• Digital Contents
• /
• no.4 s.131
• /
• pp.100-104
• /
• 2004

처음 웨더뉴스 사이트에 대한 분석 요청을 받을 때 기자로부터의 요구사항은 사이트의 다른 부분, 이를테면 프리젠테이션 영역이나 수집방법, 비즈니스 로직보다는 데이터베이스 그 자체에 초점을 맞춰달라는 것이었다. 실상‘데이터베이스’라는 것은‘데이터’ 와는 조금 다른 성향을 가지고 있다. ‘데이터’는 세상의 모든 사물, 모든 사물이 운동하는 형상, 인간의 감각기관이나 그 외의 다양한 방법으로 인지할 수 있는 모든 수치화될 수 있거나 그렇지 못한 것까지를 포함하는 포괄적인 개념이다. 그러나‘데이터베이스’는 이러한 추상적인 개념과는 근본적으로 달리 현상에 있는 수많은 데이터중 필요한 데이터를 수집하는 것이 기본이며, 이를 저장하고 필요에 의해 원하는 방법대로 꺼내어 볼 수 있도록 하는 것까지를 모두 갖춰 하나의 시스템이 되어야만 비로소 하나의 데이터베이스가 되는 근본 요소가 갖춰졌다고 할 수 있는 것이다. 이번 글에서는 웨더뉴스사가 날씨 정보를 실시간으로 또한 안정적으로 운영하기 위한 노력과 이를 비즈니스화 한 방안, 그리고 다양한 디스플레이 방법을 살펴보도록 하겠다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.763-766
• /
• 2019

최근 사람들의 삶의 질이 향상됨에 따라 기호품인 와인의 수요가 늘어나고 있다. 그러나 와인은 생산하는데 길게는 수십 년이 걸리는 고가의 제품이므로 소비자가 와인과 잘못 구매했을 때의 기회비용이 크다. 본 논문에서는 전문 와인 테이스터 들의 후기 빅 데이터를 활용하여 딥러닝 기반 추천시스템을 개발을 다룬다. 테이스터 들의 후기 빅 데이터에 대해 Apache Pig와 자연어 처리를 통한 전 처리 과정을 수행해 리뷰 별로 특징 벡터를 구성하고, 하이퍼 매개변수 최적화와 조기 종료 기법을 사용해 데이터에 대하여 최적의 딥러닝 분류기를 구성하였다. 마지막으로, 구성된 시스템의 신뢰도를 검증하기 위해서 딥러닝의 정확도와 오차율을 확인하였고 시스템이 추천한 와인을 시각화 이미지와 비교하여 성능을 검증하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.355-356
• /
• 2023

본 논문에서는 지도 앱이 제공하는 식당의 시간별 평균 방문자 수 데이터와 공공 DB의 면적 데이터를 활용하여 식당의 대기 시간을 예측하여 출력해주는 모델을 제안한다. 요식업에 관련된 통계 데이터를 활용해 식당 홀이 차지하는 면적을 추정한 뒤, 식당의 예상 수용 인원을 추정하여 여기에 평균 테이블 회전율을 적용하여, 식당의 시간 당 수용 인원을 추정식당의 대기 시간을 계산한다. 거기에 사용자 리뷰와 식당 별점 데이터 등의 외부 요인을 통해 대기 시간을 보정, 예상 대기 시간의 정확도 상승을 꾀한다. 이 모델이 상용화 될시, 이용자는 식당 선택에 의해 야기되는 스트레스를 완화시킬 수 있고, 식당 이용자들의 분산효과를 낳을 수 있을 것이다.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.57-78
• /
• 2020

