RESUMEN

Large Language Models (LLMs) are powerful but also raise significant security concerns, particularly regarding the harm they can cause, such as generating fake news that manipulates public opinion on social media and providing responses to unethical activities. Traditional red teaming approaches for identifying AI vulnerabilities rely on manual prompt construction and expertise. This paper introduces AdversaFlow, a novel visual analytics system designed to enhance LLM security against adversarial attacks through human-AI collaboration. AdversaFlow involves adversarial training between a target model and a red model, featuring unique multi-level adversarial flow and fluctuation path visualizations. These features provide insights into adversarial dynamics and LLM robustness, enabling experts to identify and mitigate vulnerabilities effectively. We present quantitative evaluations and case studies validating our system's utility and offering insights for future AI security solutions. Our method can enhance LLM security, supporting downstream scenarios like social media regulation by enabling more effective detection, monitoring, and mitigation of harmful content and behaviors.

RESUMEN

Tactics play an important role in team sports by guiding how players interact on the field. Both sports fans and experts have a demand for analyzing sports tactics. Existing approaches allow users to visually perceive the multivariate tactical effects. However, these approaches require users to experience a complex reasoning process to connect the multiple interactions within each tactic to the final tactical effect. In this work, we collaborate with basketball experts and propose a progressive approach to help users gain a deeper understanding of how each tactic works and customize tactics on demand. Users can progressively sketch on a tactic board, and a coach agent will simulate the possible actions in each step and present the simulation to users with facet visualizations. We develop an extensible framework that integrates large language models (LLMs) and visualizations to help users communicate with the coach agent with multimodal inputs. Based on the framework, we design and develop Smartboard, an agent-based interactive visualization system for fine-grained tactical analysis, especially for play design. Smartboard provides users with a structured process of setup, simulation, and evolution, allowing for iterative exploration of tactics based on specific personalized scenarios. We conduct case studies based on real-world basketball datasets to demonstrate the effectiveness and usefulness of our system.

RESUMEN

In soccer, player scouting aims to find players suitable for a team to increase the winning chance in future matches. To scout suitable players, coaches and analysts need to consider whether the players will perform well in a new team, which is hard to learn directly from their historical performances. Match simulation methods have been introduced to scout players by estimating their expected contributions to a new team. However, they usually focus on the simulation of match results and hardly support interactive analysis to navigate potential target players and compare them in fine-grained simulated behaviors. In this work, we propose a visual analytics method to assist soccer player scouting based on match simulation. We construct a two-level match simulation framework for estimating both match results and player behaviors when a player comes to a new team. Based on the framework, we develop a visual analytics system, Team-Scouter, to facilitate the simulative-based soccer player scouting process through player navigation, comparison, and investigation. With our system, coaches and analysts can find potential players suitable for the team and compare them on historical and expected performances. For an in-depth investigation of the players' expected performances, the system provides a visual comparison between the simulated behaviors of the player and the actual ones. The usefulness and effectiveness of the system are demonstrated by two case studies on a real-world dataset and an expert interview.

RESUMEN

Understanding the input and output of data wrangling scripts is crucial for various tasks like debugging code and onboarding new data. However, existing research on script understanding primarily focuses on revealing the process of data transformations, lacking the ability to analyze the potential scope, i.e., the space of script inputs and outputs. Meanwhile, constructing input/output space during script analysis is challenging, as the wrangling scripts could be semantically complex and diverse, and the association between different data objects is intricate. To facilitate data workers in understanding the input and output space of wrangling scripts, we summarize ten types of constraints to express table space and build a mapping between data transformations and these constraints to guide the construction of the input/output for individual transformations. Then, we propose a constraint generation model for integrating table constraints across multiple transformations. Based on the model, we develop Ferry, an interactive system that extracts and visualizes the data constraints describing the input and output space of data wrangling scripts, thereby enabling users to grasp the high-level semantics of complex scripts and locate the origins of faulty data transformations. Besides, Ferry provides example input and output data to assist users in interpreting the extracted constraints and checking and resolving the conflicts between these constraints and any uploaded dataset. Ferry's effectiveness and usability are evaluated through two usage scenarios and two case studies, including understanding, debugging, and checking both single and multiple scripts, with and without executable data. Furthermore, an illustrative application is presented to demonstrate Ferry's flexibility.

