• Journal of Korea Entertainment Industry Association
• /
• v.14 no.4
• /
• pp.145-153
• /
• 2020

In the rapidly changing era of the fourth industry, big data is being used in various fields. In recent years, the use of big data has been rapidly applied to overall cultural and artistic contents, and among them, the use of big data is essential as a film genre with a lot of capital. This research method is analyzed as the film , which won the Palme d'Or Prize of the 72nd Cannes Film Festival in 2019 and the works and directors' award at the Academy Awards. The analyzed value predicts the film's performance through opinion mining, which gives the value of the change and sensitivity of each data cycle, and extracts the utilization index and topic keywords of SNS such as Facebook and Twitter to reflect the audience's interest. Identify the factors. As such, if model performance and model development can be predicted through model analysis of film performance using big data, the efficiency of the film production process will be maximized while the risk of production cost and the risk of film failure will be minimized.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.9
• /
• pp.381-390
• /
• 2022

Influenced by a culture that prefers non-face-to-face activity during the COVID-19 pandemic, chatbot usage is accelerating. Chatbots have been used for various purposes, not only for customer service in businesses and social conversations for fun but also for mental health. Chatbots are a platform where users can easily talk about their depressed moods because anonymity is guaranteed. However, most relevant research has been on social media data, especially Twitter data, and few studies have analyzed the commercially used chatbots data. In this study, we identified the characteristics of depressive discourse in user-chatbot interaction data by analyzing the chats, including the word 'depress,' using the topic modeling algorithm and the text-mining technique. Moreover, we compared its characteristics with those of the depressive moods in the Twitter data. Finally, we draw several design guidelines and suggest avenues for future research based on the study findings.

• Journal of the Korean Society for information Management
• /
• v.36 no.4
• /
• pp.207-226
• /
• 2019

Depression is a serious psychological disease that is expected to afflict an increasing number of people. And studies on depression have been conducted in the context of social media because social media is a platform through which users often frankly express their emotions and often reveal their mental states. In this study, large amounts of Korean text were collected and analyzed to determine whether such data could be used to detect depression in users. This study analyzed data collected from Twitter users who had and did not have depressive tendencies between January 2016 and February 2019. The data for each user was separately analyzed before and after the appearance of depressive tendencies to see how their expression changed. In this study the data were analyzed through co-occurrence word analysis, topic modeling, and sentiment analysis. This study's automated data collection method enabled analyses of data collected over a relatively long period of time. Also it compared the textual characteristics of users with depressive tendencies to those without depressive tendencies.

• Smart Media Journal
• /
• v.6 no.3
• /
• pp.41-48
• /
• 2017

Event detection using social media has been widespread since social network services have been an active communication channel for connecting with others, diffusing news message. Especially, the real-time characteristic of social media has created the opportunity for supporting for real-time applications/systems. Social network such as Twitter is the potential data source to explore useful information by mining messages posted by the user community. This paper proposed a novel system for temporal event detection by analyzing social data. As a result, this information can be used by first responders, decision makers, or news agents to gain insight of the situation. The proposed approach takes advantages of deep learning methods that play core techniques on the main tasks including informative data identifying from a noisy environment and temporal event detection. The former is the responsibility of Convolutional Neural Network model trained from labeled Twitter data. The latter is for event detection supported by Recurrent Neural Network module. We demonstrated our approach and experimental results on the case study of earthquake situations. Our system is more adaptive than other systems used traditional methods since deep learning enables to extract the features of data without spending lots of time constructing feature by hand. This benefit makes our approach adaptive to extend to a new context of practice. Moreover, the proposed system promised to respond to acceptable delay within several minutes that will helpful mean for supporting news channel agents or belief plan in case of disaster events.

• The Journal of the Korea Contents Association
• /
• v.13 no.3
• /
• pp.131-140
• /
• 2013

Assuming that roles of traditional mass media are also shown in Twitter services, the study aims at exploring Twitter users' motives and rationales in re-tweet behavior. Based on the laddering interview method, the study gathers data on (1) message attributes (what kinds of messages do you re-tweet?); (2) consequences (what kinds of consequences are you expecting when you re-tweet?); and (3) values (what are the ultimate values in your re-tweet behavior?). The most repetitive value occurring in participants' retweet was feeling "sympathy" and "sharing" rationales. For such rationales, participants oftentimes utilize messages with "agenda" and "information" that are relative to themselves. Messages with "helping" to help others also frequently showed up in their retweet rationales. Known as liberalists' rationales, "communal consciousness", and "calling for others' action" are also shown, but not as frequent as "feeling sympathy and sharing. A total of 48 items from the analyses were used in a subsequent study as variables to identify factors (dimensions) of retweet motivation.