With the development of the Internet, consumers have had an opportunity to check product information easily through E-Commerce. Product reviews used in the process of purchasing goods are based on user experience, allowing consumers to engage as producers of information as well as refer to information. This can be a way to increase the efficiency of purchasing decisions from the perspective of consumers, and from the seller's point of view, it can help develop products and strengthen their competitiveness. However, it takes a lot of time and effort to understand the overall assessment and assessment dimensions of the products that I think are important in reading the vast amount of product reviews offered by E-Commerce for the products consumers want to compare. This is because product reviews are unstructured information and it is difficult to read sentiment of reviews and assessment dimension immediately. For example, consumers who want to purchase a laptop would like to check the assessment of comparative products at each dimension, such as performance, weight, delivery, speed, and design. Therefore, in this paper, we would like to propose a method to automatically generate multi-dimensional product assessment scores in product reviews that we would like to compare. The methods presented in this study consist largely of two phases. One is the pre-preparation phase and the second is the individual product scoring phase. In the pre-preparation phase, a dimensioned classification model and a sentiment analysis model are created based on a review of the large category product group review. By combining word embedding and association analysis, the dimensioned classification model complements the limitation that word embedding methods for finding relevance between dimensions and words in existing studies see only the distance of words in sentences. Sentiment analysis models generate CNN models by organizing learning data tagged with positives and negatives on a phrase unit for accurate polarity detection. Through this, the individual product scoring phase applies the models pre-prepared for the phrase unit review. Multi-dimensional assessment scores can be obtained by aggregating them by assessment dimension according to the proportion of reviews organized like this, which are grouped among those that are judged to describe a specific dimension for each phrase. In the experiment of this paper, approximately 260,000 reviews of the large category product group are collected to form a dimensioned classification model and a sentiment analysis model. In addition, reviews of the laptops of S and L companies selling at E-Commerce are collected and used as experimental data, respectively. The dimensioned classification model classified individual product reviews broken down into phrases into six assessment dimensions and combined the existing word embedding method with an association analysis indicating frequency between words and dimensions. As a result of combining word embedding and association analysis, the accuracy of the model increased by 13.7%. The sentiment analysis models could be seen to closely analyze the assessment when they were taught in a phrase unit rather than in sentences. As a result, it was confirmed that the accuracy was 29.4% higher than the sentence-based model. Through this study, both sellers and consumers can expect efficient decision making in purchasing and product development, given that they can make multi-dimensional comparisons of products. In addition, text reviews, which are unstructured data, were transformed into objective values such as frequency and morpheme, and they were analysed together using word embedding and association analysis to improve the objectivity aspects of more precise multi-dimensional analysis and research. This will be an attractive analysis model in terms of not only enabling more effective service deployment during the evolving E-Commerce market and fierce competition, but also satisfying both customers.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.4
• /
• pp.9-21
• /
• 2024

Deep learning has been developing rapidly in recent years, with many researchers working to utilize large language models in various domains. However, there are practical difficulties that developing and utilizing language models require massive data and high-performance computing resources. Therefore, in-context learning, which utilizes prompts to learn efficiently, has been introduced, but there needs to be clear criteria for effective prompts for learning. In this study, we propose a methodology for enhancing prompt-based learning performance by improving the PET technique, which is one of the contextual learning methods, to select PVPs that are similar to the context of existing data. To evaluate the performance of the proposed methodology, we conducted experiments with 30,100 restaurant review datasets collected from Yelp, an online business review platform. We found that the proposed methodology outperforms traditional PET in all aspects of accuracy, stability, and learning efficiency.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.1
• /
• pp.380-386
• /
• 2020

The mobile application market has grown over the past decade since the advent of smartphones, making it the largest market for electronic device software. As competition intensifies in the mobile application market, the impact of application evaluations on the consumption and usage patterns of users has also significantly increased. Therefore, research has been conducted on measures to evaluate mobile applications, but most of the research has relied on qualitative methods such as expert-centered interviews or surveys. In addition, evaluation measures are being constructed from the service provider's perspective, not from the service user's perspective. However, the possibility of application-specific analyses that minimize the subjectivity of researchers is growing, as large amounts of user review data enable quantitative analysis of actual users' assessment of applications. Therefore, this study presents a methodology that can complement current problems with existing quality assessments for mobile applications by utilizing user review data. To this end, the Topic Modeling technique LDA (Latent Dirichlet allocation) is applied in order to elucidate ways to improve existing evaluation measures from a user's perspective. The study is expected to reduce bias in service assessment due to the subjectivity of service providers and researchers as well as provide a measure of assessment by area of mobile applications from a consumer perspective.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.3
• /
• pp.1-12
• /
• 2024

