In high-stakes decision-making, the acceptance of AI recommendations depends not only on system accuracy but also on how decisions are explained. While prior work on explainable AI has largely focused on transparency and interpretability, less attention has been paid to the persuasive dimension of explanations. To address this gap, we investigate how rhetorical strategies drawn from Cialdini’s persuasion theory, when embedded in natural language explanations generated by large language models (LLMs), influence user compliance and their ability to recognize persuasive intent. We conducted a controlled survey study with 129 participants in two application domains—finance and healthcare—where participants evaluated both a baseline and a persuasive explanation for an AI-generated decision across favorable and unfavorable outcomes. In a complementary task, participants rated ten short explanations on perceived persuasiveness and factual strength, enabling us to measure awareness of persuasive intent. Our results show that persuasive explanations significantly increased compliance in the healthcare scenario (p <.001), whereas baseline explanations were more effective in finance (p <.001), regardless of whether the AI decision was positive or negative. A notable proportion of participants rated explanations containing at least one of Cialdini’s persuasion techniques as highly persuasive, yet simultaneously judged them to be factually weaker. Importantly, we found no statistically significant evidence that participants’ ability to recognize persuasive intent influenced compliance. These findings highlight the dual role of persuasive explanations: they can enhance foster compliance in sensitive contexts such as healthcare but risk undermining trust in domains like finance. For HCI and IUI, our study underscores that explanations are not neutral vessels of information: their rhetorical form substantially shapes how users perceive and engage with AI-assisted decision-making. Designers of explainable AI systems should therefore carefully balance transparency and persuasion when developing interfaces for high-stakes applications.

OBJECTIVES: This study aims to summarize the usage of large language models (LLMs) in the process of creating a scientific review by looking at the methodological papers that describe the use of LLMs in review automation and the review papers that mention they were made with the support of LLMs. MATERIALS AND METHODS: The search was conducted in June 2024 in PubMed, Scopus, Dimensions, and Google Scholar by human reviewers. Screening and extraction process took place in Covidence with the help of LLM add-on based on the OpenAI GPT-4o model. ChatGPT and Scite.ai were used in cleaning the data, generating the code for figures, and drafting the manuscript. RESULTS: Of the 3788 articles retrieved, 172 studies were deemed eligible for the final review. ChatGPT and GPT-based LLM emerged as the most dominant architecture for review automation (n = 126, 73.2%). A significant number of review automation projects were found, but only a limited number of papers (n = 26, 15.1%) were actual reviews that acknowledged LLM usage. Most citations focused on the automation of a particular stage of review, such as Searching for publications (n = 60, 34.9%) and Data extraction (n = 54, 31.4%). When comparing the pooled performance of GPT-based and BERT-based models, the former was better in data extraction with a mean precision of 83.0% (SD = 10.4) and a recall of 86.0% (SD = 9.8). DISCUSSION AND CONCLUSION: Our LLM-assisted systematic review revealed a significant number of research projects related to review automation using LLMs. Despite limitations, such as lower accuracy of extraction for numeric data, we anticipate that LLMs will soon change the way scientific reviews are conducted.

Data science is the practice of deriving insight from data, enabled by modeling, computational methods, interactive visual analysis, and domain-driven problem solving. Data science draws from methodology developed in such fields as applied mathematics, statistics, machine learning, data mining, data management, visualization, and HCI. It drives discoveries in business, economy, biology, medicine, environmental science, the physical sciences, the humanities and social sciences, and beyond. Machine learning and data mining and visualization are integral parts of data science, and essential to enable sophisticated analysis of data. Nevertheless, both research areas are currently still rather separated and investigated by different communities rather independently. The goal of this workshop is to bring researchers from both communities together in order to discuss common interests, to talk about practical issues in application-related projects, and to identify open research problems. This summary gives a brief overview of the ACM KDD Workshop on Visualization in Data Science (VDS at ACM KDD and IEEE VIS), which will take place virtually on Aug 14-18, 2022 (Held in conjunction with KDD'22). The workshop website is available at http://www.visualdatascience.org/2022/

Streamflow prediction from meteorological observations provides the basic information for the management of water resources systems. The amount and magnitude of streamflow has long term consequences on human lives and the environment. Various approaches have been proposed to simulate streamflow records, ranging from physically based models to conceptual and fully data-driven models. However, the quality of streamflow prediction can be more reliable with intelligence-based data-driven models that handle nonlinear hydrological processes. We propose FlowDyn, a dynamic web based streamflow prediction pipeline to intelligently simulate and forecast global streamflow time series data. In this research a number of data driven deep learning (DL) models including multi-layer perception (MLP), long short-term memory (LSTM) and a hybrid network of convolutional neural network and LSTM (CNN-LSTM) have been implemented as a pipeline to analyze and forecast sequential streamflow values that are embedded within a web-based application for visualization. To improve the quality of streamflow forecast a set of climate and flow influencing factors were obtained from weather stations belonging to different countries across the globe. This study has focused on the effects of input data characteristics on model performance; therefore, the amount of input data and data correlation have been considered. Datasets are gathered from different databases including CAMELS [1], [2], NCDC and GRDC. To impute the missing values and pre-process the available data, several methods have been used and a reliable dataset was generated for models in the pipeline to run prediction tasks on. The developed prediction models were validated and tested using NSE (Nash–Sutcliffe efficiency), KGE (Kling-Gupta efficiency), Normalized Mutual Information (NMI), and Root Mean Squared Error (RMSE) indices. A JavaScript (JS) based web application was provided with the pipeline for users to view flow prediction and variabilities over any station at any watershed system and region. Through the findings of this paper, we advocate the merit of applying data-driven neural models in the field of rainfall-runoff prediction and prove it with global hydrological and weather data.

