• 한국IT서비스학회지
• /
• 제21권4호
• /
• pp.75-90
• /
• 2022

From the past to the present, reviews have had much influence on consumers' purchasing decisions. Companies are making various efforts, such as introducing a review incentive system to increase the number of reviews. Recently, as various types of reviews can be left, reviews have begun to be recognized as interesting new content. This way, reviews have become essential in creating loyal customers. Therefore, research and utilization of reviews are being actively conducted. Some studies analyze reviews to discover customers' needs, studies that upgrade recommendation systems using reviews, and studies that analyze consumers' emotions and attitudes through reviews. However, research that predicts the future using reviews is insufficient. This study used a dataset consisting of two reviews written in pairs with differences in usage periods. In this study, the direction of consumer product evaluation is predicted using KoBERT, which shows excellent performance in Text Deep Learning. We used 7,233 reviews collected to demonstrate the excellence of the proposed model. As a result, the proposed model using the review text and the star rating showed excellent performance compared to the baseline that follows the majority voting.

• 스마트미디어저널
• /
• 제12권1호
• /
• pp.32-46
• /
• 2023

Natural Language Processing (NLP) has grown tremendously in recent years. Typically, bilingual, and multilingual translation models have been deployed widely in machine translation and gained vast attention from the research community. On the contrary, few studies have focused on translating between spoken and sign languages, especially non-English languages. Prior works on Sign Language Translation (SLT) have shown that a mid-level sign gloss representation enhances translation performance. Therefore, this study presents a new large-scale Korean sign language dataset, the Museum-Commentary Korean Sign Gloss (MCKSG) dataset, including 3828 pairs of Korean sentences and their corresponding sign glosses used in Museum-Commentary contexts. In addition, we propose a translation framework based on self-supervised learning, where the pretext task is a text-to-text from a Korean sentence to its back-translation versions, then the pre-trained network will be fine-tuned on the MCKSG dataset. Using self-supervised learning help to overcome the drawback of a shortage of sign language data. Through experimental results, our proposed model outperforms a baseline BERT model by 6.22%.

• Journal of Information Processing Systems
• /
• 제18권5호
• /
• pp.650-664
• /
• 2022

Mobile applications can be easily downloaded and installed via markets. However, malware and malicious applications containing unwanted advertisements exist in these application markets. Therefore, smartphone users install applications with reference to the application review to avoid such malicious applications. An application review typically comprises contents for evaluation; however, a false review with a specific purpose can be included. Such false reviews are known as fake reviews, and they can be generated using artificial intelligence (AI)-based text-generating models. Recently, AI-based text-generating models have been developed rapidly and demonstrate high-quality generated texts. Herein, we analyze the features of fake reviews generated from Generative Pre-Training-2 (GPT-2), an AI-based text-generating model and create a model to detect those fake reviews. First, we collect a real human-written application review from Kaggle. Subsequently, we identify features of the fake review using natural language processing and statistical analysis. Next, we generate fake review detection models using five types of machine-learning models trained using identified features. In terms of the performances of the fake review detection models, we achieved average F1-scores of 0.738, 0.723, and 0.730 for the fake review, real review, and overall classifications, respectively.

• 정보교육학회논문지
• /
• 제3권2호
• /
• pp.113-119
• /
• 2000

I studied a distance education model for English learning on the Internet. Basic WWW files, that contain courseware, are constructed with HTML, and functions, which are required in learning, are implemented with Java. Students and educators can access the preferred unit composed of the appropriate text, voice and image data by using a WWW browser at any time. The education system supports the automatic generation facility of English problems to practice reading and writing by making good use of the courseware data or various English text resources located on the Internet. Our system has functions to manage and control the flow of distance learning and to offer interaction between students and the system in a distributed environment. Educators can manage students' learning and can immediately be aware of who is attending and who is quitting the lesson in virtual space. Also, students and educators in different places can communicate and discuss a topic through the server. I implemented these functions, which are required in a client/server environment of distance education, with the use of Java. The URL for this system is "http://park.taegu-e.ac.kr" in the name of GAIA.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2022년도 제66차 하계학술대회논문집 30권2호
• /
• pp.505-506
• /
• 2022

인공지능 기술은 점차 빠른 속도로 발전되며 응용 분야가 확대되어 창작 산업에서의 역할도 커져 예술, 영화 및 기타 창조적인 산업에도 영향을 주고 있다. 이러한 인공지능 기술을 이용하여 텍스트로 설명하면 다양한 스타일의 이미지를 생성해내는 기술이 있지만 아동이 직접 그린 손그림 스타일의 그림을 생성하지는 못한다. 본 논문에서는 아동 손그림 데이터를 통해 Text-to-Image를 학습시켜 새로운 학습 모델을 생성하는 과정에 대해서 기술한다. 이 연구를 통해 생성된 픽셀을 결합하여 텍스트를 기반으로 하나의 아동 손그림을 만들 수 있을 것으로 기대한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권12호
• /
• pp.3218-3241
• /
• 2023

Financial fraud undermines the sustainable development of financial markets. Financial statements can be regarded as the key source of information to obtain the operating conditions of listed companies. Current research focuses more on mining financial digital data instead of looking into text data. However, text data can reveal emotional information, which is an important basis for detecting financial fraud. The audit opinion of the financial statement is especially the fair opinion of a certified public accountant on the quality of enterprise financial reports. Therefore, this research was carried out by using the data features of 4,153 listed companies' financial annual reports and audits of text opinions in the past six years, and the paper puts forward a financial fraud detection model integrating audit opinions. First, the financial data index database and audit opinion text database were built. Second, digitized audit opinions with deep learning Bert model was employed. Finally, both the extracted audit numerical characteristics and the financial numerical indicators were used as the training data of the LightGBM model. What is worth paying attention to is that the imbalanced distribution of sample labels is also one of the focuses of financial fraud research. To solve this problem, data enhancement and Focal Loss feature learning functions were used in data processing and model training respectively. The experimental results show that compared with the conventional financial fraud detection model, the performance of the proposed model is improved greatly, with Area Under the Curve (AUC) and Accuracy reaching 81.42% and 78.15%, respectively.

