dyadic experience sampling

Existing tools for dialogue research often lack modularity and adaptability, limiting their capacity to support diverse conversational contexts and experimental requirements. To address this gap, this work presents Dyadic (chatdyadic.com), a web-based, extensible platform that uniquely integrates multimodal text-and-speech interaction, real-time AI-generated suggestions, live researcher monitoring, and context-sensitive dynamic questionnaires within a unified system. Designed for zero-code configuration, Dyadic seamlessly interoperates with mainstream survey platforms, substantially enhancing experimental flexibility and ecological validity. By offering an out-of-the-box yet highly customizable environment for both human–human and human–agent dialogue studies, Dyadic lowers technical barriers and significantly expands the design space for empirical research in interactive communication.

Current AI systems research predominantly relies on one-off evaluations, failing to capture the dynamic, longitudinal interaction between users and systems—including learning, adaptation, and repurposing—thereby creating methodological bottlenecks in long-term deployment, evaluation design, and data collection. To address this, this project organized a UIST workshop focused on practical challenges of longitudinal interaction research, integrating keynote presentations, small-group discussions, and hands-on sessions. It systematically proposed deployment strategies, evaluation protocols, and data collection frameworks tailored for sustained studies, and developed reusable tool prototypes. Key contributions include: (1) a structured longitudinal research framework; (2) an open-source toolchain supporting long-term human-AI interaction studies; and (3) an emerging cross-institutional academic community. The project advances longitudinal interaction research from a niche practice to a mainstream methodology in human-computer interaction, significantly enhancing researchers’ capacity to design and conduct sustained, real-world human-AI collaboration studies.

Existing methods for measuring team interpersonal dynamics—such as Cross-Recurrence Quantification Analysis (CRQA), Granger causality, and transfer entropy—are largely confined to either synchrony or unidirectional influence, lacking a unified representation that integrates psychological interpretability with behavioral system relevance. Method: We propose the “contextual matrix”—a linear dynamical model that jointly captures inter-individual behavioral synchrony and directed influence within a single, decomposable framework; its parameters map directly onto psychologically meaningful collaboration features. The approach integrates sequential Bayesian inference with eye-tracking analysis. Results: On synthetic data, the model accurately recovers ground-truth dynamics. In human collaborative experiments, it robustly identifies task-dependent dynamic differences, significantly predicts behavioral performance (p < 0.001), and aligns theoretically with established metrics. This framework establishes a novel, interpretable, and empirically verifiable paradigm for modeling team collaboration mechanisms.

This work addresses a fundamental limitation in traditional behavioral measurement, which often relies on passive observation under static or weakly controlled conditions and struggles to disentangle distinct internal mechanisms that produce similar overt behaviors. Treating human behavior as the observable output of a dynamic system, this study introduces— for the first time—the principles of system identification into behavioral science. It proposes a closed-loop experimental framework based on structured perturbations: precise, programmable disturbances are delivered via immersive environments while multimodal behavioral trajectories are simultaneously recorded. These data are integrated with dynamic computational models to enable mechanism-driven, real-time inference. By synergistically combining psychometrics, experimental design, and generative modeling, the approach advances behavioral science from descriptive analysis toward an identifiable, reproducible paradigm centered on generative mechanisms, substantially enhancing both theoretical rigor and causal interpretability in behavioral inference.

Current research on online behavioral change suffers from narrow behavioral coverage, overreliance on API-restricted platforms as data sources, and a persistent theory–empiricism gap. To address these limitations, this study conducts a systematic literature review of 148 peer-reviewed articles published between 2000 and 2023, constructing a four-dimensional knowledge graph encompassing behavioral categories, detection methodologies, platform ecosystems, and theoretical foundations. Our analysis uncovers three salient trends: (1) affective orientation dominates behavioral modeling; (2) platform distribution is heavily skewed toward a few API-constrained platforms; and (3) theoretical integration remains markedly underdeveloped. We propose a novel methodology framework—“Multi-behavioral Modeling, Heterogeneous Data Integration, and Theory–Practice Alignment”—and deliver a structured research map that precisely identifies critical gaps. This work advances the computational behavioral paradigm and offers an actionable methodological guide for digital social governance.

Traditional questionnaires struggle to simultaneously capture qualitative depth and quantitative structure, limiting comprehensive understanding of complex social phenomena. This study proposes a dynamic survey platform powered by large language models (LLMs) that, for the first time, enables real-time semantic clustering of open-ended responses. Through an interactive feedback mechanism, users can rate, rank, and reflect on these clusters, generating visual reports that integrate qualitative insights with quantitative analysis. Innovatively embedding LLMs within a closed-loop data collection framework, the approach facilitates dynamic comparisons between individual perspectives and group-level trends. Empirical validation across two field studies involving 93 participants demonstrates that the platform significantly enhances data richness and user engagement compared to conventional survey tools, while effectively fostering collaborative sensemaking.

This study addresses the lack of systematic preprocessing standards, integrated analytical workflows, and cross-method consistency checks in current computer-based assessment process data. To bridge this gap, the authors propose an end-to-end analytical framework featuring a unified preprocessing pipeline and a dual-path analysis paradigm that synergistically combines feature engineering with model-based inference. The framework incorporates large language models (LLMs) to standardize action sequences and facilitate process-data-driven differential item functioning (DIF) detection. Technically, it integrates timestamp correction, action chunking, n-gram and TF-IDF feature extraction, multidimensional scaling, hidden Markov modeling, and subtask identification. Empirical results demonstrate that n-gram–based behavioral clustering offers diagnostic value for incorrect responders, multidimensional scaling effectively reconstructs behavioral constructs, and process data can identify and mitigate construct-irrelevant group differences.

Traditional ecological momentary assessment (EMA) analyses often rely on simplified metrics such as means, which inadequately capture individual longitudinal dynamics. This study moves beyond mean-based approaches by integrating sequence analysis, principal component analysis, and K-means clustering to directly identify latent subgroups exhibiting similar behavioral patterns from full time-series data, while effectively accommodating heterogeneity in sample size and observation frequency. Validated against latent class analysis (LCA) and latent transition analysis (LTA), the proposed method successfully uncovers distinct stress trajectory subgroups in real-world EMA stress data and substantially enhances explanatory power for variability in cognitive performance.