• The Journal of the Korea Contents Association
• /
• v.16 no.6
• /
• pp.671-679
• /
• 2016

We investigated subgroups within a global communication network to improve the empirical understanding of global communication phenomenon from the social network perspective. We collected global communication data from Twitter and constructed a global communication network. We also added countries' geographic and economic properties used in the United Nations and the World Economic Forum. We analyzed the subgroups' structure within the global communication network using centrality analysis, core-peripheral analysis, and cohesion analysis. We also detected communities embedded within the global communication network with modularity-based community detection methods. We found that the core countries occupy central positions in the global communication network and there is a hierarchical communication structure among the economic subgroups. Futhermore, we discovered some communities within the global communication network and found that countries within the communities can have homophily such as economy, geography, history, culture, and religion.

• KIISE Transactions on Computing Practices
• /
• v.20 no.9
• /
• pp.492-497
• /
• 2014

In this paper, we propose a method of retrieving opinioned tweets in Twitter, which is the one of the popular Social Network Services and shares diverse opinions among various users. In typical opinion retrieval systems, they may consider the presence of sentiment phrases (subjectivity) as the important factor even if the subjective phrases are not related to a given query or speaker. To alleviate these problems, we utilized the syntactic structure of a sentence to identify the relationships between 1) subjectivity-query and 2) subjectivity-speaker and 3) the syntactic role of subjectivity. Besides, our learning-to-rank approach is trained to retrieve opinioned tweets based on query-relevance, textual features, user information, and Twitter-specific features. Experimental results on real world data show that our proposed method can achieve better performance than several baseline methods in terms of precision and nDCG.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.1
• /
• pp.31-36
• /
• 2014

Social network services(SNS) including Twitter and Facebook are good resources to extract various issues like public interest, trend and topic. This paper proposes a method to extract query-related issues by calculating relatedness between terms in Twitter. As a term that frequently appears near query terms should be semantically related to a query, we calculate term relatedness in retrieved documents by summing proximity that is proportional to term frequency and inversely proportional to distance between words. Then terms, relatedness of which is bigger than threshold, are extracted as query-related issues, and our system shows those issues with a connected network. By analyzing single transitions in a connected network, compound words are easily obtained.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.14 no.4
• /
• pp.199-209
• /
• 2019

The importance of business strategy for successful social media engagement has quickly increased as more businesses engage in social media. The importance is even greater for startup companies because startup companies are genuinely new to business, and they need to increase their presence in the market, and quickly access future customers. The objective of this paper lies in exploring key indicators of social media engagements by selected startup companies. The key indicators include two aspects of social media usages by the companies: i) overall social media activities, and ii) properties of network structure of the information flow platform provided by social media service. To better assess and evaluate the key indicators of social media usages by startup companies, the indicators will be compared with those of selected large established companies. Twitter is selected as a social media service for the analysis of this paper, and using Twitter REST API, data regarding the key indicators of overall Twitter activities and the Twitter follower-network of each company in the sample are collected. Then, the data are analyzed using social network analysis and hierarchical clustering analysis to examine the characteristics of the follower-network structures and to compare the characteristics between startup companies and established companies. The results show that most indicators are significantly different across startup companies and established companies. One key interesting finding is that the startup companies have proportionally more influencers in their follower-networks than the established companies have. Another interesting finding is that the follower-networks of startup companies in the sample have higher modularity and higher transitivity, suggesting that the startup companies tend to have a proportionally larger number of communities of users in their follower-networks, and the users in the networks are more tightly connected and cohesive internally. The key business implication for the future social media engagement efforts by startup companies in general is that startup companies may need to focus on getting more attention from influencers and promoting more cohesive communities in their follower-networks to appreciate the potential benefits of social media in the early stage of business of startup companies.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.24 no.4
• /
• pp.75-90
• /
• 2013

Given the context that users are actively using social media with multimedia embedded information, the purpose of this study is to demonstrate how images are used within Twitter messages, especially in influential and favorited messages. In order to achieve the purpose of this study, the top 200 influential and favorited messages with images were selected out of 1,589 tweets related to "Boston bombing" in April 2013. The characteristics of the message, image use, and user are analyzed and compared. Two phases of the analysis were conducted on three data sets containing the top 200 influential messages, top 200 favorited messages, and general messages. In the first phase, coding schemes have been developed for conducting three categorical analyses: (1) categorization of tweets, (2) categorization of image use, and (3) categorization of users. The three data sets were then coded using the coding schemes. In the second phase, comparison analyses were conducted among influential, favorited, and general tweets in terms of tweet type, image use, and user. While messages expressing opinion were found to be most favorited, the messages that shared information were recognized as most influential to users. On the other hand, as only four image uses - information dissemination, illustration, emotive/persuasive, and information processing - were found in this data set, the primary image use is likely to be data-driven rather than object-driven. From the perspective of users, the user types such as government, celebrity, and photo-sharing sites were found to be favorited and influential. An improved understanding of how users' image needs, in the context of social media, contribute to the body of knowledge of image needs. This study will also provide valuable insight into practical designs and implications of image retrieval systems or services.