• Information Systems Review
• /
• v.24 no.1
• /
• pp.1-19
• /
• 2022

Social media-based communication has become crucial part of our personal and official lives. Therefore, it is no surprise that social media sentiment analysis has emerged an important way of detecting potential customers' sentiment trends for all kinds of companies. However, social media sentiment analysis suffers from huge number of sentiment features obtained in the process of conducting the sentiment analysis. In this sense, this study proposes a novel method by using Bayesian Network. In this model MBFS (Markov Blanket-based Feature Selection) is used to reduce the number of sentiment features. To show the validity of our proposed model, we utilized online review data from Yelp, a famous social media about restaurant, bars, beauty salons evaluation and recommendation. We used a number of benchmarking feature selection methods like correlation-based feature selection, information gain, and gain ratio. A number of machine learning classifiers were also used for our validation tasks, like TAN, NBN, Sons & Spouses BN (Bayesian Network), Augmented Markov Blanket. Furthermore, we conducted Bayesian Network-based what-if analysis to see how the knowledge map between target node and related explanatory nodes could yield meaningful glimpse into what is going on in sentiments underlying the target dataset.

• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.5
• /
• pp.15-30
• /
• 2023

Recently, generative models based on the Transformer architecture, such as ChatGPT, have been gaining significant attention. The Transformer architecture has been applied to various neural network models, including Google's BERT(Bidirectional Encoder Representations from Transformers) sentence generation model. In this paper, a method is proposed to create a text binary classification model for determining whether a comment on Korean movie review is positive or negative. To accomplish this, a pre-trained multilingual BERT sentence generation model is fine-tuned and transfer learned using a new Korean training dataset. To achieve this, a pre-trained BERT-Base model for multilingual sentence generation with 104 languages, 12 layers, 768 hidden, 12 attention heads, and 110M parameters is used. To change the pre-trained BERT-Base model into a text classification model, the input and output layers were fine-tuned, resulting in the creation of a new model with 178 million parameters. Using the fine-tuned model, with a maximum word count of 128, a batch size of 16, and 5 epochs, transfer learning is conducted with 10,000 training data and 5,000 testing data. A text sentiment binary classification model for Korean movie review with an accuracy of 0.9582, a loss of 0.1177, and an F1 score of 0.81 has been created. As a result of performing transfer learning with a dataset five times larger, a model with an accuracy of 0.9562, a loss of 0.1202, and an F1 score of 0.86 has been generated.

• Journal of Intelligence and Information Systems
• /
• v.18 no.4
• /
• pp.19-42
• /
• 2012

Consumer consumption patterns are shifting rapidly as buyers migrate from offline markets to e-commerce routes, such as shopping channels on TV and internet shopping malls. In the offline markets consumers go shopping, see the shopping items, and choose from them. Recently consumers tend towards buying at shopping sites free from time and place. However, as e-commerce markets continue to expand, customers are complaining that it is becoming a bigger hassle to shop online. In the online shopping, shoppers have very limited information on the products. The delivered products can be different from what they have wanted. This case results to purchase cancellation. Because these things happen frequently, they are likely to refer to the consumer reviews and companies should be concerned about consumer's voice. E-commerce is a very important marketing tool for suppliers. It can recommend products to customers and connect them directly with suppliers with just a click of a button. The recommender system is being studied in various ways. Some of the more prominent ones include recommendation based on best-seller and demographics, contents filtering, and collaborative filtering. However, these systems all share two weaknesses : they cannot recommend products to consumers on a personal level, and they cannot recommend products to new consumers with no buying history. To fix these problems, we can use the information which has been collected from the questionnaires about their demographics and preference ratings. But, consumers feel these questionnaires are a burden and are unlikely to provide correct information. This study investigates combining collaborative filtering with the centrality of social network analysis. This centrality measure provides the information to infer the preference of new consumers from the shopping history of existing and previous ones. While the past researches had focused on the existing consumers with similar shopping patterns, this study tried to improve the accuracy of recommendation with all shopping information, which included not only similar shopping patterns but also dissimilar ones. Data used in this study, Movie Lens' data, was made by Group Lens research Project Team at University of Minnesota to recommend movies with a collaborative filtering technique. This data was built from the questionnaires of 943 respondents which gave the information on the preference ratings on 1,684 movies. Total data of 100,000 was organized by time, with initial data of 50,000 being existing customers and the latter 50,000 being new customers. The proposed recommender system consists of three systems : [+] group recommender system, [-] group recommender system, and integrated recommender system. [+] group recommender system looks at customers with similar buying patterns as 'neighbors', whereas [-] group recommender system looks at customers with opposite buying patterns as 'contraries'. Integrated recommender system uses both of the aforementioned recommender systems to recommend movies that both recommender systems pick. The study of three systems allows us to find the most suitable recommender system that will optimize accuracy and customer satisfaction. Our analysis showed that integrated recommender system is the best solution among the three systems studied, followed by [-] group recommended system and [+] group recommender system. This result conforms to the intuition that the accuracy of recommendation can be improved using all the relevant information. We provided contour maps and graphs to easily compare the accuracy of each recommender system. Although we saw improvement on accuracy with the integrated recommender system, we must remember that this research is based on static data with no live customers. In other words, consumers did not see the movies actually recommended from the system. Also, this recommendation system may not work well with products other than movies. Thus, it is important to note that recommendation systems need particular calibration for specific product/customer types.

