KRAN: Knowledge Refining Attention Network for Recommendation

Recommender algorithms combining knowledge graph and graph convolutional network are becoming more and more popular recently. Specifically, attributes describing the items to be recommended are often used as additional information. These attributes along with items are highly interconnected, intrinsically forming a Knowledge Graph (KG). These algorithms use KGs as an auxiliary data source to alleviate the negative impact of data sparsity. However, these graph convolutional network based algorithms do not distinguish the importance of different neighbors of entities in the KG, and according to Pareto’s principle, the important neighbors only account for a small proportion. These traditional algorithms can not fully mine the useful information in the KG. To fully release the power of KGs for building recommender systems, we propose in this article KRAN, a Knowledge Refining Attention Network, which can subtly capture the characteristics of the KG and thus boost recommendation performance. We first introduce a traditional attention mechanism into the KG processing, making the knowledge extraction more targeted, and then propose a refining mechanism to improve the traditional attention mechanism to extract the knowledge in the KG more effectively. More precisely, KRAN is designed to use our proposed knowledge-refining attention mechanism to aggregate and obtain the representations of the entities (both attributes and items) in the KG. Our knowledge-refining attention mechanism first measures the relevance between an entity and it’s neighbors in the KG by attention coefficients, and then further refines the attention coefficients using a “richer-get-richer” principle, in order to focus on highly relevant neighbors while eliminating less relevant neighbors for noise reduction. In addition, for the item cold start problem, we propose KRAN-CD, a variant of KRAN, which further incorporates pre-trained KG embeddings to handle cold start items. Experiments show that KRAN and KRAN-CD consistently outperform state-of-the-art baselines across different settings.

Data Sources for Drug Utilization Research in Brazil—DUR-BRA Study

Background: In Brazil, studies that map electronic healthcare databases in order to assess their suitability for use in pharmacoepidemiologic research are lacking. We aimed to identify, catalogue, and characterize Brazilian data sources for Drug Utilization Research (DUR).Methods: The present study is part of the project entitled, “Publicly Available Data Sources for Drug Utilization Research in Latin American (LatAm) Countries.” A network of Brazilian health experts was assembled to map secondary administrative data from healthcare organizations that might provide information related to medication use. A multi-phase approach including internet search of institutional government websites, traditional bibliographic databases, and experts’ input was used for mapping the data sources. The reviewers searched, screened and selected the data sources independently; disagreements were resolved by consensus. Data sources were grouped into the following categories: 1) automated databases; 2) Electronic Medical Records (EMR); 3) national surveys or datasets; 4) adverse event reporting systems; and 5) others. Each data source was characterized by accessibility, geographic granularity, setting, type of data (aggregate or individual-level), and years of coverage. We also searched for publications related to each data source.Results: A total of 62 data sources were identified and screened; 38 met the eligibility criteria for inclusion and were fully characterized. We grouped 23 (60%) as automated databases, four (11%) as adverse event reporting systems, four (11%) as EMRs, three (8%) as national surveys or datasets, and four (11%) as other types. Eighteen (47%) were classified as publicly and conveniently accessible online; providing information at national level. Most of them offered more than 5 years of comprehensive data coverage, and presented data at both the individual and aggregated levels. No information about population coverage was found. Drug coding is not uniform; each data source has its own coding system, depending on the purpose of the data. At least one scientific publication was found for each publicly available data source.Conclusions: There are several types of data sources for DUR in Brazil, but a uniform system for drug classification and data quality evaluation does not exist. The extent of population covered by year is unknown. Our comprehensive and structured inventory reveals a need for full characterization of these data sources.

Improving the Numerical Modelling of In-Situ Rock Bolts Using Axial and Bending Strain Data from Instrumented Bolts

Numerical modelling has become an important tool in the underground rock bolt reinforcement designing process. Numerical modelling provides the advantage of easily and quickly simulating complex underground geometries and mechanisms with sensitivity analyses. However, a numerical model needs to be calibrated using mathematical solutions, lab testing or with actual in-situ observations and measurements (which is the preferred method) before its results can be quantitatively applied to reinforcement design. Instrumented rock bolts provide a useful data source for calibrating in-situ rock bolt models. In this work, procedures have been presented to identify and determine the orientation of structures in the rock mass based on the strains on the instrumented rock bolts. A method to calibrate the rock bolt model with in-situ data is also presented. The results of the presented procedures have been validated with laboratory tests and numerical modelling. The procedures have been applied to create and calibrate an in-situ rock bolt model in FLAC3D and the results are validated using in-situ data.

