Task Analysis Research Articles

Semi-supervised lung adenocarcinoma histopathology image classification based on multi-teacher knowledge distillation.

In this study, we propose a semi-supervised learning scheme using a patch-based deep learning framework to tackle the challenge of high-precision classification of seven lung tumor growth patterns, despite having a small amount of labeled data in whole slide images (WSIs). This scheme aims to enhance generalization ability with limited data and reduce dependence on large amounts of labeled data. It effectively addresses the common challenge of high demand for labeled data in medical image analysis.

Approach. To address these challenges, the study employs a semi-supervised learning approach enhanced by a dynamic confidence threshold mechanism. This mechanism adjusts based on the quantity and quality of pseudo labels generated. This dynamic thresholding mechanism helps avoid the imbalance of pseudo-label categories and the low number of pseudo-labels that may result from a higher fixed threshold. Furthermore, the research introduces a multi-teacher knowledge distillation technique. This technique adaptively weights predictions from multiple teacher models to transfer reliable knowledge and safeguard student models from low-quality teacher predictions.

Main results. The framework underwent rigorous training and evaluation using a dataset of 150 WSIs, each representing one of the seven growth patterns. The experimental results demonstrate that the framework is highly accurate in classifying lung tumor growth patterns in histopathology images. Notably, the performance of the framework is comparable to that of fully supervised models and human pathologists. In addition, the framework's evaluation metrics on a publicly available dataset are higher than those of previous studies, indicating good generalizability.

Significance. This research demonstrates that a semi-supervised learning approach can achieve results comparable to fully supervised models and expert pathologists, thus opening new possibilities for efficient and cost-effective medical images analysis. The implementation of dynamic confidence thresholding and multi-teacher knowledge distillation techniques represents a significant advancement in applying deep learning to complex medical image analysis tasks. This advancement could lead to faster and more accurate diagnoses, ultimately improving patient outcomes and fostering the overall progress of healthcare technology.&#xD.

MBFusion: Multi-modal balanced fusion and multi-task learning for cancer diagnosis and prognosis

Pathological images and molecular omics are important information for predicting diagnosis and prognosis. The two kinds of heterogeneous modal data contain complementary information, and the effective fusion of the two modals can better reveal the complex mechanisms of cancer. However, due to the different representation learning methods, the expression strength of different modals in different tasks varies greatly, so that many multimodal fusions do not achieve the best results. In this paper, MBFusion is proposed, to achieve multiple tasks such as prediction of diagnosis and prognosis through multi-modal balanced fusion. The MBFusion framework uses two kinds of specially constructed graph convolutional network to extract the features of molecular omics data, and uses ResNet to extract the features of pathological image data and retain important deep features by using attention and clustering, which effectively improves both kinds of the features representation, making their expressive ability balanced and comparable. The features of these two modal data are then fused through cross-attention Transformer, and the fused features are used to learn both tasks of cancer subtype classification and survival analysis by using multi-task learning. In this paper, MBFusion and other state of the art methods are compared on two public cancer datasets, and MBFusion shows an improvement of up to 10.1% by three kinds of evaluation metrics. In the ablation experiment, MBFusion explores the contribution of each modal data and each framework module to the performance. Furthermore, the interpretability of MBFusion is explained in detail to show the value of application.

A prediction method of diabetes comorbidity based on non-negative latent features

In this paper, we present a novel network-based approach, namely Inherently Non-negative Latent Feature Analysis for Diabetes Mellitus Comorbidity Detection (INDM), to enhance the detection and analysis of comorbidities associated with diabetes mellitus. Different from existing methods, INDM is the first computational approach that integrates comorbidity networks of the chronic disease spectrum with patient clinical characteristics. To perform the analytical tasks, the proposed INDM adopts the following core components. First, comorbidity networks representing patients diagnosed solely with hypertension and those with hypertension and diabetes are constructed, following the case-control design that establishes a 1:1 matching in age and gender between two cohorts. Subsequently, the disease set is modeled in the comorbidity network according to the relative risk methodology. This enables nodes and edges in the comorbidity network to represent disease interactions that are derived from the patient-disease bipartite graph. Second, a nonlinear loss function with the capability of inherently non-negative latent feature analysis followed by a comorbidity classifier is adopted to uncover the patterns indicating the diabetes comorbidity in the comorbidity network. The proposed INDM has been rigorously tested on actual diabetes comorbidity datasets. The notable results demonstrate that INDM exhibits superior detection accuracy. Furthermore, the topological structure discovered by the proposed INDM can provide a profound insight into hypertension comorbidity in both the case and control groups.

