• Journal of Information Science Theory and Practice
• /
• v.10 no.3
• /
• pp.40-56
• /
• 2022

This paper aims to implement a topic modeling technique for extracting the topics of online discussions among library professionals in India. Topic modeling is the established text mining technique popularly used for modeling text data from Twitter, Facebook, Yelp, and other social media platforms. The present study modeled the online discussions of Library and Information Science (LIS) professionals posted on Lis Links. The text data of these posts was extracted using a program written in R using the package "rvest." The data was pre-processed to remove blank posts, posts having text in non-English fonts, punctuation, URLs, emails, etc. Topic modeling with the Latent Dirichlet Allocation algorithm was applied to the pre-processed corpus to identify each topic associated with the posts. The frequency analysis of the occurrence of words in the text corpus was calculated. The results found that the most frequent words included: library, information, university, librarian, book, professional, science, research, paper, question, answer, and management. This shows that the LIS professionals actively discussed exams, research, and library operations on the forum of Lis Links. The study categorized the online discussions on Lis Links into ten topics, i.e. "LIS Recruitment," "LIS Issues," "Other Discussion," "LIS Education," "LIS Research," "LIS Exams," "General Information related to Library," "LIS Admission," "Library and Professional Activities," and "Information Communication Technology (ICT)." It was found that the majority of the posts belonged to "LIS Exam," followed by "Other Discussions" and "General Information related to the Library."

• The Journal of Asian Finance, Economics and Business
• /
• v.7 no.6
• /
• pp.457-464
• /
• 2020

This study aims to recognize customers' real sentiment and then discover the data-driven insights for strategic decision-making in the financial sector of Saudi Arabia. The data was collected from the social media (Facebook and Twitter) from start till October 2018 in financial companies (NCB, Al Rajhi, and Bupa) selected in the Kingdom of Saudi Arabia according to criteria. Then, it was analyzed using a sentiment analysis, one of data mining techniques. All three companies have similar likes and followers as they serve customers as B2B and B2C companies. In addition, for Al Rajhi no negative sentiment was detected in English posts, while it can be seen that Internet penetration of both banks are higher than BUPA, rarely mentioned in few hours. This study helps to predict the overall popularity as well as the perception or real mood of people by identifying the positive and negative feelings or emotions behind customers' social media posts or messages. This research presents meaningful insights in data-driven approaches using a specific data mining technique as a tool for corporate decision-making and forecasting. Understanding what the key issues are from customers' perspective, it becomes possible to develop a better data-based global strategies to create a sustainable competitive advantage.

• Korean journal of communication and information
• /
• v.81
• /
• pp.329-362
• /
• 2017

This study starts from the awareness that 'rebellious communication' is still being regulated in various ways even though 'rebellious communication' was declared unconstitutional in a decision by the Constitutional Court in 2002. The meaning of 'rebellious' has been amplified and transformed at various points through the censorship systems established during the Japanese colonial era, the US military period, and the regime of Park Jung-hee. In particular, 'rebellious communication' is regulated to protect 'national security' and 'social customs' from the perspective of power. This study analyzed discourses containing judgement about the Park Jung-geun case and the violation of the National Security Law using retweet accounts or posts related to North Korea. This study explores the genealogy of 'rebellious communication' based on its relationship to the characteristics of Twitter and specific individuals.

• Journal of Contemporary Eastern Asia
• /
• v.18 no.1
• /
• pp.49-69
• /
• 2019

Over the last couple of years, digital diplomacy has become a fascinating area of research among Mass Communication, Peace and Conflict Studies, and International Affairs scholars. Social media and new technology open up new avenues for governments, individuals, and organizations to engage with foreign audiences. However, developing countries' governments are still lacking in the realization of the potential of social media. This study aims to analyze the usage of social media (Facebook & Twitter) by the two biggest countries in South Asia (Pakistan and India). I selected 10 government officials' social media accounts including prime ministers', national press offices', military public relations offices', public diplomacy divisions', and ministries of foreign offices' profiles. The study relies on quantitative content analysis and a comparative research approach. The total number of analyzed Twitter tweets (n=1,015) and Facebook posts (n=1,005) include 10 accounts, five from each country. In light of Kent and Taylor's (1998) dialogic communication framework, the results indicate that no digital engagement and dialogue occurs between government departments and the public through social networking sites. Government departments do not engage with local or foreign audiences through digital media. When comparing both countries, results reveal that India has more institutionalized and organized digital diplomacy. In terms of departmental use of social media, the digital diplomacy division and foreign office of India is more active than other government departments in that nation. Meanwhile, Pakistan's military public relations office and press office is more active than its other government departments. In conclusion, both countries realize the potential of social media in digital diplomacy, but still lack engagement with foreign audiences.

• Asian Journal for Public Opinion Research
• /
• v.8 no.3
• /
• pp.393-406
• /
• 2020

