본 논문은 제안한 리뷰 만족도 및 카테고리 분류 시스템이 실제 효과적으로 리뷰를 보다 의미 있는 정보로써 제공할 수 있음을 보인다.

Cross-Domain Text Sentiment Classification Method Based on the CNN-BiLSTM-TE Model

  • Zeng, Yuyang;Zhang, Ruirui;Yang, Liang;Song, Sujuan
    • Journal of Information Processing Systems
    • /
    • v.17 no.4
    • /
    • pp.818-833
    • /
    • 2021
  • To address the problems of low precision rate, insufficient feature extraction, and poor contextual ability in existing text sentiment analysis methods, a mixed model account of a CNN-BiLSTM-TE (convolutional neural network, bidirectional long short-term memory, and topic extraction) model was proposed. First, Chinese text data was converted into vectors through the method of transfer learning by Word2Vec. Second, local features were extracted by the CNN model. Then, contextual information was extracted by the BiLSTM neural network and the emotional tendency was obtained using softmax. Finally, topics were extracted by the term frequency-inverse document frequency and K-means. Compared with the CNN, BiLSTM, and gate recurrent unit (GRU) models, the CNN-BiLSTM-TE model's F1-score was higher than other models by 0.0147, 0.006, and 0.0052, respectively. Then compared with CNN-LSTM, LSTM-CNN, and BiLSTM-CNN models, the F1-score was higher by 0.0071, 0.0038, and 0.0049, respectively. Experimental results showed that the CNN-BiLSTM-TE model can effectively improve various indicators in application. Lastly, performed scalability verification through a takeaway dataset, which has great value in practical applications.

EDGE: An Enticing Deceptive-content GEnerator as Defensive Deception

  • Li, Huanruo;Guo, Yunfei;Huo, Shumin;Ding, Yuehang
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • v.15 no.5
    • /
    • pp.1891-1908
    • /
    • 2021
  • Cyber deception defense mitigates Advanced Persistent Threats (APTs) with deploying deceptive entities, such as the Honeyfile. The Honeyfile distracts attackers from valuable digital documents and attracts unauthorized access by deliberately exposing fake content. The effectiveness of distraction and trap lies in the enticement of fake content. However, existing studies on the Honeyfile focus less on this perspective. In this work, we seek to improve the enticement of fake text content through enhancing its readability, indistinguishability, and believability. Hence, an enticing deceptive-content generator, EDGE, is presented. The EDGE is constructed with three steps: extracting key concepts with a semantics-aware K-means clustering algorithm, searching for candidate deceptive concepts within the Word2Vec model, and generating deceptive text content under the Integrated Readability Index (IR). Furthermore, the readability and believability performance analyses are undertaken. The experimental results show that EDGE generates indistinguishable deceptive text content without decreasing readability. In all, EDGE proves effective to generate enticing deceptive text content as deception defense against APTs.

A Study on the Awareness of Artificial Intelligence Development Ethics based on Social Big Data (소셜 빅데이터 기반 인공지능 개발윤리 인식 분석)

  • Kim, Marie;Park, Seoha;Roh, Seungkook
    • Journal of Engineering Education Research
    • /
    • v.25 no.3
    • /
    • pp.35-44
    • /
    • 2022
  • Artificial intelligence is a core technology in the era of digital transformation, and as the technology level is advanced and used in various industries, its influence is growing in various fields, including social, ethical and legal issues. Therefore, it is time to raise social awareness on ethics of artificial intelligence as a prevention measure as well as improvement of laws and institutional systems related to artificial intelligence development. In this study, we analyzed unstructured data, typically text, such as online news articles and comments to confirm the degree of social awareness on ethics of artificial intelligence development. The analysis showed that the public intended to concentrate on specific issues such as "Human," "Robot," and "President" in 2018 to 2019, while the public has been interested in the use of personal information and gender conflics in 2020 to 2021.

Malware API Classification Technology Using LSTM Deep Learning Algorithm (LSTM 딥러닝 알고리즘을 활용한 악성코드 API 분류 기술 연구)

  • Kim, Jinha;Park, Wonhyung
    • Proceedings of the Korean Institute of Information and Commucation Sciences Conference
    • /
    • 2022.05a
    • /
    • pp.259-261
    • /
    • 2022
  • Recently, malicious code is not a single technique, but several techniques are combined and merged, and only important parts are extracted. As new malicious codes are created and transformed, attack patterns are gradually diversified and attack targets are also diversifying. In particular, the number of damage cases caused by malicious actions in corporate security is increasing over time. However, even if attackers combine several malicious codes, the APIs for each type of malicious code are repeatedly used and there is a high possibility that the patterns and names of the APIs are similar. For this reason, this paper proposes a classification technique that finds patterns of APIs frequently used in malicious code, calculates the meaning and similarity of APIs, and determines the level of risk.

