• International Journal of Computer Science & Network Security
• /
• 제24권10호
• /
• pp.25-31
• /
• 2024

Currently, on social media, malicious comments have emerged as a serious issue. Existing artificial intelligence-based comment classification systems have limitations due to data bias and overfitting. To address this, this study proposed a novel comment classification system that combines crowdsourcing and federated learning. This system collects data from various users and utilizes a large language model like KoBERT through federated learning to classify comments accurately while protecting user privacy. It is expected to provide higher accuracy than existing methods and improve significantly the efficiency of detecting malicious comments. The proposed system can be applied to social media platforms and online communities.

• 한국융합학회논문지
• /
• 제11권6호
• /
• pp.23-28
• /
• 2020

인터넷상의 소통을 위해 댓글 시스템은 필수적이다. 하지만 온라인상의 익명성을 악용하여 타인에 대한 부적절한 표현 등의 악성 댓글 또한 존재한다. 악성 댓글로부터 사용자를 보호하기 위해 악성/정상 댓글의 분류가 필요하고 이는 텍스트 분류로 구현할 수 있다. 자연어 처리에서 텍스트 분류는 중요한 주제 중 하나이고 최근 BERT 등 pretrained model을 활용한 연구와 GCN, GAT 등의 그래프 구조를 활용한 연구가 활발히 진행되고 있다. 본 연구에서는 실제 공개된 댓글에 대해 BERT, GCN, GAT 을 활용하여 댓글 분류 시스템을 구현하고 성능을 비교하였다. 본 연구에서는 그래프 기반 모델을 사용한 시스템이 BERT 대비 높은 성능을 보여주었다.

• Journal of Information Processing Systems
• /
• 제16권2호
• /
• pp.329-342
• /
• 2020

In recent years, emotional text classification is one of the essential research contents in the field of natural language processing. It has been widely used in the sentiment analysis of commodities like hotels, and other commentary corpus. This paper proposes an improved W-LDA (weighted latent Dirichlet allocation) topic model to improve the shortcomings of traditional LDA topic models. In the process of the topic of word sampling and its word distribution expectation calculation of the Gibbs of the W-LDA topic model. An average weighted value is adopted to avoid topic-related words from being submerged by high-frequency words, to improve the distinction of the topic. It further integrates the highest classification of the algorithm of support vector machine based on the extracted high-quality document-topic distribution and topic-word vectors. Finally, an efficient integration method is constructed for the analysis and extraction of emotional words, topic distribution calculations, and sentiment classification. Through tests on real teaching evaluation data and test set of public comment set, the results show that the method proposed in the paper has distinct advantages compared with other two typical algorithms in terms of subject differentiation, classification precision, and F1-measure.

• 한국정보통신학회논문지
• /
• 제24권5호
• /
• pp.576-583
• /
• 2020

이 논문은 최근 엄청난 성장을 하고 있는 유튜브의 댓글 중 스팸 댓글을 판별하는 기법을 제안한다. 유튜브에서는 광고를 통한 수익 창출이 가능하기 때문에 인기 동영상에서 자신의 채널이나 동영상을 홍보하거나 영상과 관련 없는 댓글을 남기는 스패머(spammer)들이 나타났다. 유튜브에서는 자체적으로 스팸 댓글을 차단하는 시스템을 운영하고 있지만 여전히 제대로 차단하지 못한 스팸 댓글들이 있다. 따라서, 유튜브 스팸 댓글 판별에 대한 관련 연구들을 살펴 보고 인기 동영상인 싸이, 케이티 페리, LMFAO, 에미넴, 샤키라의 뮤직비디오 댓글 데이터에 6가지 머신러닝 기법(의사결정나무, 로지스틱 회귀분석, 베르누이 나이브 베이즈, 랜덤 포레스트, 선형 커널을 이용한 서포트 벡터 머신, 가우시안 커널을 이용한 서포트 벡터 머신)과 이들을 결합한 앙상블 모델로 스팸 탐지 실험을 진행하였다.