Intelligent virtual agents increasingly use machine learning to model the needs and preferences of their users in order to give personalized support. In this paper we present a vision of "human-centric modeling" that moves this practice beyond the automated estimation of users' current preferences based on observable behaviors to a modeling process that a) considers users' hidden characteristics rather than observable behaviors, b) models possible futures rather than users' current state, and c) gives users an opportunity to interactively control this modeling process. This vision focuses on the long-term needs of individual humans and a genuine betterment of society.

Nowadays we are drowning in data of various varieties. For all these mixed types and categories of data there exist even more different analysis approaches, often done in single hand-written solutions. We propose to extend HyPer, a main memory database system to a uniform data agent platform following the one system fits all approach for solving a wide variety of data analysis problems. We achieve this by applying a flexible operator concept to a set of various important data exploration algorithms. With that, HyPer solves analytical questions using clustering, classification, association rule mining and graph mining besides standard HTAP (Hybrid Transaction and Analytical Processing) workloads on the same database state. It enables to approach the full variety and volume of HTAP extended for data exploration (HTAPx), and only needs knowledge of already introduced SQL extensions that are automatically optimized by the database's standard optimizer. In this demo we will focus on the benefits and flexibility we create by using the SQL extensions for several well-known mining workloads. In our interactive webinterface for this project named HyPerInsight we demonstrate how HyPer outperforms the best open source competitor Apache Spark in common use cases in social media, geo-data, recommender systems and several other.

Data can encapsulate different object groupings in subspaces of arbitrary dimension and orientation. Finding such subspaces and the groupings within them is the goal of generalized subspace clustering. In this work we present a generalized subspace clustering technique capable of finding multiple non-redundant clusterings in arbitrarily-oriented subspaces. We use Independent Subspace Analysis (ISA) to find the subspace collection that minimizes the statistical dependency (redundancy) between clusterings. We then cluster in the arbitrarily-oriented subspaces identified by ISA. Our algorithm ISAAC (Independent Subspace Analysis and Clustering) uses the Minimum Description Length principle to automatically choose parameters that are otherwise difficult to set. We comprehensively demonstrate the effectiveness of our approach on synthetic and real-world data.

How can we retrieve information from sparse graphs? Traditional graph mining approaches focus on discovering dense patterns inside complex networks, for example modularity-based or cut-based methods. However, most real world data sets are very sparse. Nevertheless, traditional approaches tend to omit interesting sparse patterns like stars. In this paper, we propose a novel graph mining technique modeling the transitivity and the hub ness of a graph using structure primitives. We exploit these structure primitives for effective graph compression using the Minimum Description Length Principle. The compression rate is an unbiased measure for the transitivity or hub ness and therefore provides interesting insights into the structure of even very sparse graphs. Since real graphs can be composed of sub graphs of different structures, we propose a novel algorithm CXprime (Compression-based exploiting Primitives) for clustering graphs using our coding scheme as an objective function. In contrast to traditional graph clustering methods, our algorithm automatically recognizes different types of sub graphs without requiring the user to specify input parameters. Additionally we propose a novel link prediction algorithm based on the detected substructures, which increases the quality of former methods. Extensive experiments evaluate our algorithms on synthetic and real data.

The density-based clustering algorithm DBSCAN is a fundamental technique for data clustering with many attractive properties and applications. However, DBSCAN requires specifying all pair wise (dis)similarities among objects that can be non-trivial to obtain in many applications. To tackle this problem, in this paper, we propose a novel active density-based clustering algorithm, named Act-DBSCAN, which works under a restricted number of used pair wise similarities. Act-DBSCAN exploits the pair wise lower-bounding (LB) similarities to initialize the cluster structure. Then, it adaptively selects the most informative pair wise LB similarities to update with the real ones in order to reconstruct the result until the budget limitation is reached. The goal is to approximate as much as possible the true clustering result with each update. Our Act-DBSCAN framework is built upon a proposed probabilistic model to score the impact of the update of each pair wise LB similarity on the change of the intermediate clustering structure. Deriving from this scoring system and the monotonicity and reduction property of our active clustering process, we propose the two efficient algorithms to iteratively select and update pair wise similarities and cluster structure. Experiments on real datasets show that Act-DBSCAN acquires good clustering results with only a few pair wise similarities, and requires only a small fraction of all pair wise similarities to reach the DBSCAN results. Act-DBSCAN also outperforms other related techniques such as active spectral clustering.