• The Journal of the Korea Contents Association
• /
• v.20 no.10
• /
• pp.89-99
• /
• 2020

In this study, we tried to produce moving-image works through sentiment analysis of music. First, Google natural language API was used for the sentiment analysis of lyrics, then the result was applied to the image visualization rules. In prior engineering researches, text-based sentiment analysis has been conducted to understand users' emotions and attitudes by analyzing users' comments and reviews in social media. In this study, the data was used as a material for the creation of artworks so that it could be used for aesthetic expressions. From the machine's point of view, emotions are substituted with numbers, so there is a limit to normalization and standardization. Therefore, we tried to overcome these limitations by linking the results of sentiment analysis of lyrics data with the rules of formative elements in visual arts. This study aims to transform existing traditional art works such as literature, music, painting, and dance to a new form of arts based on the viewpoint of the machine, while reflecting the current era in which artificial intelligence even attempts to create artworks that are advanced mental products of human beings. In addition, it is expected that it will be expanded to an educational platform that facilitates creative activities, psychological analysis, and communication for people with developmental disabilities who have difficulty expressing emotions.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.1
• /
• pp.265-274
• /
• 2021

In this paper, we propose a novel recommendation model based on Doc2vec using search keywords and product details. Until now, a lot of prior studies on recommender systems have proposed collaborative filtering (CF) as the main algorithm for recommendation, which uses only structured input data such as customers' purchase history or ratings. However, the use of unstructured data like online customer review in CF may lead to better recommendation. Under this background, we propose to use search keyword data and product detail information, which are seldom used in previous studies, for product recommendation. The proposed model makes recommendation by using CF which simultaneously considers ratings, search keywords and detailed information of the products purchased by customers. To extract quantitative patterns from these unstructured data, Doc2vec is applied. As a result of the experiment, the proposed model was found to outperform the conventional recommendation model. In addition, it was confirmed that search keywords and product details had a significant effect on recommendation. This study has academic significance in that it tries to apply the customers' online behavior information to the recommendation system and that it mitigates the cold start problem, which is one of the critical limitations of CF.

• Journal of the Korean Applied Science and Technology
• /
• v.38 no.1
• /
• pp.241-262
• /
• 2021

This paper reviewed the necessity of a information and communication technology (ICT)-based smart livestock system as a development strategy for the animal life industry in the future. It also predicted the trends of livestock and animal food until 2050, 30 years later. Worldwide, livestock raising and consumption of animal food are rapidly changing in response to population growth, aging, reduction of agriculture population, urbanization, and income growth. Climate change can change the environment and livestock's productivity and reproductive efficiencies. Livestock production can lead to increased greenhouse gas emissions, land degradation, water pollution, animal welfare, and human health problems. To solve these issues, there is a need for a preemptive future response strategy to respond to climate change, improve productivity, animal welfare, and nutritional quality of animal foods, and prevent animal diseases using ICT-based smart livestock system fused with the 4th industrial revolution in various aspects of the animal life industry. The animal life industry of the future needs to integrate automation to improve sustainability and production efficiency. In the digital age, intelligent precision animal feeding with IoT (internet of things) and big data, ICT-based smart livestock system can collect, process, and analyze data from various sources in the animal life industry. It is composed of a digital system that can precisely remote control environmental parameters inside and outside the animal husbandry. The ICT-based smart livestock system can also be used for monitoring animal behavior and welfare, and feeding management of livestock using sensing technology for remote control through the Internet and mobile phones. It can be helpful in the collection, storage, retrieval, and dissemination of a wide range of information that farmers need. It can provide new information services to farmers.