  • PDF

An Automatic Approach for the Recommendation of Bug Report Priority Based on the Stack Trace (Stack Trace 기반 Bug report 우선순위 자동 추천 접근 방안)

  • Lee, JeongHoon;kim, Taeyoung;Choi, Jiwon;Kim, SunTae;Ryu, Duksan
    • Annual Conference of KIPS
    • /
    • 2020.11a
    • /
    • pp.866-869
    • /
    • 2020
  • 소프트웨어 개발 환경이 빠르게 변화함에 따라 시스템의 복잡성이 증가하고 있다. 이에 따라 크고 작은 소프트웨어의 버그를 피할 수 없게 되며 이를 효율적으로 처리하기 위해 Bug report 를 사용한다. 하지만, Bug report 에서 개발자가 해당 Bug report 의 우선순위를 결정하는 과정은 노력과 비용 그리고 시간을 많이 소모하게 만든다. 따라서, 본 논문에서는 Bug report 내의 Stack trace 를 기반으로 Bug 의 우선순위를 자동적으로 추천하는 기법을 제안한다. 이를 위해 본 연구에서는 첫 번째로 Bug report 로부터 Stack trace 를 추출하였으며 Stack trace 의 3 가지 요소(Exception, Reason 그리고 Stack frame)에 TF-IDF, Word2Vec 그리고 Stack overflow 를 사용하여 특징 벡터를 정의하였다. 그리고 Bug 의 우선순위 추천 모델을 생성하기 위해 4 가지의 Classification 알고리즘을(Random Forest, Decision Tree, XGBoost, SVM)을 적용하였다. 평가에서는 266,292 개의 JDK library 의 Bug report 데이터를 수집하였고 그중 Stack trace 를 가진 Bug report 로부터 68%의 정확도를 산출하였다.

Embedding with different levels for idiom disambiguation (관용표현 중의성 해소를 위한 다층위 임베딩 연구)

  • Park, Seo-Yoon;Kang, Ye-Jee;Kang, Hye-Rin;Jang, Yeon-Ji;Kim, Han-Saem
    • Annual Conference on Human and Language Technology
    • /
    • 2021.10a
    • /
    • pp.167-172
    • /
    • 2021
  • 관용표현 중에는 중의성을 가진 표현이 많다. 즉 하나의 표현이 맥락에 따라 일반적 의미와 관용적 의미 두 가지 이상으로 해석될 가능성이 있어 이런 유형의 관용표현을 중의성 해소 없이 자연어 처리 태스크에 적용할 경우 문제가 발생하게 된다. 본 연구에서는 관용표현의 특성인 중의성과 더불어 '관용표현은 이미 사용자의 머릿속에 하나의 토큰으로 저장되어 있다'라는 'Idiom Principle'을 바탕으로 관용표현에 대해 각각 표면형, 단순 단일 토큰형, stemming 단일 토큰형 층위의 임베딩을 만들어 관용표현 분류 연구를 진행하였으며, 실험 결과 표면형 및 stemming을 적용하지 않은 단순 단일 토큰으로 학습하는 것보다, stemming을 적용한 후 단일 토큰으로 학습하는 것이 관용표현의 중의성 해소에 유의미한 효과가 있음을 확인하였다.

  • PDF

Extracting User-Specific Advertising Keywords Based on Textual Data Mining from KakaoTalk (카카오톡에서의 텍스트 데이터 마이닝 기반의 사용자별 적합 광고 키워드 도출 )

  • Yerim Jeon;Dayeong So;Jimin Lee;Eunjin (Jinny) Jo;Jihoon Moon
    • Annual Conference of KIPS
    • /
    • 2023.05a
    • /
    • pp.368-369
    • /
    • 2023
  • 대화 데이터 기반 광고 추천은 광고 마케팅에서 고객 맞춤형 광고 제공, 마케팅 효과 극대화 등을 위한 중요한 기술로 주목받고 있다. 본 논문에서는 모바일 인스턴스 메신저인 카카오톡 대화창에서 발생한 텍스트 데이터를 기반으로 대화 내용을 분석하여 대화 주제별 적절한 광고 키워드를 제안한다. 이를 위해 주제별 대화 내용을 미용, 식음료, 상거래로 세분하고 KoNLPy 의 Okt 를 이용하여 텍스트 전처리를 수행하고 키워드별로 빈도수를 뽑아 워드 클라우드를 제시한다. 또한, 잠재 디리클레 할당(Latent Dirichlet Allocation, LDA)을 기반으로 대화 주제를 세분화한 뒤 라벨링을 통해 주제별 대화 키워드를 분석한다. 실험 결과, 대화 주제를 온라인 쇼핑, 헤어, 뷰티 관리, 음식으로 나눌 수 있었으며, 토픽별 상위 키워드를 Word2Vec 을 통해 특정 단어와 유사한 키워드를 도출하여 적절한 광고 키워드를 제시할 수 있었다.