Learning Sentence-to-Hashtags Semantic Mapping for Hashtag Recommendation on Microblogs

The growing use of microblogging platforms is generating a huge amount of posts that need effective methods to be classified and searched. In Twitter and other social media platforms, hashtags are exploited by users to facilitate the search, categorization, and spread of posts. Choosing the appropriate hashtags for a post is not always easy for users, and therefore posts are often published without hashtags or with hashtags not well defined. To deal with this issue, we propose a new model, called HASHET ( HAshtag recommendation using Sentence-to-Hashtag Embedding Translation ), aimed at suggesting a relevant set of hashtags for a given post. HASHET is based on two independent latent spaces for embedding the text of a post and the hashtags it contains. A mapping process based on a multi-layer perceptron is then used for learning a translation from the semantic features of the text to the latent representation of its hashtags. We evaluated the effectiveness of two language representation models for sentence embedding and tested different search strategies for semantic expansion, finding out that the combined use of BERT ( Bidirectional Encoder Representation from Transformer ) and a global expansion strategy leads to the best recommendation results. HASHET has been evaluated on two real-world case studies related to the 2016 United States presidential election and COVID-19 pandemic. The results reveal the effectiveness of HASHET in predicting one or more correct hashtags, with an average F -score up to 0.82 and a recommendation hit-rate up to 0.92. Our approach has been compared to the most relevant techniques used in the literature ( generative models , unsupervised models, and attention-based supervised models ) by achieving up to 15% improvement in F -score for the hashtag recommendation task and 9% for the topic discovery task.

Ambient intelligence governance review: from service-oriented to self-service

The current generation of connected devices and the Internet of Things augment people’s capabilities through ambient intelligence. Ambient Intelligence (AmI) support systems contain applications consuming available services in the environment to serve users. A well-known design of these applications follows a service architecture style and implement artificial intelligence mechanisms to maintain an awareness of the context: The service architecture style enables the distribution of capabilities and facilitates interoperability. Intelligence and context-awareness provide an adaptation of the environment to improve the interaction. Smart objects in distributed deployments and the increasing machine awareness of devices and people context also lead us to architectures, including self-governed policies providing self-service. We have systematically reviewed and analyzed ambient system governance considering service-oriented architecture (SOA) as a reference model. We applied a systematic mapping process obtaining 198 papers for screening (out of 712 obtained after conducting searches in research databases). We then reviewed and categorized 68 papers related to 48 research projects selected by fulfilling ambient intelligence and SOA principles and concepts. This paper presents the result of our analysis, including the existing governance designs, the distribution of adopted characteristics, and the trend to incorporate service in the context-aware process. We also discuss the identified challenges and analyze research directions.

Coordination of sustainable financing for evidence-based youth mental health treatments: protocol for development and evaluation of the fiscal mapping process

Background Sustained delivery of evidence-based treatments (EBTs) is essential to addressing the public health and economic impacts of youth mental health problems, but is complicated by the limited and fragmented funding available to youth mental health service agencies (hereafter, “service agencies”). Strategic planning tools are needed that can guide these service agencies in their coordination of sustainable funding for EBTs. This protocol describes a mixed-methods research project designed to (1) develop and (2) evaluate our novel fiscal mapping process that guides strategic planning efforts to finance the sustainment of EBTs in youth mental health services. Method Participants will be 48 expert stakeholder participants, including representatives from ten service agencies and their partners from funding agencies (various public and private sources) and intermediary organizations (which provide guidance and support on the delivery of specific EBTs). Aim 1 is to develop the fiscal mapping process: a multi-step, structured tool that guides service agencies in selecting the optimal combination of strategies for financing their EBT sustainment efforts. We will adapt the fiscal mapping process from an established intervention mapping process and will incorporate an existing compilation of 23 financing strategies. We will then engage participants in a modified Delphi exercise to achieve consensus on the fiscal mapping process steps and gather information that can inform the selection of strategies. Aim 2 is to evaluate preliminary impacts of the fiscal mapping process on service agencies’ EBT sustainment capacities (i.e., structures and processes that support sustainment) and outcomes (e.g., intentions to sustain). The ten agencies will pilot test the fiscal mapping process. We will evaluate how the fiscal mapping process impacts EBT sustainment capacities and outcomes using a comparative case study approach, incorporating data from focus groups and document review. After pilot testing, the stakeholder participants will conceptualize the process and outcomes of fiscal mapping in a participatory modeling exercise to help inform future use and evaluation of the tool. Discussion This project will generate the fiscal mapping process, which will facilitate the coordination of an array of financing strategies to sustain EBTs in community youth mental health services. This tool will promote the sustainment of youth-focused EBTs.

