Social Network Interactions Research Articles

Social network enhanced behavioral interventions for diabetes and obesity: A 3 arm randomized trial with 2 years follow-up in Jordan.

While obesity and diabetes are rising pandemics, few low-cost and effective prevention and management strategies exist, especially in the Middle East. Nearly 20% of adults in Jordan suffer from diabetes, and over 75% are overweight or obese. Social network-based programs have shown promise as a viable public health intervention strategy to address these growing crises. We evaluated the effectiveness of the Microclinic Program (MCP) via a 6-month multi-community randomized trial in Jordan, with follow-up at 2 years. The MCP leverages existing social relationships to propagate positive health behaviors and information. We recruited participants from 3 community health centers in Amman, Jordan. Participants were eligible for the study if they had diabetes, pre-diabetes, or possessed ≥1 metabolic risk factor along with a family history of diabetes. We randomized participants into three trial arms: (A Group) received the Full MCP with curriculum-activated social network interactions; (B Group) received Basic MCP educational sessions with organic social network interactions; or (C Group-Control) received standard care coupled with active monitoring and parallel screenings. Groups of individuals were randomized as units in a 3:1:1 ratio, with resulting group sizes of n = 540, 186, and 188 in arms A, B, and C, respectively. We assessed the overall changes in body weight, fasting glucose, hemoglobin A1c (HbA1c) and mean arterial blood pressure between study arms in multiple evaluations across 2 years (including at 6-months and 2-years follow-up). We investigated the effectiveness of Full and Basic MCP social network interventions using multilevel models for longitudinal data with hierarchical nesting of individuals within MCP classrooms, within community centers, and within temporal cohorts. We observed significant overall 2-year differences between all 3 groups for changes in body weight (P = 0.0003), fasting blood glucose (P = 0.0015), and HbA1c (P = 0.0004), but not in mean arterial blood pressure (P = 0.45). However, significant changes in mean arterial pressure were observed for Full MCP versus controls (P = 0.002). Weight loss in the Full MCP exceeded (-0.97 kg (P<0.001)) the Basic MCP during the intervention. Furthermore, both Full and Basic MCP yielded greater weight loss compared to the control group at 2 years. The Full MCP also sustained a superior fasting glucose change over 2 years (overall P<0.0001) versus the control group. For HbA1c, the Full MCP similarly led to greater 6-month reduction in HbA1c versus the control group (P<0.001), with attenuation at 2 years. For mean arterial blood pressure, the Full MCP yielded a greater drop in blood pressure versus control at 6 months; with attenuation at 2 years. These results suggest that activated social networks of classroom interactions can be harnessed to improve health behaviors related to obesity and diabetes. Future studies should investigate how public health policies and initiatives can further leverage social network programs for greater community propagation. Trial registration. ClinicalTrials.gov Identifier: NCT01818674.

Interviews With Lay Caregivers About Their Experiences Supporting Patients Throughout Kidney Transplantation.

Introduction: Lay caregivers provide essential support to patients throughout the kidney transplant process, pretransplant through discharge. Sparse data exists about kidney transplant caregiver experience and facilitators of caregiver engagement. The aim of this study was to explore and describe lay caregivers' accounts of supporting a patient before and early after kidney transplantation. Methods: Caregivers of recent kidney transplant recipients were individually interviewed about their experiences, coping strategies, and perspectives of center-specific support approaches for patients and caregivers in a single transplant center. Results: Inductive content analysis of transcribed interviews with 23 caregivers revealed 6 domain areas: visit preparation, initial evaluation, caregiver role discussion, exposure to support resources, transplant preparedness, and coping styles. Caregivers used and appreciated information offered by the transplant center, including materials directed to the patient. They recommended repeating information, online access, and adding video to complement print resources. They valued and requested information directed to them, both within passive materials and communication with providers. Social network interactions were helpful for practical, emotional, and informational support. Support group reminders and connection pathways to peers were suggested for both patients and caregivers. Conclusion: Findings highlight steps that can be taken by transplant centers and may stimulate caregiver engagement. Featuring caregiver-focused information and communication more prominently may support caregivers to improve patient progress in navigating kidney transplantation.