Design and Assessment of Fighter Pilot Assistance Systems for Air-to-Air Refuelling with Probe-and-Drogue-Equipment

Air-to-air refuelling (AAR) with a probe-and-drogue system is a highly demanding process for fighter pilots. In the frame of the project “Future Air-to-Air Refuelling” (F(AI)2R) the German Aerospace Center (DLR) is designing concepts for assistance systems to support fighter pilots during this manoeuvre. The AAR process was examined using a hierarchical task analysis (HTA) based on a literature review and semi-structured interviews with Eurofighter-, Tornado- and test pilots. “Situation Awareness Requirements” (SAR), which represent relevant parameters for the situation awareness of the fighter pilot were derived from the HTA and rated by pilots according to their relevance. The collected data was then used to design different concepts of pilot assistance systems using a morphological box and a decision matrix. The concepts were visualised as storyboards, assessed by test pilots of the “Wehrtechnische Dienststelle 61” (WTD 61) and optimized based on their feedback. In this paper, the used methodology as well as the results of the HTA and SAR analysis are presented. Besides that, storyboards for pilot assistance systems displaying the overtake speed “German Patent No. 10.2022.110.505” and the “Contact Assistance, Status and Warning System” (CASWS) “German Patent No. 10.2022.123.653” are described. Additionally, the planned implementation using a HoloLens 2 is explained and the strategy for the subsequent simulator study on the DLR fighter aircraft simulator “Military AiR vehicle Simulator – Fast Integration Testbed” (MARS-FIT) is described.

Community influence analysis in social networks

Heterogeneous influence detection across network nodes is an important task in network analysis. A community influence model (CIM) is proposed to allow nodes to be classified into different communities (i.e., clusters or groups) such that the nodes within the same community share the common influence parameter. Employing the quasi-maximum likelihood approach, together with the fused lasso-type penalty, both the number of communities and the influence parameters can be estimated without imposing any specific distribution assumption on the error terms. The resulting estimators are shown to enjoy the oracle property; namely, they perform as well as if the true underlying network structure were known in advance. The proposed approach is also applicable for identifying influential nodes in a homogeneous setting. The performance of our method is illustrated via simulation studies and two empirical examples using stock data and coauthor citation data, respectively.

Multi-task metric learning for optical performance monitoring

In our experiments, applying few shot metric learning for optical performance monitoring (OPM), we set the dataset as 16-way-6-shot. Modulation format identification (MFI) was utilized as a classification task, and optical signal-to-noise ratio (OSNR) estimation was used as a regression task for joint analysis. Multi-task metric learning (MML) used the adaptive weights to balance the weights of the three metric functions, six modulation formats (QPSK, 8QAM, 16QAM, 32QAM, 64QAM, 128QAM) are classified correctly with 100 % accuracy after 200 epochs. Furthermore, the lowest mean square error (MSE) of OSNR is 0.431 dB. Then, Ablation experiments compute the corresponding similarity (SIM) for each metric function show that the MSE of MML, SIMLocal+Cosine, SIMCosine+Point, SIMLocal+Point, single-task metric learning (SML) and adaptive multi-task learning (AMTL) is 0.431 dB, 0.572 dB, 0.569 dB, 0.567 dB, 0.637 dB, 1.319 dB, respectively. The proposed model achieves the highest accuracy in MFI and the lowest MSE in OSNR estimation. Finally, when comparing the various metric functions while altering the transmission distance of the optical fiber, it was observed that MML stayed within an acceptable range between 200 km and 800 km. This shows that our algorithm requires only a small number of training samples to create a reasonably good model, offering a new approach to solving problems that arise in optical performance monitoring.