The discourse on the lockdown in Indonesia is getting stronger due to the increasing number of positive cases of the coronavirus and the death rate. As of August 12, 2020, the confirmed number of COVID-19 cases in Indonesia reached 130,718. There were 85,798 victims who have recovered and 5,903 who have died. Data show a significant increase in cases of COVID-19 every day. For this reason, there needs to be an evaluation of the government policy of the Republic of Indonesia in dealing with the COVID-19 pandemic in Indonesia. An evaluation of policies for handling the pandemic must include public opinion to determine any weaknesses of this policy. The development of public opinion about the lockdown policy can be understood through social media. During the COVID-19 pandemic, measuring public opinion through traditional methods (surveys) was difficult. For this reason, we utilized big data on social media as research data. The main purpose of this study is to understand public opinion on the lockdown policy in overcoming the COVID-19 pandemic in Indonesia. The things observed included: volume of Twitter users, top influencers, top tweets, and communication networks between Twitter users. For the methodological development of future public opinion research, the researchers outline the obstacles faced in researching public opinion based on big data from Twitter. The research results show that the lockdown policy is an interesting issue, as evidenced by the number of active users (79,502) forming 133,209 networks. Posts about the lockdown on Twitter continued to increase after the implementation of the lockdown policy on April 10, 2020. The lockdown policy has caused various reactions, seen from the word analysis showing 14.8% positive sentiment, 17.5% negative, and 67.67% non-categorized words. Sources of information who have played the roles of top influencers regarding the lockdown policy include: Jokowi (the president of the Republic of Indonesia), online media, television media, government departments, and governors. Based on the analysis of the network structure, it shows that Jokowi has a central role in controlling the lockdown policy. Several challenges were found in this study: 1) choosing keywords for downloading data, 2) categorizing words containing public opinion sentiment, and 3) determining the sample size.

• Journal of Digital Convergence
• /
• v.18 no.6
• /
• pp.9-16
• /
• 2020

The purpose of this study is to understand the public needs for AI education actively promoted and supported by the current government. In doing so, 11 metropolitan news articles and Twitter posts regarding AI education that have been posted from January 1, 2018 to December 31, 2019 were collected. Then, word frequency analysis using TF(Term Frequency) method and LDA(Latent Dirichlet Allocation) method of topic modeling analysis were conducted. The topics of the news articles turn out to be a macroscopic policy support such as 'training female manpower in the AI field' and 'curriculum reform of university and K-12', whereas the topics of twitter delineate more detailed social perception on future society, such as future competencies and pedagogical methods, including 'coexistence with intelligent robots', 'coding education', and 'humane education competence development'. The findings are expected to be used to suggest the implications for the composition and management of AI curriculum as well as the basic framework of human resources development in the future industry.

• Journal of the Korean Society for Library and Information Science
• /
• v.56 no.3
• /
• pp.47-72
• /
• 2022

This study aims to understand the trends of subjects related to real estate policies and public's emotional opinion on the policies. Two keywords related to real estate policies such as "real estate policy" and "real estate measure" were used to collect tweets created from February 25, 2008 to August 31, 2021. A total of 91,740 tweets were collected and we applied sentiment analysis and dynamic topic modeling to the final preprocessed and categorized data of 18,925 tweets. Sentiment analysis and dynamic topic model analysis were conducted for a total of 18,925 posts after preprocessing data and categorizing them into supply, real estate tax, interest rate, and population variance. Keywords of each category are as follows: the supply categories (rental housing, greenbelt, newlyweds, homeless, supply, reconstruction, sale), real estate tax categories (comprehensive real estate tax, acquisition tax, holding tax, multiple homeowners, speculation), interest rate categories (interest rate), and population variance categories (Sejong, new city). The results of the sentiment analysis showed that one person posted on average one or two positive tweets whereas in the case of negative and neutral tweets, one person posted two or three. In addition, we found that part of people have both positive as well as negative and neutral opinions towards real estate policies. As the results of dynamic topic modeling analysis, negative reactions to real estate speculative forces and unearned income were identified as major negative topics and as for positive topics, expectation on increasing supply of housing and benefits for homeless people who purchase houses were identified. Unlike previous studies, which focused on changes and evaluations of specific real estate policies, this study has academic significance in that it collected posts from Twitter, one of the social media platforms, used emotional analysis, dynamic topic modeling analysis, and identified potential topics and trends of real estate policy over time. The results of the study can help create new policies that take public opinion on real estate policies into consideration.

• Journal of Digital Contents Society
• /
• v.19 no.1
• /
• pp.157-163
• /
• 2018

People who use SNS publish their diverse ideas on SNS every day. The data posted on the SNS contains many people's thoughts and opinions. In particular, popular keywords served on Twitter compile the number of frequently appearing words in user posts and rank them. However, this method is sensitive to unnecessary data simply by listing duplicate words. The proposed method determines the ranking based on the topic of the word using the relationship diagram between words, so that the influence of unnecessary data is less and the main word can be stably extracted. For the performance comparison in terms of the descending keyword rank and the ratios of meaningless keywords among high rank 20 keywords, we make a comparison between the proposed scheme which is based on morphological analysis and PageRank, and the existing scheme which is based on the number of appearances. As a result, the proposed scheme and the existing scheme have included 55% and 70% of meaningless keywords among high rank 20 keywords, respectively, where the proposed scheme is improved about 15% compared with the existing scheme.

• 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 Information Technology Services
• /
• v.15 no.3
• /
• pp.147-155
• /
• 2016

According to rapid development of technology, web text is growing explosively and attracting many fields as substitution for survey. The user of Facebook is reaching up to 113 million people per month, Twitter is used in various institution or company as a behavioral analysis tool. However, many research has focused on meaning of the text itself. And there is a lack of study for text's creation subject. Therefore, this research consists of sex/age text classification with by using 20,187 Facebook users' posts that reveal the sex and age of the writer. This research utilized Convolution Neural Networks, a type of deep learning algorithms which came into the spotlight as a recent image classifier in web text analyzing. The following result assured with 92% of accuracy for possibility as a text classifier. Also, this research was minimizing the Korean morpheme analysis and it was conducted using a Korean web text to Authorship Attribution. Based on these feature, this study can develop users' multiple capacity such as web text management information resource for worker, non-grammatical analyzing system for researchers. Thus, this study proposes a new method for web text analysis.