Conference Agenda (All times are shown in Eastern Daylight Time)

Understanding public perceptions and government responsiveness through digital platforms is crucial for accountable and ethical policymaking, enhancing the role of e-government users is particularly effective in communicating policy information. This paper applies computational social science methods, including Large Language Model driven content analysis and sentiment analysis, to examine longitudinal trends in citizen appeals related to fertility policy on China’s leading e-petition platform and government responses from social media platform. We identify alignments and mismatches between citizen’s demands and official actions, emphasizing the important role of citizens in digital governance. Findings from our research reveal the fundamental role of government policy information on citizens’ policy literacy and life decisions: Changes in fertility policy influence citizen’s information-seeking behavior, altering the types of information they pursue online. Our study therefore recommends a human-centric approach for policy analytics and highlights inclusivity in digital policy information dissemination.

Expectation confirmation in data retrieval systems remains a critical yet understudied issue. To bridge this gap, this paper proposes a multi-dimensional framework for investigating the confirmation formation in the context of data retrieval, drawing upon the Expectation-Confirmation Theory and expectancy-value theory. Furthermore, it introduces a deep-learning model called Multiple-Expert System based on Bayesian Neural Networks (MES-BNN) to predict multi-dimensional confirmation by analyzing users’ search behavior data. The findings reveal the multi-dimensional and context-dependent nature of confirmation. In the data retrieval context, users discern gaps between their search experiences and expectations in terms of task, cognition, and emotion, collectively forming a three-dimensional confirmation. This three-dimensional confirmation can be predicted through search behavior data mining. Furthermore, the MES-BNN model demonstrates its effectiveness in mining small-scale behavioral data, enabling automatic and accurate prediction of the three-dimensional confirmation and contributes to advancing data analytical approaches employed in user-oriented retrieval studies in the intelligent age.

Generative search engines address limitations of traditional data retrieval systems, including rigid keyword-based queries, impersonalized results, and choice overload. However, they introduce new challenges such as prompt literacy demands, hallucination risks, and reduced output diversity. While these trade-offs fundamentally reshape user interactions with search systems, the comparative dynamics of search behavior across generative and traditional systems remain underexplored. This study bridges this gap by analyzing data search behaviors through a search stage framework, revealing distinct interaction patterns. Building upon the Information Search Process Model and Information Seeking Behavior Model, this study proposes a stage model of data search behavior. Experimental data were analyzed to explore the proposed model. Our findings identify both convergent and divergent behavioral patterns: while certain search stage types and behaviors overlap across systems, substantial differences emerge in stage transition dynamics (encompassing transition types, frequencies, and pathways) and specific behaviors. This study uncovers a fundamental tension in data search: traditional retrieval systems support broad exploratory patterns but constrain interaction depth, while generative search engines enable deeper engagement at the expense of exploration breadth. This trade-off between breadth and depth presents significant implications for the design of next-generation intelligent retrieval systems that optimize both dimensions of user interaction.