Multi-task heterogeneous graph learning on electronic health records

Learning electronic health records (EHRs) has received emerging attention because of its capability to facilitate accurate medical diagnosis. Since the EHRs contain enriched information specifying complex interactions between entities, modeling EHRs with graphs is shown to be effective in practice. The EHRs, however, present a great degree of heterogeneity, sparsity, and complexity, which hamper the performance of most of the models applied to them. Moreover, existing approaches modeling EHRs often focus on learning the representations for a single task, overlooking the multi-task nature of EHR analysis problems and resulting in limited generalizability across different tasks. In view of these limitations, we propose a novel framework for EHR modeling, namely MulT-EHR (Multi-Task EHR), which leverages a heterogeneous graph to mine the complex relations and model the heterogeneity in the EHRs. To mitigate the large degree of noise, we introduce a denoising module based on the causal inference framework to adjust for severe confounding effects and reduce noise in the EHR data. Additionally, since our model adopts a single graph neural network for simultaneous multi-task prediction, we design a multi-task learning module to leverage the inter-task knowledge to regularize the training process. Extensive empirical studies on MIMIC-III and MIMIC-IV datasets validate that the proposed method consistently outperforms the state-of-the-art designs in four popular EHR analysis tasks — drug recommendation, and predictions of the length of stay, mortality, and readmission. Thorough ablation studies demonstrate the robustness of our method upon variations to key components and hyperparameters.

Investigating Professional Analyst Strategies in Immersive Space to Think.

Existing research on sensemaking in immersive analytics systems primarily focuses on understanding how users complete analysis within these systems with quantitative and qualitative datasets. However, these user studies mainly concentrate on understanding analysis styles and methodologies from a predominantly novice user study population. While this approach provides excellent initial insights into what users may do within IA systems, it fails to address how professionals may utilize an immersive analytic system for analysis tasks. In our work, we build upon an existing immersive analytics concept - "Immersive Space to Think" to understand how professional user populations differ from novice users in immersive analytic system usage. We conducted a user study with 11 professional intelligence analysts who completed three analysis sessions each. Using our results from this study, we provide deep analysis into how professional users complete sensemaking within immersive analytic systems, compare our findings to previously published findings with a novice user population, and provide insights into how to develop better IA systems to support the professional analyst's strategies within these systems.

Distance-reconstructed dependency enhanced aspect-based sentiment analysis with sentiment strength

Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment analysis task that requires the detection of sentiment polarity towards specific aspects. Dependency tree-based graph convolutional network models (GCN) have been widely applied in ABSA. These studies utilize syntactic analysis tools to derive syntactic dependency graphs, which are then inputted into GCN. It enables iterative learning of sentiment dependency information from contextual words to aspect terms. However, directly using syntactic dependency graphs can lead to two shortcomings. First, the long-distance sentiment information in long sentences will be weakened during GCN iterative computations. Second, the syntactic dependency graphs of short sentences lack sentiment strength information. To address these two shortcomings, we propose a Distance-Reconstructed Dependency Enhanced Sentiment analysis approach with Sentiment Strength based on GCN (DRD-SE-GCN) approach, in which the syntactic dependency graph of long sentences is reconstructed based on distance, thus narrowing the gap between sentiment words and target aspect words. It ensures that the sentiment dependency information carried by the long-distance sentiment words will not be weakened or lost during the GCN iteration. Additionally, the weights of the syntactic dependency graph for short sentences are reassigned so as to carry the strength information of sentiment words. Experimental results on four standard datasets show that our proposed model can effectively improve the accuracy of aspect-level sentiment analysis.

A task-dependent analysis of closed vs. open and fine vs. gross motor skills in handedness

ABSTRACT The traditional classifications of motor skills nature (open vs closed; fine vs gross) have not been considered in handedness investigations. Instead, previous research focused on comparing complex vs less complex motor behaviour, leaving a gap in the literature. We compared manual preference between different motor skill characteristics, namely: fine and closed (FC), gross and closed (GC) and gross and open (GO) tasks. The hand preference was assessed with the Global Lateral Preference Inventory in four hundred and forty participants (244 women) aged from 18 to 59 years old. By assessing the degree and direction of handedness in different motor skills, our results showed a stronger lateralization pattern for FC motor skills as compared to GC and GO, with GO also being less lateralized than GC. Our results expand those of previous investigations that used the motor skill complexity definitions by showing how handedness can also be modulated by the interaction between classic motor skills classifications. Future research should consider fine vs. gross and open vs. closed classifications when selecting tasks for analysis of asymmetries of preference.

