• The Journal of the Korea Contents Association
• /
• v.14 no.10
• /
• pp.527-538
• /
• 2014

The demand prediction is a critical issue for the film industry. As the social media, such as Twitter and Facebook, gains momentum of late, considerable efforts are being dedicated to prediction and analysis of hit movies based on unstructured text data. For prediction of trends found in commercially successful films, the correlations between the amount of data and hit movies may be analyzed by estimating the data variation by period while opinion mining that assigns sentiment polarity score to data may be employed. However, it is not possible to understand why the audience chooses a certain movie or which attribute of a movie is preferred by using such a quantitative approach. This has limited the efforts to identify factors driving a movie's commercial success. In this regard, this study aims to investigate a movie's attributes that reflect the interests of the audience. This would be done by extracting topic keywords that represent the contents of Twits through frequency measurement based on the collected Twitter data while analyzing responses displayed by the audience. The objective is to propose factors driving a movie's commercial success.

• The Journal of the Korea Contents Association
• /
• v.20 no.1
• /
• pp.142-151
• /
• 2020

The reason why today's public actively uses social communication is that the necessary information is collected and classified under the name of social big data through the web space to create the big data era, an ecosystem of information. In order for big data information to be used by the public, it is necessary to visualize it easily. This study categorized the types of visualization according to the information of social big data, and targeted the experienced students including the related majors and the general public who need to directly utilize and study the actual big data visualization as an experience evaluation target. As a result of analyzing the experiences of the experienced people, important implications for the visualization method for managing, analyzing, and utilizing the data were derived. The big data visualization strategy is to be expressed in a way that fits the data environment and user's eye level on SNS. In the future, if big data visualization is applied to product service or social trend, it will be an important data in terms of broadening its role, scope of application, and application.

• Journal of KIISE:Databases
• /
• v.41 no.4
• /
• pp.217-225
• /
• 2014

Analysis of social media such as Twitter can yield interesting perspectives to understanding human behavior, detecting hot issues, identifying influential people, or discovering a group and community. However, it is difficult to gather the data relevant to specific topics due to the main characteristics of social media data; data is large, noisy, and dynamic. This paper proposes a new algorithm that dynamically selects the seed nodes to efficiently collect tweets relevant to topics. The algorithm utilizes attributes of users to evaluate the user influence, and dynamically selects the seed nodes during the collection process. We evaluate the proposed algorithm with real tweet data, and get satisfactory performance results.

• Knowledge Management Research
• /
• v.22 no.4
• /
• pp.135-155
• /
• 2021

With the emergence of various types of social media and the diversification of their roles, it has become essential for marketers to understand how different types of social media influence consumers' purchase decisions differently and derive more detailed strategies by social media types. This study classifies social media into two types-expression-focused social media and relationship-focused social media-and investigates the relationship between consumer purchases and social media mentions by type. Using the Seoul bike-sharing data and time-series data for social media mentions, we apply the VAR model with Exogenous Variables (VARX). We find that the increase of product mentions in expression-focused social media positively affects both the number of new customers (customer acquisition) and the number of shared bike rentals, while that in relationship-focused social media negatively affects the number of new customers only. In addition, as new customers increase, the product mentions in both types of social media increase. On the other hand, the number of bike rentals has no significant effect in increasing social media mentions regardless of type. This study contributes to the social media and sharing economy literature and provides managerial implications for establishing sophisticated social media marketing in bike-sharing businesses.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.51 no.5
• /
• pp.44-56
• /
• 2023

This research explores the enhancement of park operation and management by analyzing the changing demands of park users. While traditional methods depended on surveys, there has been a recent shift towards utilizing social media data to understand park usage trends. Notably, most research has focused on text data from social media, overlooking the valuable insights from image data. Addressing this gap, our study introduces a novel method of assessing park usage using social media image data and then applies it to actual city park evaluations. A unique image analysis tool, built on Visual Question Answering (VQA) deep learning technology, was developed. This tool revealed specific city park details such as user demographics, behaviors, and locations. Our findings highlight three main points: (1) The VQA-based image analysis tool's validity was proven by matching its results with traditional text analysis outcomes. (2) VQA deep learning technology offers insights like gender, age, and usage time, which aren't accessible from text analysis alone. (3) Using VQA, we derived operational and management strategies for city parks. In conclusion, our VQA-based method offers significant methodological advancements for future park usage studies.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.9
• /
• pp.1199-1205
• /
• 2021

In the era of big data, not only structured data well organized in databases, but also the Internet, social network services, it is very important to effectively analyze unstructured big data such as web documents, e-mails, and social data generated in real time in mobile environment. Big data analysis is the process of creating new value by discovering meaningful new correlations, patterns, and trends in big data stored in data storage. We intend to summarize and visualize the analysis results through frequency analysis of unstructured article data using R language, a big data analysis tool. The data used in this study was analyzed for total 104 papers in the Mon-May 2021 among the journals of the Korea Institute of Information and Communication Engineering. In the final analysis results, the most frequently mentioned keyword was "Data", which ranked first 1,538 times. Therefore, based on the results of the analysis, the limitations of the study and theoretical implications are suggested.