Bridges and Barriers: An Exploration of Engagements of the Research Community with the OpenStreetMap Community

The academic community frequently engages with OpenStreetMap (OSM) as a data source and research subject, acknowledging its complex and contextual nature. However, existing literature rarely considers the position of academic research in relation to the OSM community. In this paper we explore the extent and nature of engagement between the academic research community and the larger communities in OSM. An analysis of OSM-related publications from 2016 to 2019 and seven interviews conducted with members of one research group engaged in OSM-related research are described. The literature analysis seeks to uncover general engagement patterns while the interviews are used to identify possible causal structures explaining how these patterns may emerge within the context of a specific research group. Results indicate that academic papers generally show few signs of engagement and adopt data-oriented perspectives on the OSM project and product. The interviews expose that more complex perspectives and deeper engagement exist within the research group to which the interviewees belong, e.g., engaging in OSM mapping and direct interactions based on specific points-of-contact in the OSM community. Several conclusions and recommendations emerge, most notably: that every engagement with OSM includes an interpretive act which must be acknowledged and that the academic community should act to triangulate its interpretation of the data and OSM community by diversifying their engagement. This could be achieved through channels such as more direct interactions and inviting members of the OSM community to participate in the design and evaluation of research projects and programmes.

Propuesta metodológica para la caracterización y tipificación de las costas españolas. Aplicación a las costas de Galicia.

There are several coastal classifications. Most of them have been elaborated worldwide using tectonic, climatic, topographic, or oceanographic criteria. Other classifications have been generated on a larger scale and focused on classifying the coastal forms, as cliffs, beaches, estuaries, lagoons, or dune complexes in different places.This project analyzes the types of coastlines, understanding as such each sector that presents certain topographic conditions marked by the elevation and slope, and that was modeled on a concrete type of rock in a specific climatic and marine environment. This paper describes a methodological approach for a detailed scale classification. This approach based on the delimitation of the different coastal systems, exemplified in cliffs and boulder beaches, sandy beaches, and dunes. In this case the shore platforms, marshes and lagoons have not been considered for the technical problems derived from the LiDAR data source, from which the 2 m spatial resolution digital terrain models (DTM) are derived.The first step in the classification was a manual delimitation combining DTMs and orthophotographs. Subsequently, other typification has been carried out through the automatic creation of Coastal Topographic Units (CTU). This index is the combination of two variables: coastal elevation and slope. The possible integration of others, such as orientation or lithology, is possible, but generate a very high number of units and make it difficult to interpret. For this reason, this study did not consider more variables.In this project 30 CTUs was generated, and then selecting only those that appear in the cliffs, boulder beaches, sandy beaches, and coastal dunes sectors. The possibility of viewing one or several CTUs in any sector of the coast allows to know more accurately the conditions of each sector and these categories could be improve the coastal management plans.

THE STRUGGLE OF WOMEN EXISTENCE IN “ISN’T IT ROMANTIC” NOVEL BY WENDY WESSERSTEIN

This study aimed to reveal the struggle of women to gain existence in the novel as a representation of social phenomena. The data source of this research was Isn't It Romantic drama by Wendy Wesserstein. This drama is about women who want to achieve their dreams without the participation of their parents. They want to live without any interference from their parents. To reveal the struggle for existence, the researcher uses the existentialism approach by Simone Beauvoir. Existentialists fight for the nature of human existence, especially for women who have been subordinated to the patriarchal system. The method used in this research is Descriptive qualitative method. The close reading data collection method is effective in tracing data relevant to research variables. The analysis method is carried out critically by using an existentialism approach. The researcher got three main analyses toward the novel, they are: independence over women, authority in making decisions, and lastly, the same existence as a human being.