RESUMEN

Propagation analysis refers to studying how information spreads on social media, a pivotal endeavor for understanding social sentiment and public opinions. Numerous studies contribute to visualizing information spread, but few have considered the implicit and complex diffusion patterns among multiple platforms. To bridge the gap, we summarize cross-platform diffusion patterns with experts and identify significant factors that dissect the mechanisms of cross-platform information spread. Based on that, we propose an information diffusion model that estimates the likelihood of a topic/post spreading among different social media platforms. Moreover, we propose a novel visual metaphor that encapsulates cross-platform propagation in a manner analogous to the spread of seeds across gardens. Specifically, we visualize platforms, posts, implicit cross-platform routes, and salient instances as elements of a virtual ecosystem - gardens, flowers, winds, and seeds, respectively. We further develop a visual analytic system, namely BloomWind, that enables users to quickly identify the cross-platform diffusion patterns and investigate the relevant social media posts. Ultimately, we demonstrate the usage of BloomWind through two case studies and validate its effectiveness using expert interviews.

RESUMEN

The integration of visualizations and text is commonly found in data news, analytical reports, and interactive documents. For example, financial articles are presented along with interactive charts to show the changes in stock prices on Yahoo Finance. Visualizations enhance the perception of facts in the text while the text reveals insights of visual representation. However, effectively combining text and visualizations is challenging and tedious, which usually involves advanced programming skills. This paper proposes a semi-automatic pipeline that builds links between text and visualization. To resolve the relationship between text and visualizations, we present a method which structures a visualization and the underlying data as a contextual knowledge graph, based on which key phrases in the text are extracted, grouped, and mapped with visual elements. To support flexible customization of text-visualization links, our pipeline incorporates user knowledge to revise the links in a mixed-initiative manner. To demonstrate the usefulness and the versatility of our method, we replicate prior studies or cases in crafting interactive word-sized visualizations, annotating visualizations, and creating text-chart interactions based on a prototype system. We carry out two preliminary model tests and a user study and the results and user feedbacks suggest our method is effective.

RESUMEN

Data charts are prevalent across various fields due to their efficacy in conveying complex data relationships. However, static charts may sometimes struggle to engage readers and efficiently present intricate information, potentially resulting in limited understanding. We introduce "Live Charts," a new format of presentation that decomposes complex information within a chart and explains the information pieces sequentially through rich animations and accompanying audio narration. We propose an automated approach to revive static charts into Live Charts. Our method integrates GNN-based techniques to analyze the chart components and extract data from charts. Then we adopt large natural language models to generate appropriate animated visuals along with a voice-over to produce Live Charts from static ones. We conducted a thorough evaluation of our approach, which involved the model performance, use cases, a crowd-sourced user study, and expert interviews. The results demonstrate Live Charts offer a multi-sensory experience where readers can follow the information and understand the data insights better. We analyze the benefits and drawbacks of Live Charts over static charts as a new information consumption experience.

RESUMEN

Querying time series based on their relations is a crucial part of multiple time series analysis. By retrieving and understanding time series relations, analysts can easily detect anomalies and validate hypotheses in complex time series datasets. However, current relation extraction approaches, including knowledge- and data-driven ones, tend to be laborious and do not support heterogeneous relations. By conducting a formative study with 11 experts, we concluded six time series relations, including correlation, causality, similarity, lag, arithmetic, and meta, and summarized three pain points in querying time series involving these relations. We proposed RelaQ, an interactive system that supports the time series query via relation specifications. RelaQ allows users to intuitively specify heterogeneous relations when querying multiple time series, understand the query results based on a scalable, multi-level visualization, and explore possible relations beyond the existing queries. RelaQ is evaluated with two cases and a user study with 12 participants, showing promising effectiveness and usability.

RESUMEN

To enhance the appeal and informativeness of data news, there is an increasing reliance on data analysis techniques and visualizations, which poses a high demand for journalists' abilities. While numerous visual analytics systems have been developed for deriving insights, few tools specifically support and disseminate viewpoints for journalism. Thus, this work aims to facilitate the automatic creation of sports news from natural language insights. To achieve this, we conducted an extensive preliminary study on the published sports articles. Based on our findings, we propose a workflow - 1) exploring the data space behind insights, 2) generating narrative structures, 3) progressively generating each episode, and 4) mapping data spaces into communicative visualizations. We have implemented a human-AI interaction system called SNIL, which incorporates user input in conjunction with large language models (LLMs). It supports the modification of textual and graphical content within the episode-based structure by adjusting the description. We conduct user studies to demonstrate the usability of SNIL and the benefit of bridging the gap between analysis tasks and communicative tasks through expert and fan feedback.