Co-Activity Maximization in Online Social Networks

Social media with online social networks has risen to be a prevalent force in information diffusion and public discourse. Despite its popularity and convenience, social media has been criticized for contributing to societal and ideological polarization as the result of trapping users in an echo chamber and filter bubbles. An emerging line of research focuses on ways to redesign content or link recommendation algorithms to mitigate the polarization phenomenon. However, existing works mainly concentrate on node-level balancing, while omitting the balancing effect that can be incurred by edge interaction in social networks. In this article, we take the first step to study the problem (CoAM) that assuming two campaigns are present in a network, how we should select seeds for each so as to maximize the interaction/activity between the followers of two campaigns (co-activity) after the diffusion process is finished. We begin our analysis by showing the hardness of CoAM under two diffusion models that are generalized from wildly used diffusion models and its objective function is neither submodular nor supermodular. This encourages us to design a submodular function that acts as a lower bound to the objective, by exploiting which we are able to devise a greedy algorithm with a provable approximation guarantee. To overcome the #P-hardness of diffusion calculation, we further extend the notion of random reverse-reachable (RR) set to devise a scalable instantiation of our approximation algorithm. We experimentally demonstrate the quality of our approximation algorithm on datasets collected from real-world social networks.

Event marketing as an effective tool for the advertising campaign of the social network "VKontakte"

The subject of this article is event marketing as a tool for the advertising campaign of the social network "VKontakte." It provides an analytical perspective on current trends in advertising and offers specific recommendations for the effective use of marketing tools in the evolving advertising environment. The main focus is on the importance of the social network's interaction with its audience through the organization and sponsorship of various events, as well as the optimization of feedback analysis and the effectiveness of advertising campaigns in the context of digital technologies and social media. The article proposes a theoretical and practical justification for the feasibility of conducting not only online events and activities (forums, discussions, educational courses) but also offline events (concerts in clubs and open venues), as well as organizing events in collaboration with cultural and educational centers in the country. An example of the advertising campaign of the social network "VKontakte" serves as illustrative material to confirm the effectiveness of the proposed approaches. The scientific relevance and novelty of this article are manifested in several key aspects. Firstly, the work considers event marketing as an innovative tool aimed at creating "viral messages" and improving the interaction of the promoted social network with its audience, opening new perspectives in brand promotion and consumer interaction. The second aspect is related to the reverse effect in this case - the influence of social networks on the effectiveness of event marketing. Given the complexity of the nature of social networks, as they simultaneously act as service providers to their users and media channels, the combination of these two functions in the activities of such market participants allows them to leverage many advantages associated with the complexity of their nature, which increases the importance of analyzing the theoretical foundations and possibilities of advertising campaigns.

A neural probabilistic bounded confidence model for opinion dynamics on social networks

Opinion dynamics (OD) models simulate the evolution of personal opinions using computer science, social dynamics, physics, and complexity science tools on social networks. However, current opinion dynamics models mainly utilize agent-based models to simulate user interactions but still need to leverage large-scale data fully. Social networks typically involve a vast number of users and information, making it difficult for models to capture the complex interactions in real social networks. Additionally, many models overlook the specific mechanisms of user interactions, such as how network individuals influence and interact with one another, resulting in inaccuracies in modeling individual opinion evolution. This paper proposes a novel approach that integrates the probabilistic bounded confidence model (PBC) with deep learning, i.e., Neural Probabilistic Bounded Confidence (NPBC), to tackle these challenges. The NPBC model adopts an attention network, a long short-term memory (LSTM) network, and a feedforward neural network to approximate the evolution of individual opinions within networks. It satisfies the data approximation and the users’ opinion update rule that conforms to the PBC model. This model enhances the understanding of opinion dynamics, helping to develop effective strategies for opinion guidance in social networks. Finally, the proposed NPBC model is evaluated on three synthetic and Twitter datasets. The results demonstrate that the proposed NPBC model performs better than the six baseline methods in predicting user opinions. Compared to baseline models, the model’s accuracy (ACC) and comprehensive evaluation (F1) scores improve by up to 18% and 7%, respectively.

