• Journal of Internet Computing and Services
• /
• v.15 no.5
• /
• pp.73-82
• /
• 2014

SNS becomes a recent issue, and many researches in various kinds of field are being done by taking advantage of it. Especially, there are many researches existed on the system that finds user's interest and makes recommendation based on multiple social data generated on the SNS. User's interest is not only revealed from the user's writing but also from the user's relationship with friends. This study proposes a recommendation method that extracts user's interest by using social relationship and its categorization applies it to the recommendation. In this way, it can recommend user's interest with category based on the writings by the user and furthermore it can apply the user's relationship with his/her friends for more accurate recommendation. In addition, if necessary, the recommendation can be made by extracting any interest shared between the user and specific friends. Through experiments, we show that our method using social category can produce satisfactory result.

• The Journal of the Convergence on Culture Technology
• /
• v.6 no.2
• /
• pp.449-454
• /
• 2020

This paper proposes a machine learning-based emotion analysis system that detects a user's depression through their SNS posts. We first made a list of keywords related to depression in Korean, then used these to create a training data by crawling Twitter data - 1,297 positive and 1,032 negative tweets in total. Lastly, to identify the best machine learning model for text-based depression detection purposes, we compared RNN, LSTM, and GRU in terms of performance. Our experiment results verified that the GRU model had the accuracy of 92.2%, which is 2~4% higher than other models. We expect that the finding of this paper can be used to prevent depression by analyzing the users' SNS posts.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.12
• /
• pp.1800-1808
• /
• 2022

During the election period, many polling agencies survey and distribute the approval ratings for each candidate. In the past, public opinion was expressed through the Internet, mobile SNS, or community, although in the past, people had no choice but to survey the approval rating by relying on opinion polls. Therefore, if the public opinion expressed on the Internet is understood through natural language analysis, it is possible to determine the candidate's approval rate as accurately as the result of the opinion poll. Therefore, this paper proposes a method of inferring the approval rate of candidates during the election period by synthesizing the political comments of users through internet community posting data. In order to analyze the approval rate in the post, I would like to suggest a method for generating the model that has the highest correlation with the actual opinion poll by using the KoBert, KcBert, and KoELECTRA models.

• Proceedings of The KACE
• /
• 2018.08a
• /
• pp.147-149
• /
• 2018

음성인식, 행동패턴인식, 텍스트마이닝 등 사람의 자연스러운 사회적인 활동을 통해 감성을 분석하려는 연구는 지속적으로 증가하고 있다. 특히 SNS는 현대사회에서 없어서는 안 될 소통의 도구로 자리 잡았기 때문에 SNS의 비정형데이터를 이용한 감성분석은 마케팅 분야에서 중요한 활용도구로 사용되고 있다. 이러한 추세에 따라 한국어에 대한 감성인식 역시 다방면으로 분석, 활용되고 있고 한국어의 어순과 표현방식, 중의성, 방언 등의 몇 가지 특징으로 인해 영어와는 다른 방식으로의 접근방식에 대한 필요성이 많은 연구에서 논의되고 있다. 따라서, 이 연구에서는 이러한 한국어의 특징을 수용하여 분석할 수 있도록 시계열 분석에 유용한 LSTM과 중복단어에 대한 가중치를 적용하여 한국어 감성분석을 진행해보고자 한다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.372-372
• /
• 2020

사회가 다원화되고 발달하면서 생활환경과 행동양식에 따라 홍수 등의 수난(水難) 으로 인한 피해 정도와 양상은 크게 달라질 수 있으나, 수난으로 인한 체감 가능한 피해의 정도와 규모는 예측이 어려운 현실이다. 그리고, 최근 인터넷과 소셜 네트워크 서비스(SNS)의 급진적 발달은 재난 관리에 대중적 지식을 수집하여 활용하도록 촉진하고 있고, 이로 인해 재난 상황에서 '대중적인 정보가 기술자에 의해 어떻게 얼마나 신중하게 고려되어야 하는지와 어떻게 과학적으로 해석해야하는지'가 핵심 쟁점으로 부상하고 있다. 본 연구에서는 최근 널리 사용되는 인공지능 및 딥러닝 기법을 조사 분석하였다. 분석을 통해 수문 예측 분야에서 이러한 기술이 적용된 사례와 신기술을 조망해 보고 기존 기술이 인공지능 및 딥러닝 기법의 적용으로 대체 가능한 정도를 가늠해 보았다.

