Target Behavior Research Articles

Multi-view multi-behavior interest learning network and contrastive learning for multi-behavior recommendation

The recommendation system aims to recommend items to users by capturing their personalized interests. Traditional recommendation systems typically focus on modeling target behaviors between users and items. However, in practical application scenarios, various types of behaviors (e.g., click, favorite, purchase, etc.) occur between users and items. Despite recent efforts in modeling various behavior types, multi-behavior recommendation still faces two significant challenges. The first challenge is how to comprehensively capture the complex relationships between various types of behaviors, including their interest differences and interest commonalities. The second challenge is how to solve the sparsity of target behaviors while ensuring the authenticity of information from various types of behaviors. To address these issues, a multi-behavior recommendation framework based on Multi-View Multi-Behavior Interest Learning Network and Contrastive Learning (MMNCL) is proposed. This framework includes a multi-view multi-behavior interest learning module that consists of two submodules: the behavior difference aware submodule, which captures intra-behavior interests for each behavior type and the correlations between various types of behaviors, and the behavior commonality aware submodule, which captures the information of interest commonalities between various types of behaviors. Additionally, a multi-view contrastive learning module is proposed to conduct node self-discrimination, ensuring the authenticity of information integration among various types of behaviors, and facilitating an effective fusion of interest differences and interest commonalities. Experimental results on three real-world benchmark datasets demonstrate the effectiveness of MMNCL and its advantages over other state-of-the-art recommendation models. Our code is available at https://github.com/sujieyang/MMNCL.

Uptake of eye care services in South India: Retrospective mapping of self-reported barriers using the Theoretical Domains Framework.

Understanding barriers to seeking eye care and providing evidence-based theory-informed solutions can improve the uptake of eye care services. Therefore, in this cross-sectional study, we aim to report and analyse barriers to seeking eye care services among individuals with vision impairment in the Akividu region of Andhra Pradesh, India. Out of the 3000 enumerated participants, a total of 2587 were examined. All participants with vision impairment were asked to report barriers for not seeking eye care despite noticing reduced vision using a validated questionnaire. The reported barriers were mapped to the theoretical domains framework (TDF) to explore potential individual and environmental influences on the uptake of eye care services. Barriers to seeking eye care services are most frequently mapped to the 'beliefs about capabilities', 'environmental context and resources' and 'social influences' domains of the TDF. The most frequently reported barrier was 'aware of the problem but can manage' (beliefs about capabilities), expressed by 43.4% (n = 156) and 55.7% (n = 337) of participants with distance and near vision impairment, respectively. 'No one to accompany' for an appointment (social influences) was a significant barrier for participants with distance vision impairment (n = 44, 12.2%) in comparison to participants with near vision impairment (n = 19, 3.1%). Additionally, fear of losing eyesight or operation or consultation (emotion) was a major deterrent for seeking eye care services, particularly among participants with distance vision impairment (n = 31, 8.6%) when compared with near vision impairment (n = 17, 2.8%). The uptake of eye care services is influenced by a complex set of interacting factors. Identification of potentially modifiable target behaviours provides an opportunity to develop theory-informed solutions to improve uptake of services and prevent avoidable vision loss.

Enrollment in Alzheimer’s disease-focused research registries: altruistic and egocentric motivations

ABSTRACT The relative effectiveness of altruistic and egocentric persuasion messages is an important research question when voluntary participation in medical research is the target behavior. In the US, most participants in Alzheimer’s disease-focused research registries are White females, so increasing diversity in registry membership is a public health priority. We compared the association of two belief-based motivations – egocentric and altruistic – with intention to enroll in an Alzheimer’s research registry using a nationally representative theory-based survey of US adults 50 years of age or older while oversampling Black and Hispanic respondents. With the exception of Hispanic females, there were few respondent differences between individual motivational belief items and the correlations between the altruistic and egocentric indices were similar with independent effects on intention: the effects of the two motivations on intention were not redundant. Further analysis demonstrated that a moderation model was not superior to an additive model when both altruistic and egocentric indices simultaneously predicted intention. Registry recruitment messages should use both altruistic and egocentric persuasive message components to increase enrollment into Alzheimer’s research registries. Similar studies should determine if the additive effects of altruistic and egocentric motivations apply to other voluntary research participation contexts such as chronic diseases and mental illness.

