Preliminary Conference Agenda

The power and expressiveness of AIs are rapidly increasing, and now AIs have the ability to complete tasks in crowdsourcing as if they were human crowd workers. Therefore, the development of methods to effectively aggregate the results of tasks performed by AIs and humans is becoming a critical problem. In this study, we revisit the Dawid-Skene model that has been used to aggregate human votes to obtain better results in classification problems. Most of the state-of-the-art AI classifiers predict the class probabilities as their output. Considering the probabilities represent their uncertainty, utilizing them in Dawid-Skene aggregation may provide higher-quality annotations. To this end, we introduce a variation of the Dawid-Skene model to directly use the probabilities without discarding them and conduct experiments with two real-world datasets of different domains. Experimental results show that the Dawid-Skene model with probabilities improves the overall accuracy. Moreover, a detailed analysis shows that the aggregation results were improved for classification tasks with high uncertainty.

Academic integrity is the foundation of quality higher education. However, the resources explaining the concept tend to be definition-driven, have complex language and sometimes even a severe tone to discourage students from breaking rules. This project deployed a gamified approach, designing and evaluating a 3D immersive video game for university students to facilitate their understanding and adoption of academic integrity principles. The game allowed students to be immersed in a virtual campus through an avatar and navigate a campus (e.g., garden, library, cafe, student accommodation) with scenario-based, academic integrity related dialogues with in-game characters. The paper aims to showcase the game design and student feedback of the game. Observation (e.g., eye-tracking) and interviews were conducted with 15 participants. Thematic analysis of the data shows that the game greatly enhanced student understanding of academic integrity concepts by providing contextualized memorability whilst relieving anxiety. Students’ engagement with the game was linked to game features such as appealing aesthetics, customization, and contextualization. The paper concludes by offering recommendations concerning the employment of gamification as an educational approach for instructing students in higher education on complex concepts, such as academic integrity.

The openness characteristic of social networks facilitates the rapid spread of rumors, necessitating effective methods for detecting and managing the abundance of rumors on social media. Existing studies have primarily focused on improving the accuracy of rumor detection, but often overlook the vital aspects of interpretability and explanation of rumor patterns, limiting their credibility and real-world usability. Additionally, previous works have typically examined only a subset of user features, content, and spreading structure, neglecting the analysis of compound rules. To address these limitations, we propose a novel framework for detecting rumor patterns that emphasize comprehensive feature construction and the explanation of compound rules. Our framework incorporates multi-dimensional features, including user characteristics, post content, and the structure of information propagation. Advanced techniques, including large language models (such as ChatGPT) and graph motif discovery algorithms, are employed for feature construction. By leveraging diverse features, crucial integrated rules identified by Rulefit can investigate the contextually dependent associations among various interrelated rumor factors. We consolidate and analyze seven distinct rumor patterns based on the Credible Early Detection Dataset, deriving valuable insights into the inherent characteristics of rumors. The recognition of rumor patterns empowers social media platforms and fact-checking organizations to develop targeted and explainable interventions that effectively mitigate the spread of rumors and safeguard the integrity of information. These interventions greatly enhance the transparency and trustworthiness of rumor management, fostering a more reliable information ecosystem.