RESUMEN

Table tennis is a sport that demands high levels of technical proficiency and body coordination from players. Biomechanical fingerprints can provide valuable insights into players' habitual movement patterns and characteristics, allowing them to identify and improve technical weaknesses. Despite the potential, few studies have developed effective methods for generating such fingerprints. To address this gap, we propose TacPrint, a framework for generating a biomechanical fingerprint for each player. TacPrint leverages machine learning techniques to extract comprehensive features from biomechanics data collected by inertial measurement units (IMU) and employs the attention mechanism to enhance model interpretability. After generating fingerprints, TacPrint provides a visualization system to facilitate the exploration and investigation of these fingerprints. In order to validate the effectiveness of the framework, we designed an experiment to evaluate the model's performance and conducted a case study with the system. The results of our experiment demonstrated the high accuracy and effectiveness of the model. Additionally, we discussed the potential of TacPrint to be extended to other sports.

Asunto(s)

RESUMEN

High-quality data is critical to deriving useful and reliable information. However, real-world data often contains quality issues undermining the value of the derived information. Most existing research on data quality management focuses on tabular data, leaving semi-structured data under-exploited. Due to the schema-less and hierarchical features of semi-structured data, discovering and fixing quality issues is challenging and time-consuming. To address the challenge, this paper presents JsonCurer, an interactive visualization system to assist with data quality management in the context of JSON data. To have an overview of quality issues, we first construct a taxonomy based on interviews with data practitioners and a review of 119 real-world JSON files. Then we highlight a schema visualization that presents structural information, statistical features, and quality issues of JSON data. Based on a similarity-based aggregation technique, the visualization depicts the entire JSON data with a concise tree, where summary visualizations are given above each node, and quality issues are illustrated using Bubble Sets across nodes. We evaluate the effectiveness and usability of JsonCurer with two case studies. One is in the domain of data analysis while the other concerns quality assurance in MongoDB documents.

RESUMEN

CONTEXT: Many patients recovering from surgery in wards are disturbed by environmental noise. However, the effects of environmental noise on postoperative pain are unclear. OBJECTIVES: This study aimed to assess the association between postoperative noise and pain. METHODS: This prospective study included 182 women who underwent cesarean sections. Postoperative noise was continuously recorded, and pain intensity at rest was assessed using a numerical rating scale (NRS) for 0-6, 6-12, 12-18, and 18-24 h after the patients were returned to the ward. Cumulative pain scores were calculated by summing the NRS scores at each time point and comprised the primary outcome. The maximum pain NRS score and analgesic consumption during the 24 h after surgery were also recorded. RESULTS: Mean environmental noise intensity during the daytime was an independent factor for cumulative pain scores, maximum pain scores, and analgesic use during the first postoperative 24 h (ß, 0.37; 95% CI, 0.21-0.53 and ß, 0.12; 95% CI, 0.07-0.17; P < 0.001 for both; ß, 0.86; 95% CI, 0.25-1.46; P = 0.006). Cumulative and maximum NRS pain scores as well as the incidence of NRS ≥ 4 were significantly higher in patients under mean daytime environmental noise of ≥58, than <58 decibels (dB) (8.0 [6.0-11.3] vs. 6.0 (5.0-7.0); 3.0 [2.0-4.0] vs. 2.0 [2.0-2.0, and 25.6% vs. 11.0%; RR, 2.32; 95% CI, 1.19-4.54, respectively; P < 0.001 for all). CONCLUSIONS: Higher-level postoperative noise exposure was associated with more severe postoperative pain and increased analgesic needs, as well as a higher incidence of moderate-to-severe pain in patients recovering from cesarean delivery. Our findings indicate that reducing environmental ward noise might benefit for postoperative pain management.

Asunto(s)

RESUMEN

The use of natural language interfaces (NLIs) to create charts is becoming increasingly popular due to the intuitiveness of natural language interactions. One key challenge in this approach is to accurately capture user intents and transform them to proper chart specifications. This obstructs the wide use of NLI in chart generation, as users' natural language inputs are generally abstract (i.e., ambiguous or under-specified), without a clear specification of visual encodings. Recently, pre-trained large language models (LLMs) have exhibited superior performance in understanding and generating natural language, demonstrating great potential for downstream tasks. Inspired by this major trend, we propose ChartGPT, generating charts from abstract natural language inputs. However, LLMs are struggling to address complex logic problems. To enable the model to accurately specify the complex parameters and perform operations in chart generation, we decompose the generation process into a step-by-step reasoning pipeline, so that the model only needs to reason a single and specific sub-task during each run. Moreover, LLMs are pre-trained on general datasets, which might be biased for the task of chart generation. To provide adequate visualization knowledge, we create a dataset consisting of abstract utterances and charts and improve model performance through fine-tuning. We further design an interactive interface for ChartGPT that allows users to check and modify the intermediate outputs of each step. The effectiveness of the proposed system is evaluated through quantitative evaluations and a user study.