Cognitive Task Analysis: Eliciting Expert Cognition in Context

Cognitive Task Analysis (CTA) is a powerful methodological approach that can enhance the rigorous elicitation and documentation of complex cognitive processes within interview-based qualitative research. We provide insights into this set of semi-structured interviewing techniques that we contend have much to offer management researchers who wish to understand the complexities of expert cognition within specific work-related tasks. Distinct from traditional semi-structured interview methods, CTA is designed to identify the knowledge requirements underpinning expertise in complex work domains. First, we present CTA as a robust approach to eliciting complex cognition and note why, when, and where management scholars might best use its techniques. Second, we provide two examples of how CTA methods have been used to research management; specifically, using the Critical Decision Method to explore management in high-stakes environments, and Applied Cognitive Task Analysis to explore global leadership. In ending, we propose greater use of this pragmatic approach in management research and highlight potential avenues for future research that will advance understanding of complex cognition at work.

Leveraging Quadratic Polynomials in Python for Advanced Data Analysis.

This research explores the application of quadratic polynomials in Python for advanced data analysis. The study demonstrates how quadratic models can effectively capture nonlinear relationships in complex datasets by leveraging Python libraries such as NumPy, Matplotlib, scikit-learn, and Pandas. The methodology involves fitting quadratic polynomials to the data using least-squares regression and evaluating the model fit using the coefficient of determination (R-squared). The results highlight the strong performance of the quadratic polynomial fit, as evidenced by high R-squared values, indicating the model's ability to explain a substantial proportion of the data variability. Comparisons with linear and cubic models further underscore the quadratic model's balance between simplicity and precision for many practical applications. The study also acknowledges the limitations of quadratic polynomials and proposes future research directions to enhance their accuracy and efficiency for diverse data analysis tasks. This research bridges the gap between theoretical concepts and practical implementation, providing an accessible Python-based tool for leveraging quadratic polynomials in data analysis.

Analysis of okadaic acid using electrochemiluminescence imaging on microfluidic biosensing chip

The sensitivity and specificity of electrochemiluminescence (ECL)-based biosensor directly rely on the property of luminophor, the type of sensing carriers and the effectiveness of signal amplification used in the sensor design, which poses a major challenge to manage these elements simultaneously. In this work, an aggregation-induced electrochemiluminescence (AIECL) microfluidic sensing chip using 4′,4″,4‴,4‴'-(ethene-1,1,2,2-tetrayl)tetrabiphenyl-4-carboxylic acid (TPE)-derived hafnium-based metal-organic framework (Hf-MOF) as emitter was developed. An easily overlooked marine pollutant, okadaic acid (OA) with different concentrations ranging from 5.00 ng/mL to 1.50 × 104 ng/mL at the electrode is visualized imaging benefit from high luminescence efficiency of Hf-MOF coupled the rolling circle amplification strategy assisted by trans-cleavage activity of CRISPR/Cas12a. These highlights will solve the long-lasting task in the accurate analysis of small molecule pollutants, which can be able to provide more worthy reference solution about construction of novel ECL luminophor and signal extraction of low-abundance disease-related biomarkers.

Domestic and Existential in Stories of Vasily Shukshin and Boris Yekimov

The shared worldview of the so-called “village” writers often obscures the questions regarding their differing evaluations of social reality, interpretations of historical changes, and understandings of humanity’s place in the world. In this context, the task of comparative analysis of their similar artistic solutions appears both relevant and novel. This article examines the case of different scales of a seemingly analogous plot situation. The stories analyzed are Vasily Shukshin’s “The Boots” and Boris Yekimov’s “A Pair of Autumn Shoes”. It is demonstrated that the protagonists of Shukshin and Yekimov manifest themselves within narratives of varying existential intensity, addressing distinct challenges. Despite the apparent similarity in plots, their narrative differences are evident. Shukshin’s characters understand how life should be, yet often deviate from their ideals, fearing kindness; thus, in the writer’s world, the existential is frequently devalued. Vasily Shukshin, who captures the disintegration of the existential within the hero’s inner world, illustrates in “The Boots” that overcoming the mundane is an act of heroism and a personal triumph. Conversely, Boris Yekimov places fundamentally different emphases: within a superficially similar situation, he addresses a transpersonal challenge. The essence of the plot realized in “A Pair of Autumn Shoes” serves to remind readers of spiritual and communal values that may be lost amid everyday concerns.

