Analytics

Bibliometric topic-modeling is essential for synthesizing scientific literature, yet its adoption by domain-expert teams is hindered by technical barriers. This pilot study benchmarks four topic modeling paradigms on 286 CO₂ mineralization papers (2013–2025), with all methods implemented end-to-end on consumer hardware by researchers without prior natural language processing (NLP) training. Its principal methodological contribution is a four-level calibration protocol for zero-shot large language models (LLMs) used as innovation detectors. Naive zero-shot prompting flagged 71.0% of the corpus as innovative, over-attributing novelty by a factor of 22.7 relative to a calibrated statistical ensemble. A qualitative-strict prompt reduced this to 26.6%, while a structurally different unified prompt yielded 28.0%. Together, these results indicate a floor near 28% that prompt engineering alone does not overcome. A self-reflection pass, in which the model re-reads and revises its own output, instead reduced the flag rate to 3.5%, close to the ensemble’s 3.13%. The papers retained by self-reflection form a strict subset of those retained by the unified prompt, suggesting that the model applies a consistent discriminative criterion rather than simply adopting a stricter prompting frame. On this basis, we propose a transferable four-layer triangulation protocol combining statistical ensembles with complementary LLM regimes. The classical benchmark shows that no single pipeline dominates and we derive selection guidance accordingly.

Recent developments in artificial intelligence, including the emergence of generative AI and large language models, have brought changes to user interaction habits as well as interface design. These emerging technologies can be integrated into digital art repositories to reshape interaction paradigms through content enrichment, context-based recommendations, natural-language querying and automated artwork classification. As this landscape evolves, it is important to understand how these changes are reflected in user behavior. In this study, we present a comparative behavioral evaluation based on two versions of a publicly available digital repository for academic artworks: a traditional version and one incorporating a series of AI-powered features. A mixed factorial design with task counterbalancing was used to evaluate user behavior through an approach combining platform analytics, self-reported metrics and qualitative insights. This exploratory analysis identified feature-dependent differences in participants’ behavior and perceptions, and yielded preliminary observations that can inform large-scale research. Understanding how users perceive and engage with AI features can allow content providers to make informed decisions regarding their integration and streamline user interactions while remaining aligned with stakeholder expectations.

Forecasting stock prices, market trends, and associated emotions remains a complex challenge due to the market’s inherent volatility, nonlinearity, susceptibility to factors such as news events, and the limited availability of financial data. Stock prices are noisy, unpredictable, and sensitive to investor sentiment. To account for this, this study considers three models that effectively capture both the spatial relationships (similar sector stocks) between stocks and the temporal trends in their price movements, thereby addressing limitations in traditional forecasting methods. Specifically, we consider semiconductor stocks, which are known for their high volatility and strong correlation to technological advancements. The proposed models include Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) neural networks, a GNN-based architecture, and a Spatio-Temporal Graph Neural Network (ST-GNN). These models are trained, tested, and validated on datasets that combine historical data with sentiment insights from financial news sources. It utilizes a GRU-based temporal module to improve recognition of evolving market patterns. We demonstrate our model’s ability to adapt to dynamic financial environments and predict whether a stock closes at a higher or lower price than at the trading day open.