• Asia pacific journal of information systems
• /
• v.30 no.4
• /
• pp.785-807
• /
• 2020

The novel Coronavirus disease 2019 (COVID-19) is unprecedentedly changing the world since its outbreak in late 2019. Using the collected the data related to COVID-19 and the social media user data from a mobile application market research agency from January 25 to April 7, this study empirically examines the effect of the number of confirmed COVID-19 cases worldwide, the number news COVID-19, and the enforcement of social distancing measures on the daily active users (DAU) of two social media services - Twitter and Facebook - in South Korea. There are three important findings from the results of econometric analysis. First, the number of confirmed COVID-19 cases worldwide has a negative effect on the DAU of social media. Second, the number of COVID-19 news is negatively associated with the DAU of social media. Finally, the implementation of social distancing measures has no significant effect on the DAU of the social media. Theoretical implications and managerial guidelines are also discussed.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.6
• /
• pp.640-645
• /
• 2014

Many people use social network services as to communicate, to share an information and to build social relationships between others on the Internet. Twitter is such a representative service, where millions of tweets are posted a day and a huge amount of data collection has been being accumulated. Social mining that extracts the meaningful information from the massive data has been intensively studied. Typically, Twitter easily can deliver and retweet the contents using the following-follower relationships. Topic modeling in tweet data is a good tool for issue tracking in social media. To overcome the restrictions of short contents in tweets, we introduce a notion of reply graph which is constructed as a graph structure of which nodes correspond to users and of which edges correspond to existence of reply and retweet messages between the users. The LDA topic model, which is a typical method of topic modeling, is ineffective for short textual data. This paper introduces a topic modeling method that uses reply graph to reduce the number of short documents and to improve the quality of mining results. The proposed model uses the LDA model as the topic modeling framework for tweet issue tracking. Some experimental results of the proposed method are presented for a collection of Twitter data of 7 days.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2011.11a
• /
• pp.19-20
• /
• 2011

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.05a
• /
• pp.541-543
• /
• 2015

Due to the popularity of IT technology and smart devices, SNS (Social Networking Service), there are increasing users using. This causes increasing of data generated by the SNS may also, IT companies are developing a technique to create value in this data. In this paper, we design and implement the system that statistical information for connecting to the tweeter to create value of the data generated by the tweeter. The proposed system is a system using Mahout behind collected data and stored as a tweeter NoSQL based statistics that the contact information of the user. The developed system is expected to be helpful in providing the background technology necessary to create value in the data of the tweeter.

• Journal of the Korean Data and Information Science Society
• /
• v.26 no.5
• /
• pp.1087-1095
• /
• 2015

Influenza, commonly known as "the flu", is an infectious disease caused by the influenza virus. We consider, in this paper, regression models as a prediction model of influenza disease. While most of previous researches use mainly the meteorological variables as a predictive variables, we consider social media information in the models. As a result, we found that the contributions of two-type of informations are comparable. We used the medical treatment data of influenza provided by Natioal Health Insurance Survice (NHIS) and the meteorological data provided by Korea Meteorological Administration (KMA). We collect social media information (twitter buzz amount) from Twitter. Time series model is also considered for comparison.

• Journal of Contemporary Eastern Asia
• /
• v.14 no.1
• /
• pp.23-43
• /
• 2015

In most of the world, the current trend in information technology is for open data movement that promotes transparency and equal access. An opposite trend is observed in China, which has the world's largest Internet population. The country has implemented sophisticated cyber-infrastructure and practices under the name of The Golden Shield Project (commonly referred to as the Great Firewall) to limit access to popular international web services and to filter traffic containing 'undesirable' political content. Increasingly, tech-savvy Chinese bypass this firewall and use Twitter to share knowledge on censorship circumvention and encryption to collectively troubleshoot firewall evasion methods, and even mobilize actions that border on activism. Using a mixed mythological approach, the current study addresses such networked knowledge sharing among citizens in a restricted web ecosystem. On the theoretical front, this study uses webometric approaches to understand change agents and positive deviant in the diffusion of censorship circumvention technology. On policy-level, the study provides insights for Internet regulators and digital rights groups to help best utilize communication networks of positive deviants to counter Internet control.