Protocol for the development of an intervention to improve the use of Point-of-caRE DiagnostICs in the management of respiraTOry tRact infectionS in primary care (the PREDICTORS study)

Background Antimicrobial resistance is a significant global health challenge, exacerbated by inappropriate antibiotic prescribing, particularly in primary care where up to 50% of antibiotic prescriptions prescribed by general practitioners (GPs) and dispensed by community pharmacists (CPs) are deemed inappropriate. Respiratory tract infections (RTIs) are among the most common conditions leading to GP consultations and subsequent antibiotic prescribing, much of which is inappropriate as most RTIs are viral in nature or self-limiting bacterial infections. Point-of-care tests (POCTs) have emerged as tools to improve the diagnosis and appropriate treatment of RTIs. Objective This study aims to develop and test an intervention to improve the use of POCTs in managing RTIs involving GPs and CPs in Irish primary care, following the UK’s Medical Research Council’s (MRC) framework for complex intervention development, involving five work-packages (WPs). Methods WP1 involves creating best practice guidance for using POCT in managing RTIs, informed by a scoping review and validated with an expert Delphi panel. This guidance will be used to define target behaviour(s) for GPs and CPs related to POCT use. WP2 explores GP and CP perceived barriers and facilitators to these behaviours using the Theoretical Domains Framework, mapping influential domains to Behaviour Change Techniques to develop draft interventions. WP3 gathers patients’ perspectives on using POCTs for RTIs. In WP4, a task group will review and finalise the intervention(s). They will consider patients’ perspectives from WP3 and assess feasibility of the intervention(s). WP5 involves a proof-of-concept study to test the feasibility of the newly developed intervention(s). Conclusion A theoretically informed intervention(s) for using POCT(s) in the management of RTIs in primary care in Ireland will be developed and tested in a proof-of-concept study, following MRC guidance. Further refinement and larger studies will be needed to determine its effectiveness before widespread implementation.

A personal sensing technology enabled service versus a digital psychoeducation control for primary care patients with depression and anxiety: a pilot randomized controlled trial

BackgroundTechnology-enabled services (TES; clinical services that include both technology-driven [e.g., personal sensing technologies] and person-powered support elements) may address gaps in depression and anxiety treatments in healthcare settings. The current study: (1) developed a TES tailored for Primary Care patients with depression and/or anxiety, and (2) conducted a pilot randomized controlled trial to assess the efficacy of the TES compared to a digital psychoeducation control app.MethodsParticipants were randomized to either: (1) TES: the “Vira” smartphone app (Ksana Health Inc.), informed by behavioral activation and using passive sensing technology to provide behavioral “insights” and target behaviors associated with mental health symptoms, alongside lay-provider coaching, or (2) Control: the Mood Education mobile app (ME), containing static psychoeducational resources designed to target mental health symptoms. Both apps collected usage data. Participants completed assessments on depression (PHQ-9), anxiety (GAD-7), health-related quality of life (PedsQL), and engagement (TWEETs) at baseline, mid-treatment (week 4), end-of-treatment (week 8), and post-treatment (week 12).ResultsParticipants (N = 130) were randomized to receive either the TES (Vira; Mage= 30) or ME (Mage= 33). Linear mixed-effects models determined significant improvements in PHQ-9 and GAD-7 scores for participants across both conditions (ps < 0.001). There was no interactive effect of intervention and time for the PHQ-9 (p = .90) nor the GAD-7 (p = .49). Adjusting for baseline differences and randomization strata, TES participants reported a greater change in a quality of life rating of Physical Functioning (PedsQL) across time (p = .018). TES participants also reported higher levels of engagement and demonstrated higher app usage. However, adjusting for baseline symptom severity, neither app usage nor coach interaction frequency moderated outcomes (ps ≥ 0.2).ConclusionsWhile the TES demonstrated superior engagement, improvements in depressive and anxious symptoms for both conditions speak to the potential benefit of both TES and low-intensity psychoeducation treatments in care settings. Future research is needed to better understand which patients might differentially benefit from TESs and broader personal sensing technologies over low-intensity treatments.Trial registrationClinicalTrials.gov NCT05406791.