RESUMEN

We conduct two in-lab experiments (N=93) to evaluate the effectiveness of Gantt charts, extended Gantt charts, and stringline charts for visualizing fixed-order event sequence data. We first formulate five types of event sequences and define three types of sequence elements: point events, interval events, and the temporal gaps between them. Our two experiments focus on event sequences with a pre-defined, fixed order, and measure task error rates and completion time. The first experiment shows single sequences and assesses the three charts' performance in comparing event duration or gap. The second experiment shows multiple sequences and evaluates how well the charts reveal temporal patterns. The results suggest that when visualizing single fixed-order event sequences, 1) Gantt and extended Gantt charts lead to comparable error rates in the duration-comparing task; 2) Gantt charts exhibit either shorter or equal completion time than extended Gantt charts; 3) both Gantt and extended Gantt charts demonstrate shorter completion times than stringline charts; 4) however, stringline charts outperform the other two charts with fewer errors in the comparing task when event type counts are high. Additionally, when visualizing multiple point-based fixed-order event sequences, stringline charts require less time than Gantt charts for people to find temporal patterns. Based on these findings, we discuss design opportunities for visualizing fixed-order event sequences and discuss future avenues for optimizing these charts.

RESUMEN

As the final stage of questionnaire analysis, causal reasoning is the key to turning responses into valuable insights and actionable items for decision-makers. During the questionnaire analysis, classical statistical methods (e.g., Differences-in-Differences) have been widely exploited to evaluate causality between questions. However, due to the huge search space and complex causal structure in data, causal reasoning is still extremely challenging and time-consuming, and often conducted in a trial-and-error manner. On the other hand, existing visual methods of causal reasoning face the challenge of bringing scalability and expert knowledge together and can hardly be used in the questionnaire scenario. In this work, we present a systematic solution to help analysts effectively and efficiently explore questionnaire data and derive causality. Based on the association mining algorithm, we dig question combinations with potential inner causality and help analysts interactively explore the causal sub-graph of each question combination. Furthermore, leveraging the requirements collected from the experts, we built a visualization tool and conducted a comparative study with the state-of-the-art system to show the usability and efficiency of our system.

Asunto(s)

RESUMEN

In soccer, player action evaluation provides a fine-grained method to analyze player performance and plays an important role in improving winning chances in future matches. However, previous studies on action evaluation only provide a score for each action, and hardly support inspecting and comparing player actions integrated with complex match context information such as team tactics and player locations. In this work, we collaborate with soccer analysts and coaches to characterize the domain problems of evaluating player performance based on action scores. We design a tailored visualization of soccer player actions that places the action choice together with the tactic it belongs to as well as the player locations in the same view. Based on the design, we introduce a visual analytics system, Action-Evaluator, to facilitate a comprehensive player action evaluation through player navigation, action investigation, and action explanation. With the system, analysts can find players to be analyzed efficiently, learn how they performed under various match situations, and obtain valuable insights to improve their action choices. The usefulness and effectiveness of this work are demonstrated by two case studies on a real-world dataset and an expert interview.

Asunto(s)

RESUMEN

In geo-related fields such as urban informatics, atmospheric science, and geography, large-scale spatial time (ST) series (i.e., geo-referred time series) are collected for monitoring and understanding important spatiotemporal phenomena. ST series visualization is an effective means of understanding the data and reviewing spatiotemporal phenomena, which is a prerequisite for in-depth data analysis. However, visualizing these series is challenging due to their large scales, inherent dynamics, and spatiotemporal nature. In this study, we introduce the notion of patterns of evolution in ST series. Each evolution pattern is characterized by 1) a set of ST series that are close in space and 2) a time period when the trends of these ST series are correlated. We then leverage Storyline techniques by considering an analogy between evolution patterns and sessions, and finally design a novel visualization called GeoChron, which is capable of visualizing large-scale ST series in an evolution pattern-aware and narrative-preserving manner. GeoChron includes a mining framework to extract evolution patterns and two-level visualizations to enhance its visual scalability. We evaluate GeoChron with two case studies, an informal user study, an ablation study, parameter analysis, and running time analysis.