Sentiment Analysis Based on Heterogeneous Multi-Relation Signed Network

Existing sentiment prediction methods often only classify users’ emotions into a few categories and cannot predict the variation of emotions under different topics. Meanwhile, network embedding methods that consider structural information often assume that links represent positive relationships, ignoring the possibility of negative relationships. To address these challenges, we present an innovative approach in sentiment analysis, focusing on the construction of a denser heterogeneous signed information network from sparse heterogeneous data. We explore the extraction of latent relationships between similar node types, integrating emotional reversal and meta-path similarity for relationship prediction. Our approach uniquely handles user-entity and topic-entity relationships, offering a tailored methodology for diverse entity types within heterogeneous networks. We contribute to a deeper understanding of emotional expressions and interactions in social networks, enhancing sentiment analysis techniques. Experimental results on four publicly available datasets demonstrate the superiority of our proposed model over state-of-the-art approaches.

Blockchain culture and digital image precariousness. Questioning NFTs as an art preservation strategy

In the last decades, the digital image has moved between the thin line that separates its exponential multiplication and its continuous danger of invisibility and loss. Despite the fact of being constantly used on the internet or social network interactions, the difficulties in filtering, gathering, authenticating and preserving new media images have led them to be a type of art barely collected by contemporary art museums. Even more, the huge amount of material produced not only by artists or creatives but also by citizens makes it impossible for cultural institutions to tackle the task of preserving a significant percentage of it. Museums seem to be unable to distinguish what might be considered art or heritage among the massive amount of images that fed popular culture. Nevertheless, the irruption of blockchain culture has focused on the importance of digital images as an identity, social and economic asset. NFTs seem to attempt to remedy the weaknesses of the digital image by associating it with a verifiable and supposedly incorruptible contract. This study tries to analyse the precariousness of the digital image as a key element in the emergence and sudden rise and fall of the so-called “crypto-art”. To this end, the idea of the “poor image” outlined by Steyerl is followed. The aim is to clarify whether the digital images associated with blockchain transactions solve the problematic obsolescent and unstable condition of the works, or if, on the contrary, these are used as fuel for a new ultra-liberal financial machine being quickly consumed and discarded.

Analyzing user migration in blockchain online social networks through network structure and discussion topics of communities on multilayer networks

User migration, i.e. the movement of large sets of users from one online social platform to another one, is one of the main phenomena occurring in modern online social networks and even involves the most recent alternative paradigms of online social networks, such as blockchain online social networks (BOSNs). In these platforms, user migration mainly occurs through hard forks of the supporting blockchain, i.e. a split of the original blockchain and the creation of an alternative blockchain, to which users may decide to migrate. However, our understanding of user migration and its mechanisms is still limited, particularly regarding the role of densely connected user groups (communities) during migration and fork events. Are there differences between users who stay and those who decide to leave, in terms of network structure and discussion topics? In this work, we show, through network-based analysis centered on the identification of communities on multilayer networks and text mining that a) the “position” of a group within the network of social and economic interactions is connected to the likelihood of a group to migrate, i.e. marginal groups are more likely to leave; b) group network structure is also important, as users in densely connected groups interacting through monetary transactions are more likely to stay; c) users who leave are characterized by different discussion topics; and d) user groups interacting through monetary transactions show interest in migration-related content if they are going to leave. These findings highlight the importance of social and economic relationships between users during a user migration caused by fork events In general, in the larger context of online social media, it motivates the need to investigate user migration through a network-inspired approach based on groups and specific subgraphs while leveraging user-generated content, at the same time.

Conceptualizing Treatment Burden among People with Type 2 Diabetes

Background. Treatment burden is an illness‐management workload level that exceeds an individual’s capacity to do that work. It is a complex concept that has not been comprehensively defined for people with type 2 diabetes (T2DM). Purpose. Provide a contemporary, holistic understanding of treatment burden among people with T2DM and understand its clinical implications. Methods. Walker and Avant’s 8‐step method for concept analysis was used. PubMed, CINAHL, Web of Science, Embase, and PsychInfo databases were searched from 2012 to 2023 to identify uses of the concept, defining attributes, antecedents, and consequences of treatment burden. Empirical referents were identified and modeled; contrary and related cases are presented. Findings. Thirty‐three articles were identified to extract the concept of treatment burden. Defining attributes were responsibility for self‐care, complexity of interactions with the healthcare system, perpetual emotional management, medical expenses, and social network interactions. Antecedents of treatment burden among people with T2DM were workload designated to the patient, resource scarcity, and understanding of the disease state. Consequences include impaired ability to conduct treatment regimen, impacted quality of life, realization of the necessity to work, and fatigue or exhaustion. Empirical referents cover various clinical tools, but none comprehensively capture all defining attributes. Discussion. Treatment burden is not dependent solely on the objective complexity of self‐care tasks. Instead, it is inextricably linked with one’s ecosystem, especially social interactions, interactions with the healthcare system, and available resources. Nurses and other healthcare professionals can use these findings to explore their patients’ burden experiences and select appropriate treatment.