Intervention development and optimisation of a multi-component digital intervention for the monitoring and management of hypertensive pregnancy: the My Pregnancy Care Intervention

BackgroundHypertensive disorders of pregnancy affect around 10% of pregnancies and remain a major cause of maternal and foetal morbidity and mortality. Trials have shown that self-monitoring blood pressure during pregnancy is safe, but self-monitoring alone does not improve blood pressure control or pregnancy outcomes. This study aimed to develop and optimise a multicomponent intervention to support blood pressure monitoring, hypertension management and urine testing within current care pathways.MethodsRelevant literature, input from patient and public contributors (PPI) and stakeholder groups, and the researcher’s previous experience were used to develop an initial intervention. Think-aloud interviews and focus groups with women from diverse backgrounds with lived experience of hypertension in pregnancy and healthcare professionals provided feedback on the intervention prototype (n = 29). The MRC Framework for Developing Complex Interventions guided the processes to optimise the intervention’s acceptability and maximise engagement. A detailed tabulation of participants’ views and logic models was produced using the COM-B model of Behaviour Change.ResultsThe prototype intervention was acceptable and viable to both pregnant women with experience of hypertensive pregnancy and healthcare professionals. Emerging themes centred on how the intervention could be optimised within current National Health Service care pathways and the lives of pregnant women to support behaviour change. Key target behaviours to support the intervention included increasing understanding of blood pressure management, engagement with the intervention, monitoring blood pressure and urine and taking appropriate actions based on those readings. This informed the development of recommendations involving clear action timelines for women and evidence-based guidance to support decision-making by healthcare professionals. The findings were used to produce the multi-component My Pregnancy Care intervention, consisting of a smartphone application and an information leaflet to support blood pressure self-monitoring and proteinuria self-testing, self-management of antihypertensive medication and smartphone application use.ConclusionsThis research provided comprehensive insight into the needs of pregnant women with hypertension and their healthcare teams regarding self-monitoring and management of blood pressure. This supported the development of a tailored multi-component digital intervention that addresses barriers to blood pressure self-management by being user-friendly, persuasive and acceptable. It is hoped that the intervention will support the monitoring and management process, collaboration between healthcare professionals and women, clinical action and improved clinical outcomes.

Research on combined damage characteristics of underwater armor-piercing and explosion based on supercavitating projectile

Recent studies of supercavitating projectiles primarily focus on the formation and evolution of the cavity, as well as its underwater ballistic characteristics, while neglecting the terminal damage effects. Little attention has been given to exploring the combined damage effects of armor-piercing-explosion supercavitating projectiles (APESP). Therefore, this study comparatively analyzes the response processes and failure modes of an underwater aluminum alloy cylindrical shell target under the action of three different types of loads: armor piercing, explosion, and combined armor-piercing and explosion. This study investigates the underwater combined damage mechanisms of the APESP, clarifies each damage phase under the combined effect, discusses the advantages of damage resulting from the combined armor-piercing and explosion effect based on the target responses and damage modes, and explores the reasons for dissipation of explosion energy. The results show that: the APESP combines localized point damage characteristics of armor piercing with overall surface damage features of underwater explosion. Depending on load stages and target responses, the target response process under the action of the APESP can be divided into the hydrodynamic ram phase, penetration phase, shock wave phase, stable vibration phase, and bubble pulsation phase. The entire physical system can be abstracted as a low-frequency series spring system (equivalent to bubble pulsation frequency) with high-frequency external energy input, based on the energy relationship of the medium and the structure. The concept of the 'blower effect' is proposed based on target behavior during the stable vibration phase. Following the application of different loads, the plastic deformation of the target in a stable state is ranked as: underwater explosion > combined armor-piercing and explosion > underwater armor piercing. Supercavity, shell casing and penetration hole will cause the dissipation of explosion energy.