• Journal of Creative Information Culture
• /
• v.5 no.3
• /
• pp.215-223
• /
• 2019

The wave of the information age gradually accelerates, and fusion analysis solutions that can utilize these knowledge data according to accumulation of various forms of big data such as large capacity texts, sounds, movies and the like are increasing, Reduction in the cost of storing data accordingly, development of social network service (SNS), etc. resulted in quantitative qualitative expansion of data. Such a situation makes possible utilization of data which was not trying to be existing, and the potential value and influence of the data are increasing. Research is being actively made to present future-oriented education systems by applying these fusion analysis systems to the improvement of the educational system. In this research, we conducted a big data analysis on Twitter, analyzed the natural language of the data and frequency analysis of the word, quantitative measure of how domestic windows education problems and outcomes were done in it as a solution.

• KIPS Transactions on Computer and Communication Systems
• /
• v.4 no.7
• /
• pp.227-234
• /
• 2015

USN-based real-time monitoring systems, which receive raw data from sensor nodes and store the processed information in traditional servers, recently get to be replaced by IoT(Internet of Things)/WoT(Web of Things)-based ones. Especially, Social Web of Things(SWoT) paradigm can make use of cloud storage over Social Network Service(SNS) and enable the possibility of integrated access, management and sharing. This paper proposes an improved SWoT-based real-time monitoring system which makes up for weak points of existing systems, and implements monitoring service integrating a legacy sensor network and commercial SNS without requiring additional servers. Especially, the proposed system can reduce emergency propagation time by employing PUSH messages.

• Convergence Security Journal
• /
• v.20 no.3
• /
• pp.3-11
• /
• 2020

The social networking service (SNS) is free, but the data usage fee paid to the telecommunications company and the member's information must be provided directly or indirectly. In addition, while SNS' specifications for transmitting and receiving devices such as smart-phones and PCs are increasing day by day, using universal transmission protocols in special environments such as contaminated areas or semiconductor manufacturing plants where work instructions are mainly made using short messages is not easy. It is not free and has a problem of weak security. This paper verified the practicality through the operation test by implementing IMCP, a low-power, low-cost message transmission protocol that aims to be wearable in special environments such as risk, pollution, and clean zone based on ATmega128.

• Journal of IKEEE
• /
• v.20 no.3
• /
• pp.235-240
• /
• 2016

In this study, we use the data collected from Twitter, as an SNS(Social Networking Service), for service innovation. This data was collected and processed by Flume. The data set in May 2016 was 4,766 and 15,543 from company S and company X, respectively. We were able to figure out the emotional atmosphere of the two companies through the sentiment analysis(SA) and to find out about the vertical relationship through the bibliometric analysis(BA). Furthermore, we were able to grasp the horizontal relationship through the social network analysis(SNA). It was concluded that SNS was worth while to derive an innovative item.

• Convergence Security Journal
• /
• v.16 no.2
• /
• pp.25-34
• /
• 2016

This study aims to prevent the serious threat from dangerous person or group by responding or blocking or separating illegal activities by use of SNA: Social Network Analysis. SNA enables to identify the complex social relation of suspect and individuals in order to enhance the effectiveness and efficiency of investigation. SNS has rapidly developed and expanded without restriction of physical distance and geo-location for making new relation among people and sharing large amount of information. As rise of SNS(facebook and twitter) related crimes, terrorist group 'ISIS' has used their website for promotion of their activity and recruitment. The use of SNS costs relatively lower than other methods to achieve their goals so it has been widely used by terrorist groups. Since it has a significant ripple effect, it is imperative to stop their activity. Therefore, this study precisely describes criminal and terrorist activities on SNS and demonstrates how effectively detect, block and respond against their activities. Further study is also suggested.