Interactions in virtual social networks: a systematic literature review

Las redes sociales virtuales se han establecido como nuevos espacios de interacción social durante las últimas dos décadas. La interacción en contextos virtuales como Facebook e Instagram incide en diferentes dimensiones de la vida de la población adolescente. Este estudio tiene como objetivo determinar el estado de la investigación acerca del proceso de interacción social entre adolescentes en las redes sociales virtuales mediante la revisión sistemática de la literatura. Se llevó a cabo la búsqueda bibliográfica por medio del protocolo PRISMA y fueron seleccionados cuarenta estudios empíricos en las bases de datos Scopus, Web of Science, SciELO y Dialnet, los cuales fueron publicados en el periodo 2011-2022. Se establecieron cinco categorías emergentes de las investigaciones analizadas: identidad, bienestar social, competencias socioemocionales, conductas de riesgo y comunicación. Como resultado se evidencia que la población adolescente interactúa en las redes sociales virtuales con el propósito de obtener reconocimiento social, consolidar lazos de amistad y desarrollar el sentido de pertenencia a un grupo; sin embargo, es posible que se vean expuestos a riesgos como el ciberacoso. Se concluye que es necesario ampliar la investigación acerca de las interacciones online entre adolescentes; así como la necesidad de fortalecer las competencias socioemocionales de los adolescentes en el contexto familiar y escolar para que puedan hacer un uso responsable de las redes sociales virtuales.

Community Engagement in Smart Cities: A Social Network Analysis and Community Engagement Test

This study, carried out in the ever-changing context of Smart Cities, reveals the complex interactions of digital social networks, digital community involvement, and the Community involvement Test (CET) framework. The examination of data obtained from certain Smart Cities indicates a thriving milieu of community engagement, characterized by a markedly elevated rate of active participation. The identification of urgent issues, particularly those related to environmental sustainability, safety, traffic management, and educational quality, is consistent with the larger urban difficulties that these creative urban centers are facing. Additionally, the CET framework's integration of SNA data and survey results produces very high ratings, indicating the engagement programs' outstanding performance in promoting resident satisfaction and active involvement. These results highlight how digital technologies can help Smart Cities foster vibrant, engaged communities. They also highlight the continued need for smart urban policies to address urgent issues and maintain residents' quality of life while adhering to the Smart City paradigm.

Global feedback mechanism by explicit and implicit power for group consensus in social network

This paper investigates a global feedback consensus model which determines the importance of decision makers by combining explicit and implicit Power. Explicit power is obtained according to the differences in organizational hierarchy, while implicit power manifests itself by being recognized in social network interaction. Combining these two types of power, an approach is proposed to characterize the binary power of decision makers jointly to identify the key decision units. Then, a global feedback mechanism based on the binary power is investigated. Its innovation is that it searches the adjustors who are most conducive to achieve group consensus in global and implement personalized feedback services to achieve the minimum cost optimization goal. Finally, an illustrative example to verify the validity of the proposed method are reported.

An Online Support Vector Machine Algorithm for Dynamic Social Network Monitoring

Online monitoring of social networks offers exciting features for platforms, enabling both technical and behavioral analysis. Numerous studies have explored the adaptation of traditional quality control methods for detecting change points within social networks. However, the current research studies face limitations such as an overreliance on case-based attributes, high computational costs, poor scalability with large networks, and low sensitivity in fast change point detection. This paper proposes a novel algorithm for social network monitoring using One-Class Support Vector Machines (OC-SVMs) to address these limitations. Additionally, using both nodal and network-level attributes makes it versatile for diverse social network applications and effectively detecting network disturbances. The algorithm utilizes a well-defined training data dictionary with an updating procedure for evolutionary networks, enhancing memory and time efficiency by reducing the processing of input data. Extensive numerical experiments are conducted using an EpiCNet model to simulate interactions in an online social network, covering six change scenarios to evaluate the proposed methodology. The results show lower Average Run Length (ARL) and Expected Delay Detection (EDD), demonstrating the superior accuracy and effectiveness of the OC-SVM algorithm compared to alternative methods. Applying OC-SVM to the Enron Email network indicates its capability to identify change points, reflecting the tumultuous timeline that led to Enron's downfall. This further validates the substantial advancement of OC-SVM in social network monitoring and opens doors to broader real-world applications.