Sedimentological, Geochemical, and Environmental Assessment in an Eastern Mediterranean, Stressed Coastal Setting: The Gialova Lagoon, SW Peloponnese, Greece

This study describes the prevalent sedimentological and geochemical patterns and investigates the environmental status of the bottom of Gialova lagoon, a highly vulnerable coastal site of the EU’s Natura 2000 network. For this task, lithological, geochemical, and microfaunal analyses of sediment samples were combined with a high-resolution bathymetric survey. Potential pollution was determined using geochemical-based (EF, I-geo, and PLI) and faunal (Foram-AMBI) indices. We find that sedimentation is mainly controlled by the bottom morphology, hydrodynamic variations, and biogenic productivity of the lagoon. The application of the multivariate factor analysis technique revealed four dominant factors explaining the geochemical processes occurring in the lagoon. The first factor, namely “terrigenous aluminosilicates associated with Corg vs. autochthonous biogenic carbonates”, discriminates the deposition of detrital sediments, related to the high adsorption of heavy metals—versus bioclastic sediments. The “sulfides” factor represents an anoxic phase of the lagoon floor, whereas the “Mn-oxyhydroxides” factor indicates increased manganese content with several compounded trace elements. The “phosphate” factor reveals multiple sources of phosphorus in the lagoon. The lagoon bottom shows negligible to minor contamination in heavy metals, except Mo and Pb, which induce moderate pollution levels. The maximum contamination and environmental stress concern two small-sized, shallow basins within the lagoon.

Training morphosyntactic skills in Dutch preschoolers with (presumed) Developmental Language Disorder: A novel group-based intervention.

Morphosyntactic problems are a core symptom of Developmental Language Disorder (DLD). In the Netherlands, children with (presumed) DLD can receive special care in language-focused treatment groups. The focus of these groups mainly lies in improving communicative intentions, vocabulary and phonology. Morphosyntactic skills receive less attention. The authors developed a scripted group-based intervention targeting morphosyntactic skills in young children with DLD. In this study, the effect of the intervention on the morphosyntactic skills of preschoolers with (presumed) DLD was tested and the usability for pedagogical practitioners (PPs) was evaluated. Twenty-seven preschoolers with DLD (aged 2;10-3;10 [years;months]) participated in an A-B group study in which the development of grammatical structures was monitored with a morphosyntactic task and language sample analyses (LSA). Progression during 8 weeks usual care (UC) and 8 weeks morphosyntactic intervention was examined using Bayesian mixed effects models. In LSA, structures that were targeted were compared to control structures. The intervention consisted of a weekly script-based group session in which morphosyntactic structures were targeted, and daily activities in which these target structures were repeated. The intervention was provided by trained PPs, who were coached by a speech-language therapist. An early indication of usability and feasibility was evaluated using an online questionnaire. The analyses show that morphosyntactic skills improved during the intervention period, with strong evidence for growth in the production of target structures on the morphosyntactic task and target and control structures in LSA, while barely any evidence was found for growth in the use of these structures in UC. However, target structures and control structures seem to develop at the same rate. General measures of morphosyntactic ability showed improvement both during UC and the intervention phase. Evaluation among practitioners suggested that the intervention is regarded as usable and feasible. Growth in morphosyntactic skills of children in the intervention period was demonstrated, but this could not be proven to be related to the intervention because both target and control structures improved during the intervention. This growth might be due to maturation instead of the intervention. Nevertheless, our study demonstrates that the morphosyntactic skills of preschoolers with DLD can show considerable improvement over a period of 8 weeks. Furthermore, our study underlines the importance of using LSA measures when monitoring the morphosyntactic development of children, as they might be more sensitive to change than standardised tests. What is already known on the subject Most children with Developmental Language Disorder (DLD) experience difficulties in their morphosyntactic development. In the Netherlands, preschoolers with DLD can receive special care in language-focused treatment groups. These groups mainly focus on stimulating communicative intentions, vocabulary and phonology, but less so on stimulating morphosyntactic skills. What this study adds We designed a new group-based intervention targeting the expressive morphosyntactic skills of children with DLD, examined the effect and investigated the usability and feasibility. Although there is strong evidence for growth in morphological skills, intervention effects could not be demonstrated. Evaluations among practitioners suggested that the intervention is regarded as usable and feasible. Furthermore, this study shows that children's morphosyntactic skills can improve over relatively short periods of time and language sample analyses seem to be sensitive to detect these changes. What are the clinical implications of this work? Currently, very few group-based morphosyntactic interventions exist (in the Netherlands). Since practitioners were generally positive about the intervention and its usability and feasibility, the proposed intervention might benefit the treatment of morphosyntactic problems in children with DLD.

