False information spreads on social media, and fact-checking is a potential countermeasure. However, there is a severe shortage of fact-checkers; an efficient way to scale fact-checking is desperately needed, especially in pandemics like COVID-19. In this study, we focus on spontaneous debunking by social media users, which has been missed in existing research despite its indicated usefulness for fact-checking and countering false information. Specifically, we characterize the tweets with false information, or fake tweets, that tend to be debunked and Twitter users who often debunk fake tweets. For this analysis, we create a comprehensive dataset of responses to fake tweets, annotate a subset of them, and build a classification model for detecting debunking behaviors. We find that most fake tweets are left undebunked, spontaneous debunking is slower than other forms of responses, and spontaneous debunking exhibits partisanship in political topics. These results provide actionable insights into utilizing spontaneous debunking to scale conventional fact-checking, thereby supplementing existing research from a new perspective.

Collecting good ideas is vital for organizations, especially companies, to retain their competitiveness. Social media is gathering attention as a place to extract ideas efficiently; however, the characteristics of ideas and the posters of ideas on social media are underexamined. Thus, this study aims to characterize spontaneous ideation contests among social media users by taking an event of Facebook’s name change to Meta as a case study. As a dataset, we comprehensively collect tweets containing new acronyms of Big Tech companies, which we treat as an "idea" in this work. In the analysis, we especially focus on the diversity of ideas, which would be the main reason for enlisting social media for idea generation. As the main results, we discovered that social media users offered a wider range of ideas than those in mainstream media. The follow-follower network of the users suggested that the users’ position on the network is related to the preferred ideas. Additionally, we discovered a link between the amount of user interaction on social media and the diversity of ideas. This study would promote the use of social media as a part of open innovation and co-creation processes in the industry.

For efficient policy-making, a thorough recognition of controversial topics is crucial because the cost of unmitigated controversies would be extremely high for society. However, identifying controversial topics is costly. In this paper, we proposed a framework to search for controversial topics comprehensively. We then conducted a retrospective analysis of the controversial topics of COVID-19 with data obtained via Twitter in Japan as a case study of the framework. The results show that the proposed framework can effectively detect controversial topics that reflect current reality. Controversial topics tend to be about the government, medical matters, economy, and education; moreover, the controversy score had a low correlation with the traditional indicators-scale and sentiment of the topics-which suggests that the controversy score is a potentially important indicator to be obtained. We also discussed the difference between highly controversial topics and less controversial ones despite their large scale and sentiment.

In the fashion industry where social media has a growing presence, it is increasingly important to find the emergence of people's new tastes in the early stage based on the photos posted there. However, the amount of photos posted on fashion social media is so large that it is almost impossible for people to examine them manually. Also, previous studies on image analysis in social media focus only on individual items for trend detection. Therefore, in this research, we propose a novel framework for capturing changes in people's tastes in terms of coordination rather than individual items. In the framework, we apply Emerging Topic Detection (ETD) to multiple meta-data of images automatically extracted by deep learning. In ETD, new topics which did not exist previously are detected by comparing multiple time windows. To better capture the nature of fashion topics, we employ a clustering method MULIC as a topic detection method, which is density-based, centroid-based, and designed for categorical data. Our experiments with real-world data, in terms of method stability, qualitative evaluation of the output, and experts review, confirmed that the Emerging Topics were properly captured.