Feasibility and user-experience of a virtual environment for social connection and education after stroke: A pilot study

ObjectivesTo evaluate the feasibility and usability of stroke survivor participation in an 8-week virtual environment intervention that provides opportunities for social support exchanges, social network interactions, and recovery education. Materials and methodsA single-group, pre- and post-test measure design was used. Descriptive statistics were used to examine enrollment and retention rates, proportion of questionnaires completed, and virtual environment process data (e.g., number of log-ins) and usability scores. Changes in pre- and post-intervention questionnaire (e.g., usability, social support, depression, anxiety, loneliness, and self-efficacy) scores were explored using Wilcoxon signed-rank tests and paired t-test. ResultsFifteen (65 %) of the eligible stroke survivors enrolled (60 % white, 27 % black), 12 (80 %) had an ischemic stroke, ages ranged from 33 to 74 years (mean 44 years), and mean months since stroke was 33 ± 23. Retention and questionnaire completion rates were both 93 % (n = 14). Survivors logged into the virtual environment a total of 122 times, logged an average of 49 min/log-in, and 12 (80 %) attended support groups and social activities. Median usability score indicated lower than average usability. Improvement trends in social support, loneliness, and depressive symptoms were found, but significant changes in mean questionnaire scores were not found. ConclusionsOverall, the results suggest that using a virtual environment to foster social support exchanges, social network interactions, and recovery education after stroke is feasible. Similar to other chronic disease populations, stroke survivor adoption of a virtual environment likely requires ongoing technical assistance, repetition of instructions, and opportunities for practice to reinforce engagement. Trial registrationNCT05487144.

Tracking the structure and sentiment of vaccination discussions on Mumsnet

Vaccination is one of the most impactful healthcare interventions in terms of lives saved at a given cost, leading the anti-vaccination movement to be identified as one of the top 10 threats to global health in 2019 by the World Health Organization. This issue increased in importance during the COVID-19 pandemic where, despite good overall adherence to vaccination, specific communities still showed high rates of refusal. Online social media has been identified as a breeding ground for anti-vaccination discussions. In this work, we study how vaccination discussions are conducted in the discussion forum of Mumsnet, a UK-based website aimed at parents. By representing vaccination discussions as networks of social interactions, we can apply techniques from network analysis to characterize these discussions, namely network comparison, a task aimed at quantifying similarities and differences between networks. Using network comparison based on graphlets—small connected network subgraphs—we show how the topological structure of vaccination discussions on Mumsnet differs over time, in particular before and after COVID-19. We also perform sentiment analysis on the content of the discussions and show how the sentiment toward vaccinations changes over time. Our results highlight an association between differences in network structure and changes to sentiment, demonstrating how network comparison can be used as a tool to guide and enhance the conclusions from sentiment analysis.

Experimental flintknapping with sandstones and prospection of lithic raw material sources from Cabra Corral area, Salta, Argentina

Within the framework of the project named Technological Variability and Social Interaction Networks in Northwest Argentina through the study of lithic technology strategies throughout the Formative period (Mercuri 2012) we collected samples of lithic raw materials in different portions of Las Conchas- Guachipas river area (Salta, Argentina) in order to create a reference collection. With part of this material we performed experimental lithic flintknapping with the aim to observe fractures and other characteristics that allow determining flintknapping quality so that we can understand and give a first reading to the selection of raw materials for making artifacts using local rocks.We present the results of these experiments conducted on sandstone, as it was the predominant raw material in the archaeological record. First results allow us to affirm that sandstone, given the availability and quality for flintknapping tasks constitutes an optimal raw material for the production of artifacts. We also note that the obtained edges are suitable for cutting work and the notches recorded in the artifacts are due probably to the characteristics of rock fracture.

Design and validation of a scale of core components of community interventions in mental health.