Examining Immediate and Sustained Effects of Check-In/Check-Out in Finnish Elementary Schools

Check-in/Check-out (CICO) behavioral support has been implemented in Finnish School-Wide Positive Behavior Interventions and Support (SWPBIS) schools to cater to students who require personalized behavior support beyond the universal level. Previous studies have demonstrated the effectiveness of CICO as a behavioral support method. However, further research is needed to investigate its effectiveness in a larger sample and to analyze the timeline for behavioral change. This study focused on 51 elementary school students, assessing their behavior at baseline and during the CICO intervention phase using two data collection methods: the Daily Report Card (DRC) and the School Situation Questionnaire (SSQ). Nonlinear growth modeling was employed to examine the effects of the intervention. The results indicated that CICO yielded significant positive effects on behavior within 1 week of initiating support. After the outcomes stabilized, the behavior change remained stable beyond the first week of the intervention. These effects were detected in both the target behavior measured with DRC and the problem behavior measured with SSQ. These findings suggest that CICO interventions produce rapid and sustained changes in behavior. Further, the effects of CICO were observed in various settings within the school environment, indicating distal outcomes.

Exploring the Effects of Augmented Reality on the Emotion Recognition Skills of Autistic Children

Autistic children have significant difficulties in recognizing and labeling emotions, difficulties which may hinder the natural development of their ability to express and regulate further emotions. The purpose of this study was to evaluate the effect of an augmented reality emotion recognition program (ARERP) delivered in a group format on the emotion recognition of young autistic children. This study employed a concurrent multiple probe design across behaviors to evaluate the effects of the training on children’s emotion recognition. The target behavior was recognizing three emotion sets: positive, negative, and complex. The sequence of conditions included pre-test, baseline, training, post-test, and follow-up sessions. Positive results were found across all four children who all achieved 100% accuracy in identifying emotions during the training. Further, the emotion recognition skills were successfully maintained for 4–7 weeks post-training, with observed generalization to untrained still pictures and GIFs. This study provides preliminary evidence supporting the effectiveness of AR-based group training for young autistic children.

Long-Term Tracking of Evasive Urban Target Based on Intention Inference and Deep Reinforcement Learning.

Unmanned aerial vehicles (UAVs) have been widely used in urban target-tracking tasks, where long-term tracking of evasive targets is of great significance for public safety. However, the tracked targets are easily lost due to the evasive behavior of the targets and the unstructured characteristics of the urban environment. To address this issue, this article proposes a hybrid target-tracking approach based on target intention inference and deep reinforcement learning (DRL). First, a target intention inference model based on convolution neural networks (CNNs) is built to infer target intentions by fusing urban environment information and observed target trajectory. Then, the prediction of the target trajectory can be inspired by the inferred target intentions, which can further provide effective guidance to the target search process. In order to fully explore the policy space, the target search policy is developed under a DRL framework, where the search policy is modeled as a deep neural network (DNN) and trained by interacting with the task environment. The simulation results show that the inference of the target intentions can effectively guide the UAV to search for the target and significantly improve the target-tracking performance. Meanwhile, the generalization results indicate that the proposed DRL-based search policy has high robustness to the uncertainty of the target behavior.

Effects of grain size, dislocation density, and texture type on the etching behavior of Cu target in magnetron sputtering process

Abstract Copper thin film is commonly applied in the microelectronics and battery industries, and environmentally friendly magnetron sputtering process is one of the main coating processes. The effects of grain size, dislocation density, and texture type of Cu target on sputtering efficiency were researched in this work. High-purity copper cast ingots were rolled into plates. Pieces were then cut from different surfaces of the plates and assembled into the targets named as Target 1, Target 2, and Target 3 for magnetron sputtering. To investigate the etching behavior of the three targets, EBSD technology was utilized for analysis, and the micro-morphologies of the etching grooves were observed using SEM. After the sputtering process, the weight loss rate and etching depth of the various targets were measured to compare the respective sputtering efficiency. Target 1 exhibited the highest sputtering weight loss rate at any time period compared to Target 2 and Target 3, and reached its maximum depth after every 15 minutes of sputtering. In the first 45 minutes, the etching depth of Target 2 was slightly greater than that of Target 3. While the etching depth of Target 3 increased significantly in the last 15 minutes compared to that of Target 2. The most significant factor influencing the sputtering efficiency of the target material was grain size, with finer grains leading to higher sputtering efficiency. The dislocation density had a greater impact in the first 30 minutes, but the texture type became more important as the sputtering process continued.