Of two minds: an experiment on how time scarcity shapes risk-taking behaviour

ABSTRACT Several studies report that the brain evaluates prospects and executes decisions as the outcome of two types of mental processes: one described as slow and reflective and the other as fast and intuitive. We investigate how these two mental processes affect risk-taking behaviour in a one-shot decision by using time pressure to establish an intuitive response. We observe that time constraints do not change risk attitudes. Furthermore, it is only when subjects are given ample time to decide and instructed to reflect that they show the well-documented shift of risk preferences across the domain of losses and gains. Our results suggest that framing effects are the result of cognitive processes that become operative when individuals are granted sufficient time to undertake a more comprehensive analysis of decision tasks.

M2PSC: Multilingual sentiment analysis using improved multi-attention based Deep Learning model

Sentiment analysis, which involves determining the emotional polarity positivity, negativity, or neutrality in the source texts, is a crucial task. Multilingual sentiment analysis techniques were developed to analyze data in several languages; a notable deficiency of resources in multilingual sentiment analysis is one of the primary issues. Furthermore, the developed methods for multilingual sentiment analysis have some limitations such as data dependency, reliability, robustness, and computational complexity. To tackle these shortcomings, this research proposed a multilingual improved multi-attention Deep Learning model (M2PSC-DL), which leverages the advantages of the Bi-directional Long Short Term Memory (BiLSTM) classifier with improved attention mechanisms. The Multi-metric graph embedding technique encodes the data to provide more contextual information representation. Additionally, the combination of improved Positional Spatial Channel (SPC) attention increases the capability of the model to extract relevant features in the training process which leads to getting accurate results in sentiment analysis tasks. Furthermore, the research proposed an improved sigmoid activation for solving the vanishing gradient issues that help the model avoid gradient saturations. The validation results demonstrate that the M2PSC-DL model attains 96.26% accuracy, 96.06% precision, and 96.18% recall for the XED dataset which is far better than the traditional methods.

CSIP: Contrastive learning with Graph Neural Network enables chemical structure to image mapping

The development of advanced AI has been transforming the biomedical field. The emergence of multi-modal biomedical data such as imaging, sequencing, and other omics data further enabled the training of AI models for complex analytical tasks. However, such data analysis remains challenging due to the difficulty of integrating information from different modalities. In this paper, we aim to address this challenge by proposing a methodology to integrate image and molecular structure data. We present the Contrastive Structure-to-Image Pretraining (CSIP) framework, which leverages a self-supervised Graph Neural Network (GNN) to encode molecules and images into a joint feature embedding space. This direct mapping between the two modalities enables a wide variety of applications, including image profiling and clustering of molecules based on their effects on cell morphology. Image profiles generated by CSIP archived an average AUC of 0.708 on various biological activity prediction tasks, rivalling the state-of-the-arts and outperforming some fully supervised methodologies. Further, CSIP improved the accuracy of image-molecule matching by 29-folds from the random baseline after being trained on a small dataset, which demonstrated data efficiency. The code to reproduce our results can be found at https://github.com/LeoL18/CSIP.

Tiramisù: making sense of multi-faceted process information through time and space

AbstractKnowledge-intensive processes represent a particularly challenging scenario for process mining. The flexibility that such processes allow constitutes a hurdle as they are hard to capture in a single model. To tackle this problem, multiple visual representations of the same processes could be beneficial, each addressing different information dimensions according to the specific needs and background knowledge of the concrete process workers and stakeholders. In this paper, we propose, describe, and evaluate a framework, named , that leverages visual analytics for the interactive visualization of multi-faceted process information, aimed at supporting the investigation and insight generation of users in their process analysis tasks. is based on a multi-layer visualization methodology that includes a visual backdrop that provides context and an arbitrary number of superimposed and on-demand dimension layers. This arrangement allows our framework to display process information from different perspectives and to project this information onto a domain-friendly representation of the context in which the process unfolds. We provide an in-depth description of the approach’s founding principles, deeply rooted in visualization research, that justify our design choices for the whole framework. We demonstrate the feasibility of the framework through its application in two use-case scenarios in the context of healthcare and personal information management. Plus, we conducted qualitative evaluations with potential end users of both scenarios, gathering precious insights about the efficacy and applicability of our framework to various application domains.