To develop and validate an instrument to identify the core components of community strategies for mental health, especially mutual aid groups: The Mutual Aid Scale . 135 community strategies leaders participated in the study. The core components are active agency, coping strategies, recognition, and management of emotions, problem-solving strategies, supportive interaction, trust, self-identity construction, and strengthening of social networks. With these components a scale was designed. Content validity was carried out in addition to an exploratory factor analysis. Two dimensions resulted, strengthening of agency capacity and Coping strategies, and the internal consistency of both factors was acceptable, with a Cronbach's alpha of 0.722 and 0.727, respectively. The Kaiser-Meyer-Olkin (KMO) statistic was used with a score of 0.831 and the Barlett Sphericity Test, with a significant value of 265.175. This scale identifies the components of community interventions for mental health and can contribute to a better implementation of these strategies. It also articulates autonomous community processes with strategies developed in health services.

Graph Learning Augmented Heterogeneous Graph Neural Network for Social Recommendation

Social recommendation based on social network has achieved great success in improving the performance of the recommendation system. Since social network (user-user relations) and user-item interactions are both naturally represented as graph-structured data, Graph Neural Networks (GNNs) have thus been widely applied for social recommendation. Despite the superior performance of existing GNNs-based methods, there are still several severe limitations: (i) Few existing GNNs-based methods have considered a single heterogeneous global graph which takes into account user-user relations, user-item interactions, and item-item similarities simultaneously. That may lead to a lack of complex semantic information and rich topological information when encoding users and items based on GNN. (ii) Furthermore, previous methods tend to overlook the reliability of the original user-user relations which may be noisy and incomplete. (iii) More importantly, the item-item connections established by a few existing methods merely using initial rating attributes or extra attributes (such as category) of items, may be inaccurate or sub-optimal with respect to social recommendation. In order to address these issues, we propose an end-to-end heterogeneous global graph learning framework, namely Graph Learning Augmented Heterogeneous Graph Neural Network (GL-HGNN) for social recommendation. GL-HGNN aims to learn a heterogeneous global graph that makes full use of user-user relations, user-item interactions and item-item similarities in a unified perspective. To this end, we design a Graph Learner (GL) method to learn and optimize user-user and item-item connections separately. Moreover, we employ a Heterogeneous Graph Neural Network (HGNN) to capture the high-order complex semantic relations from our learned heterogeneous global graph. To scale up the computation of graph learning, we further present the Anchor-based Graph Learner (AGL) to reduce computational complexity. Extensive experiments on four real-world datasets demonstrate the effectiveness of our model.

The Heriot of Ramornie annotated copy of Flora Glottiana: an early nineteenth-century Flora of Fife

The ownership of a copy of Flora Glottiana heavily annotated in the 1810s is discussed. The annotations are attributed to James Heriot ( né Maitland) or his wife Margaret ( née Dalgleish), owners of the estate of Ramornie in Fife. The marginalia turn the volume into a local Flora for Fife, vice-county (vc) 85; some of the more interesting species records and their localities are discussed. Many of the localities are estates that belonged to Maitland or Dalgleish relations, suggesting that botanical recording formed part of a network of familial and social interactions. Such links went beyond Scotland and connections with India are discussed, as is the question of how the volume ended up in the ownership of John Hutton Balfour.

Predicting Learning Interactions in Social Learning Networks: A Deep Learning Enabled Approach

We consider the problem of predicting link formation in Social Learning Networks (SLN), a type of social network that forms when people learn from one another through structured interactions. While link prediction has been studied for general types of social networks, the evolution of SLNs over their lifetimes coupled with their dependence on which topics are being discussed presents new challenges for this type of network. To address these challenges, we develop a series of autonomous link prediction methodologies that utilize spatial and time-evolving network architectures to pass network state between space and time periods, and that models over three types of SLN features updated in each period: neighborhood-based (e.g., resource allocation), path-based (e.g., shortest path), and post-based (e.g., topic similarity). Through evaluation on six real-world datasets from Massive Open Online Course (MOOC) discussion forums and from Purdue University, we find that our method obtains substantial improvements over Bayesian models, linear classifiers, and graph neural networks, with AUCs typically above 0.91 and reaching 0.99 depending on the dataset. Our feature importance analysis shows that while neighborhood and path-based features contribute the most to the results, post-based features add additional information that may not always be relevant for link prediction. The code and four of the datasets used in this work are available at https://github.com/Jess-jpg-txt/sln-learning.