Graph Picture of Linear Quantum Networks and Entanglement

The indistinguishability of quantum particles is widely used as a resource for the generation of entanglement. Linear quantum networks (LQNs), in which identical particles linearly evolve to arrive at multimode detectors, exploit the indistinguishability to generate various multipartite entangled states by the proper control of transformation operators. However, it is challenging to devise a suitable LQN that carries a specific entangled state or compute the possible entangled state in a given LQN as the particle and mode number increase. This research presents a mapping process of arbitrary LQNs to graphs, which provides a powerful tool for analyzing and designing LQNs to generate multipartite entanglement. We also introduce the perfect matching diagram (PM diagram), which is a refined directed graph that includes all the essential information on the entanglement generation by an LQN. The PM diagram furnishes rigorous criteria for the entanglement of an LQN and solid guidelines for designing suitable LQNs for the genuine entanglement. Based on the structure of PM diagrams, we compose LQNs for fundamental N-partite genuinely entangled states.

Mice identify subgoal locations through an action-driven mapping process

Mammals instinctively explore and form mental maps of their spatial environments. Models of cognitive mapping in neuroscience mostly depict map-learning as a process of random or biased diffusion. In practice, however, animals explore spaces using structured, purposeful, sensory-guided actions. Here we test the hypothesis that executing specific exploratory actions is a key strategy for building a cognitive map. Previous work has shown that in arenas with obstacles and a shelter, mice spontaneously learn efficient multi-step escape routes by memorizing allocentric subgoal locations. We thus used threat-evoked escape to probe the relationship between ethological exploratory behavior and allocentric spatial memory. Using closed-loop neural manipulations to interrupt running movements during exploration, we found that blocking runs targeting an obstacle edge abolished subgoal learning. In contrast, blocking other movements while sparing edge-directed runs had no effect on memorizing subgoals. Finally, spatial analyses suggest that the decision to use a subgoal during escape takes into account the mouse's starting position relative to the layout of the environment. We conclude that mice use an action-driven learning process to identify subgoals and that these subgoals are then integrated into a map-based planning process. We suggest a conceptual framework for spatial learning that is compatible with the successor representation from reinforcement learning and sensorimotor enactivism from cognitive science.

Mapping of Wound Infection Concepts

Wound infection is a serious health care complication. Standardized clinical terminologies could be leveraged to support the early identification of wound infection. The purpose of this study was to evaluate the representation of wound infection assessment and diagnosis concepts (N=26) in SNOMED CT and ICNP, using a synthesized procedural framework. A total of 13/26 (50%) assessment and diagnosis concepts had exact matches in SNOMED CT and 2/7 (29%) diagnosis concepts had exact matches in ICNP. This study demonstrated that the source concepts were moderately well represented in SNOMED CT and ICNP; however, further work is necessary to increase the representation of diagnostic infection types. The use of the framework facilitated a systematic, transparent, and repeatable mapping process, with opportunity to extend.

A bibliometric analysis of materials research in Indonesian journal using VOSviewer

This study aims to analyze the scope of research on materials using a bibliometric review and data mapping process. Research data on materials were obtained from databases from selected journals in Indonesia. The search is done using a search engine that contains data on all related journal articles. The search process is based on a topic area with titles, keywords, and abstracts in the study material. The mapping process is done using VOSviewer. A total of 60 relevant articles were found. The results showed that the most studied study material was in the 2016-2021 range. Meanwhile, in the field of chemistry, the “acid” term is the most widely discussed material. Among all contributing countries, Indonesia is the largest country with 43 articles. Indonesia also has the most links with other countries, namely 8 links. Through VOSviewer we analyze how many articles have been published about the material and its relation to the topic area. This review can certainly provide a reference point for further research related to materials.