• Journal of Contemporary Eastern Asia
• /
• v.13 no.1
• /
• pp.69-81
• /
• 2014

While much in the field of public management has emphasized the importance of nonprofit advocacy activities in policy and decision-making procedures, few have considered the relevance and impact of leading actors on structuring diverse patterns of information sharing and communication through social media. Building nonprofit advocacy is a complicated process for a single organization to undertake, but social media applications such as Facebook and Twitter have facilitated nonprofit organizations and stakeholders to effectively share information and communicate with each other for identifying their mission as it relates to environmental issues. By analyzing the Australian Marine Conservation Society's (AMCS) Twitter network data from the period 1 April to 20 April, 2013, this research discovered diverse patterns in nonprofit advocacy by leading actors in building advocacy. Based on the webometrics approach, analysis results show that nonprofit advocacy through social media is structured by dynamic information flows and intercommunications among participants and followers of the AMCS. Also, the findings indicate that the news media and international and domestic nonprofit organizations have a leading role in building nonprofit advocacy by clustering with their followers.

• Genomics & Informatics
• /
• v.18 no.2
• /
• pp.17.1-17.4
• /
• 2020

The amount of content on social media platforms such as Twitter is expanding rapidly. Simultaneously, the lack of patient information seriously hinders the diagnosis and treatment of rare/intractable diseases. However, these patient communities are especially active on social media. Data from social media could serve as a source of patient-centric knowledge for these diseases complementary to the information collected in clinical settings and patient registries, and may also have potential for research use. To explore this question, we attempted to extract patient-centric knowledge from social media as a task for the 3-day Biomedical Linked Annotation Hackathon 6 (BLAH6). We selected amyotrophic lateral sclerosis and multiple sclerosis as use cases of rare and intractable diseases, respectively, and we extracted patient histories related to these health conditions from Twitter. Four diagnosed patients for each disease were selected. From the user timelines of these eight patients, we extracted tweets that might be related to health conditions. Based on our experiment, we show that our approach has considerable potential, although we identified problems that should be addressed in future attempts to mine information about rare/intractable diseases from Twitter.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.8
• /
• pp.377-384
• /
• 2016

Our goal is to build the system which collects tweets from Twitter, analyzes the sentiment of each tweet, and helps users build a sentiment tagged corpus semi-automatically. After collecting tweets with the Twitter API, we analyzes the sentiments of them with a sentiment dictionary. With the proposed system, users can verify the results of the system and can insert new sentimental words or dependency relations where sentiment information exist. Sentiment information is tagged with the JSON structure which is useful for building or accessing the corpus. With a test set, the system shows about 76% on the accuracy in analysing the sentiments of sentences as positive, neutral, or negative.

• The Journal of Information Systems
• /
• v.23 no.4
• /
• pp.1-24
• /
• 2014

This study is intended to examine two issues related with social media messages. At first, the authors investigate that how they can categorize messages in the social media and how corporate twitters and brand twitters communicate with consumers. Secondly, after dividing messages in the social media into several groups, the authors investigate how each type of messages differ one another in terms of the consumer response. For examining these research issues, the authors gather twitter message data of global top 100 brands and categorize messages into 5 types (i.e., interactivity, diversion, information sharing, promotional, content) based on the motivation of communication and the format of the messages. Especially, the authors use content analysis methodology, which is normally used as the qualitative approach, in order to identify the type of messages. Furthermore, the authors present interactivity type of messages can communicate better with consumers and induce more favorable responses from consumers in the social media than any other type of messages. This research can provide implications in terms of theoretical, methodological, and managerial perspective.