Facebook as Data: A Primer for Educational Technology Researchers Using Public Internet Data Mining Methods

Digital trace data has helped us understand teaching and learning on social media sites other than Facebook. Moreover, while we know a few things about the educational uses of Facebook, that knowledge has been limited because Facebook has not—until recently—been open to researchers. This paper introduces how Facebook can serve as a data source for educational technology researchers. It provides a walkthrough, from developing research questions and identifying public pages of interest, considering ethics, accessing and downloading historical data through the CrowdTangle platform, and analyzing that data. An example list of pages is provided with code for the open-source statistical software to analyze the data. Future directions for the use of Facebook for research on teaching, learning, and educational systems and their intersection with educational technologies are discussed.

Exploring Bidirectional Performance of Hotel Attributes through Online Reviews Based on Sentiment Analysis and Kano-IPA Model

As people increasingly make hotel booking decisions relying on online reviews, how to effectively improve customer ratings has become a major point for hotel managers. Online reviews serve as a promising data source to enhance service attributes in order to improve online bookings. This paper employs online customer ratings and textual reviews to explore the bidirectional performance (good performance in positive reviews and poor performance in negative reviews) of hotel attributes in terms of four hotel star ratings. Sentiment analysis and a combination of the Kano model and importance-performance analysis (IPA) are applied. Feature extraction and sentiment analysis techniques are used to analyze the bidirectional performance of hotel attributes in terms of four hotel star ratings from 1,090,341 online reviews of hotels in London collected from TripAdvisor.com (accessed on 4 January 2022). In particular, a new sentiment lexicon for hospitality domain is built from numerous online reviews using the PolarityRank algorithm to convert textual reviews into sentiment scores. The Kano-IPA model is applied to explain customers’ rating behaviors and prioritize attributes for improvement. The results provide determinants of high/low customer ratings to different star hotels and suggest that hotel attributes contributing to high/low customer ratings vary across hotel star ratings. In addition, this paper analyzed the Kano categories and priority rankings of six hotel attributes for each star rating of hotels to formulate improvement strategies. Theoretical and practical implications of these results are discussed in the end.

A new global landslide dam database (RAGLAD) and analysis utilizing auxiliary global fluvial datasets

To address the current data and understanding knowledge gap in landslide dam inventories related to geomorphological parameters, a new global-scale landslide dam dataset named River Augmented Global Landslide Dams (RAGLAD) was created. RAGLAD is a collection of landslide dam records from multiple data sources published in various languages and many of these records we have been able to precisely geolocate. In total, 779 landslide dam records were compiled from 34 countries/regions. The spatial distribution, time trend, triggers, and geomorphological characteristic of the landslides and catchments where landslide dams formed are summarized. The relationships between geomorphological characteristics for landslides that form river dams are discussed and compared with those of landslides more generally. Additionally, a potential threshold for landslide dam formation is proposed, based on the relationship of landslide volume to river width. Our findings from our analysis of the value of the use of additional fluvial datasets to augment the database parameters indicate that they can be applied as a reliable supplemental data source, when the landslide dam records were accurately and precisely geolocated, although location precision in smaller river catchment areas can result in some uncertainty at this scale. This newly collected and supplemented dataset will allow the analysis and development of new relationships between landslides located near rivers and their actual propensity to block those particular rivers based on their geomorphology.

Does health service funding go where the need is? A prototype spatial access analysis for new urban contracts data

Background Much of spatial access research measures the proximity to health service locations. We advance this research by focusing on whether health service funding is within walkable reach of neighborhoods with high hardship. This is made possible by a new administrative data source: financial contracts data for those human services that are delivered by nonprofits under contract with the government. Methods In a prototypical spatial access study we apply a classic 2-step floating area catchment model for walkable network access to analyze 2018 data about contracted nonprofit health services funded by the Chicago Department of Public Health (CDPH). CDPH collected the data for the purpose of this study. Results We find that the common container approach of aggregating contract amounts by provider headquarter locations in a given area (ignoring satellite service sites) underestimates the share of funding that goes to Chicago neighborhoods with higher hardship. Once service sites and spatial access are taken into account, a larger share of CDPH funds was found to be within walkable reach of Chicago’s high hardship areas. This was followed by low hardship areas (which could be driven by more headquarter locations there that do serve areas throughout the city). Medium hardship areas trail both, perhaps warranting closer attention. We explore these results by program type and neighborhood with a spatial decision support system developed for the health department. Conclusions The typical approach for analyzing human service contracts based on headquarters is misleading -- in fact, we find that results are reversed when service sites and walkable access are taken into account. This prototype provides an alternative framework for avoiding these misleading results.