• Journal of Korea Water Resources Association
• /
• v.55 no.10
• /
• pp.707-721
• /
• 2022

In this study, a state-of-the-art review on urban inundation simulation technology was presented summarizing major achievements and limitations, and future research recommendations and challenges. More than 160 papers published in major domestic academic journals since the 2000s were analyzed. After analyzing the core themes and contents of the papers, the status of technological development was reviewed according to simulation methodologies such as physically-based and data-driven approaches. In addition, research trends for application purposes and advances in overseas and related fields were analyzed. Since more than 60% of urban inundation research used Storm Water Management Model (SWMM), developing new modeling techniques for detailed physical processes of dual drainage was encouraged. Data-based approaches have become a new status quo in urban inundation modeling. However, given that hydrological extreme data is rare, balanced research development of data and physically-based approaches was recommended. Urban inundation analysis technology, actively combined with new technologies in other fields such as artificial intelligence, IoT, and metaverse, would require continuous support from society and holistic approaches to solve challenges from climate risk and reduce disaster damage.

• Smart Media Journal
• /
• v.12 no.11
• /
• pp.27-35
• /
• 2023

Fourth Industrial Revolution and COVID-19 pandemic have boosted the use of Government 24 app for public service complaints in the era of non-face-to-face interactions. there has been a growing influx of complaints and improvement demands from users of public apps. Furthermore, systematic management of public apps is deemed necessary. The aim of this study is to analyze the grievances of Government 24 app users, understand the current dissatisfaction among citizens, and propose potential improvements. Data were collected from the Google Play Store from May 2, 2013, to June 30, 2023, comprising a total of 6,344 records. Among these, 1,199 records with a rating of 1 and at least one 'thumbs-up' were used for topic modeling analysis. The analysis revealed seven topics: 'Issues with certificate issuance,' 'Website functionality and UI problems,' 'User ID-related issues,' 'Update problems,' 'Government employee app management issues,' 'Budget wastage concerns ((It's not worth even a single star) or (It's a waste of taxpayers' money)),' and 'Password-related problems.' Furthermore, the overall trend of these topics showed an increase until 2021, a slight decrease in 2022, but a resurgence in 2023, underscoring the urgency of updates and management. We hope that the results of this study will contribute to the development and management of public apps that satisfy citizens in the future.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.5
• /
• pp.543-550
• /
• 2020

Interest in food recipe retrieval systems has been increasing recently. Most computer-based recipe retrieval systems are searched by cooking name or ingredient name. Since each recipe provides information in different weighing units, recalculations to the desired amount are necessary and inconvenient. This paper introduces a computer system that addresses these inconveniences. The system is a chatbot system, based on web-based recipe recommendations, for users familiar with the use of messenger conversation systems. After selecting the most popular recipes by their names, and pre-processing to extract only information required for the recipes, the system recommends recipes based on the 100,000 data. Recipes are then searched by the names of food ingredients (included and excluded). Recalculations are performed based on the number of servings entered by the user. A satisfaction rate for the systems' recommendations was 90.5%.

• The Journal of the Korea Contents Association
• /
• v.9 no.2
• /
• pp.106-114
• /
• 2009

In this study, we are analysing adverse drug events and proposing a technical structure of "adverse drug event surveillance system" using business intelligence technology, hoping that we can use the system commonly and actively. It is the recent trend to adopt both of electronic review and manual review process to surveil adverse drug events and this study construct CDW applying ETL in BI Technology. As the result of analysis, the data pool included 701 doctors who prescribed and 3059 patients(1528 male, 1531 female), of total 318,222 cases, 2,086cases(0.6%) were suspected as having adverse drug events. And the single type of T.bilirubin> 3mg/dL(ADE type-LabR0005) was the most common(548 among 2085 cases) within the framework of signals.