Preventing type 2 diabetes in Portugal: a novel person-centered digital intervention

Abstract Introduction Diabetes, particularly type 2 diabetes (T2D), stands as one of the leading noncommunicable diseases worldwide. In Portugal, the prevalence of diabetes has surged, with T2D affecting 14% of adults in 2021. Its repercussions extend beyond individual health, deeply impacting familial, social, and community dynamics, presenting a significant public health challenge globally. Objectives The VA|PREVENTION project (https://doi.org/10.54499/2022.02969.PTDC) aims to assess the (cost-) effectiveness and implementation of an innovative person-centered digital intervention to prevent T2D among high-risk adults. Methodology A comprehensive approach encompasses the Behavior Change Wheel for intervention design, scalability principles, the WHO guidelines for digital health interventions, co-design, and the ISO framework for usability assessment. Evaluation will be pursued through a type 1 hybrid effectiveness-implementation study (randomized controlled trial), supplemented by qualitative and economic studies. Results The web application prototype features Ema, an automated virtual human coach (VHC), educational menus and a dashboard (version 1.0). Co-design included 2 workshops with 11 representatives of end-users and health professionals. Ema uses standardized techniques from an ontology to support behavior change, based on an initial assessment of low-level target behaviors (e.g. walking, fruit consumption, and reducing red meat intake), and barriers to performing these behaviors. Ema communicates in a helpful-cooperative style using a synthetic voice in European Portuguese, with its speech also appearing as subtitles on the interface. Users interact with Ema by pressing buttons or entering data, such as the daily number of steps. Ethics approval was granted for usability assessment with end-users. Conclusions The project is expected to yield health, scientific, technological, and policy impacts, powered by an exploitation and sustainability roadmap. Key messages • Innovative type 2 diabetes prevention through a scalable web app with a virtual human coach. • Comprehensive and robust approach for developing and evaluating the digital behavior change intervention.

Analysing the behaviour change techniques in an effective food literacy program to inform future program design.

Food literacy programs aim to improve food related skills and knowledge and are selected Governments as a strategy to address dietary intakes at a community level. The purpose of this research is to identify behaviour change techniques in a food literacy program, which were assessed by the achievement of participant goals related to food literacy and dietary behaviour changes. Consensus methods were applied to map behaviour change techniques to an adult food literacy program. A second phase investigation applied content analysis of participant process evaluation data (collected between 2016 and June 2021) to align target behaviours and behaviour change techniques. Chi-square and ANCOVA were used to assess the statistically significant demographic characteristics, food literacy, and dietary behaviour scores for participants who set goals and recorded changes. A total of 4697 program participants provided evaluation data from the 4-week food literacy program. Participants who set goals and made changes were statistically more likely to have higher food literacy factor scores (p < 0.001) and fruit serves (p = 0.004). Statistical analysis showed that participants were more likely to have set goals and recorded changes if they were female (p < 0.001), older (p < 0.001), higher education level (p < 0.001), had a higher socioeconomic status (p = 0.049), lived with children (p = 0.014), were born in Australia (p = 0.019), or did not identify as Indigenous (p < 0.001). The behaviour change technique mapping process identified nine techniques used weekly and a total of 22 techniques used over the entire 4 week program curriculum. This is the first Australian study to link the contribution of behaviour change techniques to food literacy and dietary behaviour change in an established effective food literacy program. Knowing the behaviour change techniques associated with effective programs will facilitate replication of effective interventions.

Assessment and Treatment of Target Behavior Maintained by Social Avoidance.