• Journal of Preventive Medicine and Public Health
• /
• 제49권2호
• /
• pp.139-140
• /
• 2016

• East Asian mathematical journal
• /
• 제37권5호
• /
• pp.599-612
• /
• 2021

In China, Weibo is one of the social platforms with more users. It has the characteristics of fast information transmission and wide coverage. People can comment on a certain event on Weibo to express their emotions and attitudes. Judging the emotional tendency of users' comments is not only beneficial to the monitoring of the management department, but also has very high application value for rumor suppression, public opinion guidance, and marketing. This paper proposes a two-input Adaboost model based on TextCNN and BiLSTM. Use the TextCNN model that can perform local feature extraction and the BiLSTM model that can perform global feature extraction to process comment data in parallel. Finally, the classification results of the two models are fused through the improved Adaboost algorithm to improve the accuracy of text classification.

• 대한두개안면성형외과학회지
• /
• 제24권3호
• /
• pp.143-144
• /
• 2023

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2021년도 추계학술발표대회
• /
• pp.864-867
• /
• 2021

뉴스, SNS 등의 인터넷 댓글은 익명으로 의견을 자유롭게 개진할 수 있는 반면 댓글의 익명성을 악용하여 비방이나 험담을 하는 악성 댓글이 여러 분야에서 사회적 문제가 되고 있다. 해당 문제를 해결하기 위해 AI를 활용한 댓글 분류 알고리즘을 개발하려는 많은 노력들이 이루어지고 있지만, 댓글 분류 모델에 사용되는 AI는 오버피팅의 문제로 인해 댓글 분류에 대한 정확도가 떨어지는 문제점을 가지고 있다. 이에 본 연구에서는 크라우드소싱을 활용하여 오버피팅으로 인한 악성 댓글 분류 및 판단 정확도 저하 문제를 개선한 크라우드소싱 기반 딥러닝 분류 알고리즘(Deep Learning Classification Algorithm Based on Crowdsourcing: DCAC)과 해당 알고리즘을 사용한 시스템을 제안한다. 또한, 실험을 통해 오버피팅으로 낮아진 판단 정확도를 증가시키는 데 제안된 방법이 도움이 되는 것을 확인하였다.

• IEIE Transactions on Smart Processing and Computing
• /
• 제3권5호
• /
• pp.319-324
• /
• 2014

Web applications make life more convenient. Many web applications have several kinds of user input (e.g. personal information, a user's comment of commercial goods, etc.) for the activities. On the other hand, there are a range of vulnerabilities in the input functions of Web applications. Malicious actions can be attempted using the free accessibility of many web applications. Attacks by the exploitation of these input vulnerabilities can be achieved by injecting malicious web code; it enables one to perform a variety of illegal actions, such as SQL Injection Attacks (SQLIAs) and Cross Site Scripting (XSS). These actions come down to theft, replacing personal information, or phishing. The existing solutions use a parser for the code, are limited to fixed and very small patterns, and are difficult to adapt to variations. A machine learning method can give leverage to cover a far broader range of malicious web code and is easy to adapt to variations and changes. Therefore, this paper suggests the adaptable classification of malicious web code by machine learning approaches for detecting the exploitation user inputs. The approach usually identifies the "looks-like malicious" code for real malicious code. More detailed classification using sequence information is also introduced. The precision for the "looks-like malicious code" is 99% and for the precise classification with sequence is 90%.

• Journal of Information Processing Systems
• /
• 제19권6호
• /
• pp.842-857
• /
• 2023

Currently, most sentiment classification models on microblogging platforms analyze sentence parts of speech and emoticons without comprehending users' emotional inclinations and grasping moral nuances. This study proposes a hybrid sentiment analysis model. Given the distinct nature of microblog comments, the model employs a combined stop-word list and word2vec for word vectorization. To mitigate local information loss, the TextCNN model, devoid of pooling layers, is employed for local feature extraction, while BiLSTM is utilized for contextual feature extraction in deep learning. Subsequently, microblog comment sentiments are categorized using a classification layer. Given the binary classification task at the output layer and the numerous hidden layers within BiLSTM, the Tanh activation function is adopted in this model. Experimental findings demonstrate that the enhanced TextCNN-BiLSTM model attains a precision of 94.75%. This represents a 1.21%, 1.25%, and 1.25% enhancement in precision, recall, and F1 values, respectively, in comparison to the individual deep learning models TextCNN. Furthermore, it outperforms BiLSTM by 0.78%, 0.9%, and 0.9% in precision, recall, and F1 values.