RESUMEN

STUDY OBJECTIVE: Most laparoscopic surgeries under general anesthesia are performed in noisy environments, although the effect of intraoperative noise reduction on postoperative pain remains uncertain. This study aimed to explore whether postoperative pain could be reduced through the intraoperative use of noise-cancelling headphones. DESIGN: This study was conducted as a prospective parallel-group randomized clinical trial. SETTING: Operating room and surgery room. PATIENTS: Ninety patients who underwent laparoscopic surgery under general anesthesia. INTERVENTIONS: In the intervention group, noise-cancelling headphones were used to reduce noise intensity during laparoscopic surgery under general anesthesia. MEASUREMENTS: The primary outcome was the maximum movement-evoked pain intensity within 24 h post-surgery, measured using a 10-point numeric rating scale. Secondary outcomes included the maximum resting pain score and total opioid consumption during the 24-h period post-surgery. Mean intraoperative noise and the proportion of intraoperative time with noise intensity ≥70 dB were recorded. MAIN RESULTS: The maximum movement-evoked pain score was significantly lower in the intervention group than in the control group (mean score [SD], 2.7 [1.0] and 4.0[1.0], respectively; P < 0.001). The intervention group required significantly fewer opioids than the control group (mean [SD], 44.2 [12.8] and 51.3[17.5] mg, respectively; P = 0.032). In the control group, but not the intervention group, all postoperative pain scores were significantly associated with the proportion of intraoperative time with noise intensity ≥70 dB, which was an independent risk factor for postoperative pain. CONCLUSION: During laparoscopic surgery under general anesthesia, intraoperative noise isolation using noise-cancelling headphones is a safe and effective strategy for relieving postoperative pain and decreasing total opioid analgesic consumption.

Asunto(s)

RESUMEN

Tables are a ubiquitous data format for insight communication. However, transforming data into consumable tabular views remains a challenging and time-consuming task. To lower the barrier of such a task, research efforts have been devoted to developing interactive approaches for data transformation, but many approaches still presume that their users have considerable knowledge of various data transformation concepts and functions. In this study, we leverage natural language (NL) as the primary interaction modality to improve the accessibility of average users to performing complex data transformation and facilitate intuitive table generation and editing. Designing an NL-driven data transformation approach introduces two challenges: a) NL-driven synthesis of interpretable pipelines and b) incremental refinement of synthesized tables. To address these challenges, we present NL2Rigel, an interactive tool that assists users in synthesizing and improving tables from semi-structured text with NL instructions. Based on a large language model and prompting techniques, NL2Rigel can interpret the given NL instructions into a table synthesis pipeline corresponding to Rigel specifications, a declarative language for tabular data transformation. An intuitive interface is designed to visualize the synthesis pipeline and the generated tables, helping users understand the transformation process and refine the results efficiently with targeted NL instructions. The comprehensiveness of NL2Rigel is demonstrated with an example gallery, and we further confirmed NL2Rigel's usability with a comparative user study by showing that the task completion time with NL2Rigel is significantly shorter than that with the original version of Rigel with comparable completion rates.

RESUMEN

Circular RNAs (circRNAs) play key roles in colorectal cancer (CRC) progression, but little is known about the biological functions of hsa_circRNA_001676 in CRC. Therefore, we explored the potential role of hsa_circRNA_001676 in CRC development. RT-qPCR was performed to determine hsa_circRNA_001676, miR-556-3p and Ras-GTPase-activating SH3 domain-binding-proteins 2 (G3BP2) levels in CRC tissues. Meanwhile, to evaluate the roles of hsa_circRNA_001676, miR-556-3p and G3BP2 on CRC, functional analysis of cell proliferation, migration and stemness were then performed. Our results showed that compared to normal tissues, hsa_circRNA_001676 and G3BP2 level was elevated, but miR-556-3p level was reduced in CRC tissues. Additionally, luciferase reporter results showed that hsa_circRNA_001676 was shown to target miR-556-3p, and G3BP2 was targeted by miR-556-3p. Hsa_circRNA_001676 or G3BP2 overexpression promoted CRC cell proliferation and migration. Conversely, miR-556-3p overexpression suppressed CRC cell proliferation and migration. Moreover, deficiency of hsa_circRNA_001676 or G3BP2 repressed the CRC cell proliferation, migration and stemness. Meanwhile, hsa_circRNA_001676 deficiency obviously reduced tumor growth and stemness in a CRC mouse xenograft model. Furthermore, hsa_circRNA_001676 deficiency notably reduced G3BP2 level, but elevated miR-556-3p level in tumor tissues from tumor-bearing mice. Mechanistically, hsa_circRNA_001676 targeted miR-556-3p to increase G3BP2 level, contributing to the progression of CRC. Collectively, hsa_circRNA_001676 was able to accelerate proliferation, migration and stemness in CRC through regulating miR-556-3p/G3BP2 axis, suggesting that hsa_circRNA_001676 may become a potential therapeutic target in treating CRC.

Asunto(s)