Past research has identified that some individuals with intellectual and developmental disabilities who engage in target behavior (e.g., aggression, self-injury) maintained by negative reinforcement engage in the behavior to escape or avoid social interaction specifically (i.e., social avoidance). However, assessment and treatment strategies for this function are understudied when compared to target behavior maintained by other forms of negative reinforcement. The current study builds on this limited research and demonstrates (a) a replication of functional analysis conditions and a negative reinforcement latency assessment to identify the specific types of social interaction that evoke target behavior, and (b) an intervention that includes stimulus fading, social conditioning, and differential reinforcement for five participants with autism spectrum disorder. Participant target behavior decreased within the intervention phase for four out of five participants. The implications of strategies to guide the use of antecedent-based treatment strategies are discussed for target behavior maintained by social avoidance.

Формирование элементарных математических представлений у детей с ограниченными возможностями здоровья (с нарушением зрения)

The aim of this study is to improve the math skills of preschool children (5-7 years old) with visual impairment. In this context, it is expected that the target behavior of children with visual impairment will be changed through the creation of a specialized educational space that promotes the formation of mathematical abilities, arithmetic skills, creativity, ability to plan and organize their activities. The research group consists of 48 preschool children (5-7 years old) with visual impairments. The study was conducted in the fall of the 2023-2024 school year. During the study, the preschoolers received eight weeks of training to improve math skills. The study found that numeracy and math skills in preschool children with visual impairments had a positive effect on cognitive development, fine motor skills, and motivation to learn.

Applying a new theoretical and methodological approach for behavior-change campaign planning: identifying the critical determinants for reducing littering and evaluating the resulting large-scale campaign.

This paper presents a theoretical concept and methodological approach for identifying critical determinants for behavior change interventions. The approach is based on established theories and constructs but represents them in an intervention- instead of questionnaire-oriented form. Six discriminant and targetable dimensions of behavior determinants are proposed: Consideration, feasibility, instrumental evaluation, norms and goals, affective evaluation, and needs and tension states. For estimating the importance of these dimensions for a specific behavior to be changed in a specific situation and population, a quasi-experimental approach is proposed, in which interventions are designed to have effects on one of these dimensions but none on the other dimensions. By measuring changes of the target behavior or its consequences, the impact of each dimension on changing the behavior can be estimated in-situ without questionnaires. The approach was applied to develop a campaign for reducing picnic littering in an urban park in Zurich (Switzerland). In 2019, posters targeting four dimensions were set up during three waves in up to four zones with two control zones without posters. Before, between, and after the intervention waves, for at least 2 weeks, no interventions were in place. The volume of litter was measured on 119 days at 55 points. In some cases, the amount of litter was too small for effects to be detected, but where enough littering occurred, posters providing information, inducing positive emotions, or activating reciprocity norms-as well as providing the option of separating fractions of waste for recycling as a structural measure-reduced litter significantly. Interventions targeting the tension state of disgust had no effect. Posters targeting descriptive and injunctive norms increased the amount of litter. Based on the results of the preparative study, a large-scale campaign was designed, implemented, and evaluated in 2022, which led to promising effects.

Behavioral Nudging With Generative AI for Content Development in SMS Health Care Interventions: Case Study.

Brief message interventions have demonstrated immense promise in health care, yet the development of these messages has suffered from a dearth of transparency and a scarcity of publicly accessible data sets. Moreover, the researcher-driven content creation process has raised resource allocation issues, necessitating a more efficient and transparent approach to content development. This research sets out to address the challenges of content development for SMS interventions by showcasing the use of generative artificial intelligence (AI) as a tool for content creation, transparently explaining the prompt design and content generation process, and providing the largest publicly available data set of brief messages and source code for future replication of our process. Leveraging the pretrained large language model GPT-3.5 (OpenAI), we generate a collection of messages in the context of medication adherence for individuals with type 2 diabetes using evidence-derived behavior change techniques identified in a prior systematic review. We create an attributed prompt designed to adhere to content (readability and tone) and SMS (character count and encoder type) standards while encouraging message variability to reflect differences in behavior change techniques. We deliver the most extensive repository of brief messages for a singular health care intervention and the first library of messages crafted with generative AI. In total, our method yields a data set comprising 1150 messages, with 89.91% (n=1034) meeting character length requirements and 80.7% (n=928) meeting readability requirements. Furthermore, our analysis reveals that all messages exhibit diversity comparable to an existing publicly available data set created under the same theoretical framework for a similar setting. This research provides a novel approach to content creation for health care interventions using state-of-the-art generative AI tools. Future research is needed to assess the generated content for ethical, safety, and research standards, as well as to determine whether the intervention is successful in improving the target behaviors.