Telerobotic interventions from a distance: an initial experience in 3D phantom mapping

Introduction The current COVID-19 pandemic has fostered several accelerations in “remote” patient care such as video and telephone clinics, as well as multidisciplinary collaborations using online platforms with experts consulting the local teams from a distance. The next logical step would be to also offer remote-controlled interventions which the expert operator not on site, but in support of the local team. This is especially valuable for complex interventions when either patient or expert operator can not be present at the same place. Purpose We aimed to demonstrate that an expert operator located at far distance (Austria) could directly interact with the remote magnetic navigation system in London (UK) whilst mapping a 3D phantom using an electroanatomical mapping system. Method Two experienced operators of the magnetic navigation system were tasked with creating fast anatomic maps (FAM) of the atrial and ventricular chambers of a 3D phantom using remote magnetic navigation in combination with 3D electroanatomical mapping. One was located in the control room of the magnetic catheter lab (UK) and the second one was in Tirol, Austria and connected through a secure remote desktop connection (via high speed fibre optic cable). Using a solid tip magnetic catheter connected to a mechanical drive, all interactions with the system were carried out via the Odyssey platform. Acquisitions for right and left atrium, as well as right and left ventricles plus aorta was compared with regards to mapping duration, map completeness (as judged by the average distance of surface points from 3D CT scan reconstruction), total 3D map volume and need for additional radiation exposure during the mapping process. Results Mapping time and map completeness when performed by the distant operator was not inferior to the local operator and both did not require any additional radiation exposure during the mapping process. Table 1 demonstrates the mean parameters for each chamber, respectively. Figure 1 depicts the matched data for chamber completeness as compared for the LA (green= local operator, pink= distant operator) using a contrast CT scan as the gold standard. Conclusion Telerobotic 3D mapping of a 3D phantom from a distance was equally fast delivered from the control room as compared to an operator located 1200 km away without compromising on map completeness. This demonstrates the feasibility of telerobotic interventions and stress the need for remote collaboration which is especially valuable when travel of patients and/or physician experts is restricted. Funding Acknowledgement Type of funding sources: None. Matched data for aorta

From Individual Cognitive Maps to a Collective Cognitive Map: Prescriptive Guidelines and Measurement of Factors that Could Distort the Mapping Process

In the collective navigation scenario of a trio exploring in a foreign city, we propose a theoretical piece, which is a prescriptive guideline describing rational ways that can enable the trio to form a collective cognitive map. The guidelines center around three stages of exploration: the initial gathering of information, coming together to plan a route in the new city, and executing the exploration plan. Depending on the desires and goals of the group, they might explore together for some or all of the time, splitting up only when their individual goals diverge. The guidelines suggest an optimal plan for these different possibilities. We propose that a collective cognitive map is formed and improved during the entire cognitive navigation process as demonstrated by the trio drawing sketch maps, creating place maps, and revising other people’s place maps. However, multiple factors could distort the navigation process at various points in the proposed prescriptive guidelines. These factors include individual differences (e.g., personal navigation ability, navigation anxiety, and sex), group dynamics (e.g., leaders and followers, group strategies), and the impact of the environment (e.g., language, culture, safety, and spatiality). We describe a thought experiment for testing collective navigation, including the measurement of these factors and the corresponding possible distortions in the collective map caused by these factors. Finally, we discuss future research directions, including using virtual environments and commercial applications. By utilizing our model, people can be flexible in resolving conflicting information during goal planning while still navigating efficiently.

Using intervention mapping to develop ‘ROSE’: an intervention to support peer workers in overdose response settings

Background Peer workers (those with lived/living experience of substance use working in overdose response settings) are at the forefront of overdose response initiatives in British Columbia (BC). Working in these settings can be stressful, with lasting social, mental and emotional impacts. Peer workers have also been disproportionately burdened by the current dual public health crises characterized by the onset of the COVID-19 pandemic and rise in illicit drug overdose deaths. It is therefore critical to develop supports tailored specifically to their realities. Methods We used the six steps outlined in the Intervention Mapping (IM) framework to identify needs of peer workers and design an intervention model to support peer workers in overdose response settings. Results Eight peer-led focus groups were conducted in community settings to identify peer workers’ needs and transcripts were analyzed using interpretive description. The strategies within the intervention model were informed by organizational development theory as well as by lived/living experience of peer workers. The support needs identified by peer workers were categorized into three key themes and these formed the basis of an intervention model titled ‘ROSE’; R stands for Recognition of peer work, O for Organizational support, S for Skill development and E for Everyone. The ROSE model aims to facilitate cultural changes within organizations, leading towards more equitable and just workplaces for peer workers. This, in turn, has the potential for positive socio-ecological impact. Conclusions Centering lived/living experience in the intervention mapping process led us to develop a framework for supporting peer workers in BC. The ROSE model can be used as a baseline for other organizations employing peer workers.