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.3
• /
• pp.129-134
• /
• 2015

Since automatic social engineering based spam attacks induce for users to click or receive the short message service (SMS), e-mail, site address and make a relationship with an unknown friend, it is very easy for them to active in online social networks. The previous spam detection schemes only apply manual filtering of the system managers or labeling classifications regardless of the features of social networks. In this paper, we propose the spam detection metric after reflecting on a couple of features of social networks followed by analysis of real social network data set, Twitter spam. In addition, we provide the online social networks based unsupervised scheme for automated social engineering spam with self organizing map (SOM). Through the performance evaluation, we show the detection accuracy up to 90% and the possibility of real time training for the spam detection without the manager.

• Journal of Cadastre & Land InformatiX
• /
• v.46 no.2
• /
• pp.269-281
• /
• 2016

The process of spatial big data, such as social media, is being paid more attention in the field of spatial information in recent years. This study, as an example of spatial big data analysis, analyzed the spatial and temporal distribution of Tweet data based on the location and time information. In addition, the characteristics of its spatial pattern by times were identified. Tweet data in Busan city are collected, processed, and analyzed to identify the characteristics of the temporal and spatial pattern. Then, the results of Tweet data analysis were compared with the characteristics of the land type. This study found that spatial pattern of tweeting in the city was associated with given time periods such as daytime and nighttime in both weekdays and weekends. The spatial distribution patterns of individual time periods were compared with the characteristics of the land for the spatially concentrated area. The results of this study showed that tweeted data would be related to different spatial distribution depending on the time, which potentially reflects the daily pattern and characteristics of the land type of urban area to some extent. This study presented the possible incorporation of social media data, e. g. Tweet data, into the field of spatial information. It is expected that there will be more advantage to use a variety of social media data in areas such as land planning and urban planning.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.04a
• /
• pp.333-336
• /
• 2011

최근 전 세계적으로 소셜 네트워크 서비스의 사용자가 많이 증가하면서 많은 사람들이 소셜 네트워크 서비스를 이용하고 있다. 그리고 소셜 네트워크 서비스를 사용하는 사용자들은 이를 이용하여 많은 정보를 공유하고 있다. 본 논문에서는 소셜 네트워크 서비스 사용자들이 공유하는 정보 중 음악과 관련된 정보와 개방형 API 를 이용하여 MP3 파일의 메타데이터인 ID3 태그 정보를 검색한다. 검색된 결과와 소셜 네트워크 서비스 사용자 정보를 이용하여 ID3 태그 온톨로지를 생성하고 생성된 온톨로지와 온톨로지 추론기를 사용하여 음악과 관련된 다양한 순위 분석 결과와 음악 및 사용자 추천 서비스를 사용자들에게 제공하기 위한 시스템의 설계를 보인다. 본 논문에서 제안한 시스템은 소셜 네트워크 서비스에 실시간으로 등록되는 글을 이용하기 때문에 최근 음악 트렌드를 쉽게 반영한다. 또한 순위 분석을 위해 수동적으로 자료를 수집하는데 들어가는 시간적 비용을 줄여준다. 그리고 제안한 시스템을 사용하여 제공된 정보는 음악 관련 산업에서 마케팅과 사업 전략자료 등 다양한 형태로 활용이 가능하다.

• Journal of Digital Contents Society
• /
• v.14 no.1
• /
• pp.41-50
• /
• 2013

Social network analysis use the n nodes with l connections. About dozens or hundreds number of nodes are reasonable for social network analysis to the entire data. Beyond such number of nodes it will be difficult to analyze entire data. Therefore, it is necessary to separate the whole social networks, a method that can be used at this time is Clustering. You will be able to easily perform the analysis of the features of social networks and the relationships between nodes, if sub-group consists of all the nodes by Clustering. Clustering algorithm needs the interaction with the user and computer because it is need to pre-set the number of sub-groups. Sub-groups generated like this can not be guaranteed optimal results. In this paper, we propose dynamic sub-groups creating method using the external community association. We compared with previous studies by the number of sub-groups and sub-groups purity standards. Experimental results show the excellence of the proposed method.