Overcoming Hepatic Biotransformation Barrier of Gold Nanoparticles via Au-Se Bond for Enhanced In Vivo Active Targeting.

As a key metabolic function of the liver, the hepatic biotransformation process can alter the predesigned surface chemistry of nanoparticles in vivo, leading to hampered functionality and targeting ability. However, strategies to modulate the hepatic biotransformation of nanoparticles have been rarely explored. Herein, using indocyanine green (ICG)-conjugated gold nanoparticles that target liver hepatocytes as a model, we showed that merely changing the metal-ligand bond from gold-sulfur (Au-S) to gold-selenium (Au-Se) completely reshaped the hepatic biotransformation profiles of the nanoparticle as well as its targeting and transport behaviors in vivo. Compared with those of Au-S bond, Au-Se bond markedly slowed down nanoparticle biotransformation in liver sinusoids, enhanced ICG-mediated nanoparticle targeting to hepatocytes by 15-fold, and also altered nanoparticle intrahepatic transport, distribution, and clearance pathways. Moreover, we demonstrated that Au-Se bond could improve the active targeting of gold nanoparticles to hepatic tumors by reducing liver biotransformation-induced dissociation of targeting ligands. These discoveries not only deepen our understanding of nanoparticle biotransformation in the liver but also offer a strategy to overcome the biochemical barrier of hepatic biotransformation, providing guidance for the design and engineering of related nanomedicines by tuning their in vivo biotransformation profiles.

National biodiversity strategies under-utilize the potential for individual behavior change

Biodiversity conservation is increasingly recognized as a main challenge for the sustainability agenda. With humans at the epicenter of the biodiversity crisis, conserving nature requires changes in individual behavior. This study reveals gaps regarding the incorporation of behavior change into national biodiversity policy. A total of 1306 policy actions proposed by ten National Biodiversity Strategies and Action Plans (NBSAPs) from all world regions were coded for target actors, target behavior and responsible agents as well as the policy options, intervention types and behavioral determinants listed in the Behavior Change Wheel (BCW) framework. Results show that only 11 % (n=148) of the policy actions specified individual behaviors and 10 % mentioned individual actors to be targeted. Only 3 % (n=36) of the policy actions were specific about how interventions and policies could enable individual behavior change. Policy actions targeting individual behavior change were aimed mostly at increasing people’s capabilities (i.e., providing information) or providing opportunities (i.e., resources), and rarely addressed the motivation of individuals. More attention and specificity regarding behavior change and better incorporation of the behavioral sciences can improve the effectiveness of national biodiversity strategies.

Contrastive Clustering Learning for Multi-Behavior Recommendation

Increasing multiple behavior recommendation models have achieved great successes. However, many models do not consider commonalities and differences between behaviors and data sparsity of the target behavior. This paper proposes a novel Multi-behavior Recommendation Model (MBRCC) based on Contrastive Clustering Learning. Specifically, the graph convolutional network (GCN) is employed to obtain the embeddings of users and items, respectively. Then, three kinds of tasks (including behavior-level embedding, instance-level embedding and cluster-level embedding) are designed to optimize the embeddings of users and items. In behavior-level embedding, we design an adaptive parameter learning strategy to analyze the impact of auxiliary behaviors on the target behavior. Then, the embeddings of users for each behavior are weighted to obtain the final embeddings of users. In instance-level embedding, we employ contrastive learning to analyze the instances of user and item for mitigating the issue of data sparsity. In cluster-level embedding, we design a new cluster contrastive learning method to capture the similarity between groups of user and item. Finally, we combine these three tasks to improve the quality of the embeddings of users and items. We conduct extensive experiments on three real-world datasets and experimental results indicate that the MBRCC remarkably outperforms numerous existing recommendation models.