• 지능정보연구
• /
• 제24권3호
• /
• pp.21-44
• /
• 2018

최근 인터넷 기술의 발전과 함께 스마트 기기가 대중화됨에 따라 방대한 양의 텍스트 데이터가 쏟아져 나오고 있으며, 이러한 텍스트 데이터는 뉴스, 블로그, 소셜미디어 등 다양한 미디어 매체를 통해 생산 및 유통되고 있다. 이처럼 손쉽게 방대한 양의 정보를 획득할 수 있게 됨에 따라 보다 효율적으로 문서를 관리하기 위한 문서 분류의 필요성이 급증하였다. 문서 분류는 텍스트 문서를 둘 이상의 카테고리 혹은 클래스로 정의하여 분류하는 것을 의미하며, K-근접 이웃(K-Nearest Neighbor), 나이브 베이지안 알고리즘(Naïve Bayes Algorithm), SVM(Support Vector Machine), 의사결정나무(Decision Tree), 인공신경망(Artificial Neural Network) 등 다양한 기술들이 문서 분류에 활용되고 있다. 특히, 문서 분류는 문맥에 사용된 단어 및 문서 분류를 위해 추출된 형질에 따라 분류 모델의 성능이 달라질 뿐만 아니라, 문서 분류기 구축에 사용된 학습데이터의 질에 따라 문서 분류의 성능이 크게 좌우된다. 하지만 현실세계에서 사용되는 대부분의 데이터는 많은 노이즈(Noise)를 포함하고 있으며, 이러한 데이터의 학습을 통해 생성된 분류 모형은 노이즈의 정도에 따라 정확도 측면의 성능이 영향을 받게 된다. 이에 본 연구에서는 노이즈를 인위적으로 삽입하여 문서 분류기의 견고성을 강화하고 이를 통해 분류의 정확도를 향상시킬 수 있는 방안을 제안하고자 한다. 즉, 분류의 대상이 되는 원 문서와 전혀 다른 특징을 갖는 이질적인 데이터소스로부터 추출한 형질을 원 문서에 일종의 노이즈의 형태로 삽입하여 이질성 학습을 수행하고, 도출된 분류 규칙 중 문서 분류기의 정확도 향상에 기여하는 분류 규칙만을 추출하여 적용하는 방식의 규칙 선별 기반의 앙상블 준지도학습을 제안함으로써 문서 분류의 성능을 향상시키고자 한다.

• 로봇학회논문지
• /
• 제16권3호
• /
• pp.276-282
• /
• 2021

The system for recognizing text in natural scenes has been applied in various industries. However, due to the change in brightness that occurs in nature such as light reflection and shadow, the text recognition performance significantly decreases. To solve this problem, we propose an adversarial shadow generation and training algorithm that is robust to shadow changes. The adversarial shadow generation and training algorithm divides the entire image into a total of 9 grids, and adjusts the brightness with 4 trainable parameters for each grid. Finally, training is conducted in a adversarial relationship between the text recognition model and the shaded image generator. As the training progresses, more and more difficult shaded grid combinations occur. When training with this curriculum-learning attitude, we not only showed a performance improvement of more than 3% in the ICDAR2015 public benchmark dataset, but also confirmed that the performance improved when applied to our's android application text recognition dataset.

• 한국IT서비스학회지
• /
• 제11권sup호
• /
• pp.139-152
• /
• 2012

In the medical web forum, people share medical experience and information as patients and patents' families. Some people search medical information written in non-expert language and some people offer words of comport to who are suffering from diseases. Medical web forums play a role of the informative support and the emotional support. We propose the automatic classification model of articles in the medical web forum into the information support and emotional support. We extract text features of articles in web forum using text mining techniques from the perspective of linguistics and then perform supervised learning to classify texts into the information support and the emotional support types. We adopt the Support Vector Machine (SVM), Naive-Bayesian, decision tree for automatic classification. We apply the proposed model to the HealthBoards forum, which is also one of the largest and most dynamic medical web forum.

• 대한임베디드공학회논문지
• /
• 제17권6호
• /
• pp.347-353
• /
• 2022

In this paper, we propose a method that performs a text-video retrieval model by replacing video properties using captions. In general, the exisiting embedding-based models consist of both joint embedding space construction and the CNN-based video encoding process, which requires a lot of computation in the training as well as the inference process. To overcome this problem, we introduce a video-captioning module to replace the visual property of video with captions generated by the video-captioning module. To be specific, we adopt the caption generator that converts candidate videos into captions in the inference process, thereby enabling direct comparison between the text given as a query and candidate videos without joint embedding space. Through the experiment, the proposed model successfully reduces the amount of computation and inference time by skipping the visual processing process and joint embedding space construction on two benchmark dataset, MSR-VTT and VATEX.