In this paper, we fine-tuned KoAlpaca, a large-scale Korean language model, and implemented a blog text generation system utilizing it. Blogs on social media platforms are widely used as a marketing tool for businesses. We constructed training data of positive reviews through emotion analysis and refinement of collected sponsored blog texts and applied QLoRA for the lightweight training of KoAlpaca. QLoRA is a fine-tuning approach that significantly reduces the memory usage required for training, with experiments in an environment with a parameter size of 12.8B showing up to a 58.8% decrease in memory usage compared to LoRA. To evaluate the generative performance of the fine-tuned model, texts generated from 100 inputs not included in the training data produced on average more than twice the number of words compared to the pre-trained model, with texts of positive sentiment also appearing more than twice as often. In a survey conducted for qualitative evaluation of generative performance, responses indicated that the fine-tuned model's generated outputs were more relevant to the given topics on average 77.5% of the time. This demonstrates that the positive review generation language model for sponsored content in this paper can enhance the efficiency of time management for content creation and ensure consistent marketing effects. However, to reduce the generation of content that deviates from the category of positive reviews due to elements of the pre-trained model, we plan to proceed with fine-tuning using the augmentation of training data.

• Journal of Korean Society for Geospatial Information Science
• /
• v.25 no.2
• /
• pp.3-12
• /
• 2017

Leaving positive or negative comments of places where he or she visits on location-based services is being common in daily life. The sentiment analysis of place reviews written by actual visitors can provide valuable information to potential consumers, as well as business owners. To conduct sentiment analysis of a place, a spatial sentiment lexicon that can be used as a criterion is required; yet, lexicon of spatial sentiment words has not been constructed. Therefore, this study suggested a method to construct a spatial sentiment lexicon by analyzing the place review data written by Korean internet users. Among several location categories, theme parks were chosen for this study. For this purpose, natural language processing technique and statistical techniques are used. Spatial sentiment words included the lexicon have information about sentiment polarity and probability score. The spatial sentiment lexicon constructed in this study consists of 3 tables(SSLex_SS, SSLex_single, SSLex_combi) that include 219 spatial sentiment words. Throughout this study, the sentiment analysis has conducted based on the texts written about the theme parks created on Twitter. As the accuracy of the sentiment classification was calculated as 0.714, the validity of the lexicon was verified.

• Information Systems Review
• /
• v.26 no.1
• /
• pp.337-353
• /
• 2024

The purpose of this study is to investigate the relationship between consumer reviews and managerial responses, aiming to explore the necessity of webcare for efficiently managing consumer reviews. We intend to propose a methodology for effective webcare and to construct a webcare model using machine learning techniques based on an audiobook platform. In this study, we selected four audiobook platforms and conducted data collection and preprocessing for consumer reviews and managerial responses. We utilized techniques such as topic modeling, topic inconsistency analysis, and DBSCAN, along with various machine learning methods for analysis. The experimental results yielded significant findings in clustering managerial responses and predicting responses to consumer reviews, proposing an efficient methodology considering resource constraints and costs. This research provides academic insights by constructing a webcare model through machine learning techniques and practical implications by suggesting an efficient methodology, considering the limited resources and personnel of companies. The proposed webcare model in this study can be utilized as strategic foundational data for consumer engagement and providing useful information, offering both personalized responses and standardized managerial responses.

• Informatization Policy
• /
• v.27 no.3
• /
• pp.3-18
• /
• 2020

In the growing digitalized world, the European Union implemented the General Data Protection Regulation(GDPR) to establish a comprehensive data protection framework across member states. Given the constitutional roots of GDPR, the EU's regulatory approach is different than other data protection regimes. The new regulation has strengthened individual rights to data protection, but it also introduced several obligations for businesses that collect and process personal data. We review the existing literature on privacy, particularly GDPR, from a policy perspective. The evidence outlines data regulation's effects on competition, innovation, marketing activities, and cross-border data flows. The discussion highlights the tradeoffs between increased regulation of data protection and its effects on the market.