Empirical Evaluation of Shallow and Deep Learning Classifiers for Arabic Sentiment Analysis

This work presents a detailed comparison of the performance of deep learning models such as convolutional neural networks, long short-term memory, gated recurrent units, their hybrids, and a selection of shallow learning classifiers for sentiment analysis of Arabic reviews. Additionally, the comparison includes state-of-the-art models such as the transformer architecture and the araBERT pre-trained model. The datasets used in this study are multi-dialect Arabic hotel and book review datasets, which are some of the largest publicly available datasets for Arabic reviews. Results showed deep learning outperforming shallow learning for binary and multi-label classification, in contrast with the results of similar work reported in the literature. This discrepancy in outcome was caused by dataset size as we found it to be proportional to the performance of deep learning models. The performance of deep and shallow learning techniques was analyzed in terms of accuracy and F1 score. The best performing shallow learning technique was Random Forest followed by Decision Tree, and AdaBoost. The deep learning models performed similarly using a default embedding layer, while the transformer model performed best when augmented with araBERT.

Key Issues for Realizing Open Ecoacoustic Monitoring in Australia

Many organizations are attempting to scale ecoacoustic monitoring for conservation but are hampered at the stages of data management and analysis. We reviewed current ecoacoustic hardware, software, and standards, and conducted workshops with 23 participants across 10 organizations in Australia to learn about their current practices, and to identify key trends and challenges in their use of ecoacoustics data. We found no existing metadata schemas that contain enough ecoacoustics terms for current practice, and no standard approaches to annotation. There was a strong need for free acoustics data storage, discoverable learning resources, and interoperability with other ecological modeling tools. In parallel, there were tensions regarding intellectual property management, and siloed approaches to studying species within organizations across different regions and between organizations doing similar work. This research contributes directly to the development of an open ecoacoustics platform to enable the sharing of data, analyses, and tools for environmental conservation.

The Impact of Resistance to Change on the Implementation of Quality Management System in the Ministry of Education (General Directorate of Education in South Batinah Governorate as a Model)

This study is investigating the reality of resistance to change in the light of Quality Management System (QMS) implementation in the Ministry of Education (South Batinah Directorate as a model of the study). It tries to answer some questions related to the main factors that lead to resistance to change with correlations of gender, years of experience and educational level. The method of collecting data of this study was conducting quantitatively through an electronic questionnaire including 59 participants of directors in different administrative level. The data has been analyzed statistically through SPSS. The result shows that the performance of the employees was impacted through the lack of awareness of the QMS requirements. Although, the all four factors recorded close level of resistance, the cognitive rigidity factor recorded the highest factor that lead to resistance to change. The study results can be generalized to other directorates in the Ministry of Education because the similar work environment. This study can be used to make some very crucial amendments in the future in managing QMS in the organization.

SIMULATION OF DESIGN VARIABLES EFFECT ON PERFORMANCE OF A COMMON BEANS (Phaseolus vulgaris L) PORTABLE THRESHER

In Kenya, threshing of common beans is mainly by traditional method using sticks and animal tramping, which are slow, inefficient and tedious. Consequently, there is a need to develop portable threshers locally available in the market for small and medium-scale farmers. The objective of this study was to simulate design variables effect on the performance of a common beans portable thresher. Sizing of design variables and parameters was key in development of bean thresher. This could be achieved by costly experiments or use of prediction mathematical model equation. The later method was used by developing mathematical models from combination of Buckingham pi theorem and reference to other similar work in literature. The predicting equation for power requirement, grain losses, grain damages, efficiency and throughput capacity were developed and validated using experimental thresher from the same study. The results showed that there was a positive correlation with R2 of 0.9. Based on actual data and 10% absolute residual error interval, the prediction performance of the developed models were above 77%. The results noted that increase in cylinder peripheral speed of the pegs resulted into increase in power requirement, bean grains damages, threshing efficiency and throughput capacity. Also increase in effective cylinder diameter caused increase in threshing efficiency and grain damages.

Faktor-Faktor yang Berpengaruh dalam Pemilihan Subkontraktor dan Pengaruhnya Terhadap Waktu Pelaksanaan

Prime contractors rely heavily on subcontractor services to lower costs and increase efficiency on construction projects. Subcontractors perform certain tasks that the main contractor cannot perform efficiently. To get a competent subcontractor, it is necessary to hold the selection of subcontractors. The selection of subcontractors becomes very important in keeping pace with the growth of the construction industry, so the main contractor as the construction executor requires a subcontractor or specialist contractor for certain jobs that require specialized expertise. This study was conducted by reviewing the findings of several related scientific journals, so that the factors that influence the selection of subcontractors and the most influential factors are the experience of doing similar work. In addition, it also found its effect on the time of implementation of the project.

Still Standing: Innocence work in England and Wales

This article examines the two categories that have evolved in the literature concerning Innocence Projects; the pedagogical value of innocence work and the problems with associating the term innocence with the English criminal justice process. This research draws upon a study undertaken in 2017 by the Innocence Project London (unpublished) and another in 2020. Both studies sought to understand the extent to which organisations are undertaking innocence work in England and Wales. This research is written from the perspective of the Directors of both the Innocence Project London and Manchester Innocence Project, and as a result, the projects are discussed at length in various sections. An effort has been made however, to discuss other organisations that undertake similar work in various parts of this article.

Translational Science Education Through Citizen Science

Guided by the six elements of Translational Ecology (TE; i.e., decision-framing, collaboration, engagement, commitment, process, and communication), we showcase the first explicit example of a Translational Science Education (TSE) effort in the coastal redwood ecosystem of Humboldt County, CA. Using iNaturalist, a flexible and free citizen science/crowdsourcing app, we worked with students from grade school through college, and their teachers and community, to generate species lists for comparison among 19 school and non-profit locations spanning a range of urbanization. Importantly, this TSE effort resulted in both learning and data generation, highlighting the ability of a TSE framework to connect and benefit both students and researchers. Our data showed that, regardless of the age of the observers, holding organized BioBlitzes added substantially more species to local biodiversity lists than would have been generated without them. In support of current ecological theory, these data showed an urbanization gradient among sites, with rural sites containing fewer non-native species than urban ones. On the education side, qualitative assessments revealed students and educators remained engaged throughout the project. Future projects would also benefit by establishing quantifiable metrics for assessing student learning from project conception. Throughout the project, the fundamentals of TE were followed with repeated interactions and shared objectives developed over time within trusted community relationships. Such positive human interactions can lead new naturalists to think of themselves as champions of their local biodiversity (i.e., as land stewards). We anticipate that such newly empowered and locally expert naturalists will remain committed to land stewardship in perpetuity and that other scientists and educators are inspired to conduct similar work.

Clustering as feature selection method in spam classification: uncovering sick-leave sellers

PurposeThis paper aims to propose a novel way of using textual clustering as a feature selection method. It is applied to identify the most important keywords in the profile classification. The method is demonstrated through the problem of sick-leave promoters on Twitter.Design/methodology/approachFour machine learning classifiers were used on a total of 35,578 tweets posted on Twitter. The data were manually labeled into two categories: promoter and nonpromoter. Classification performance was compared when the proposed clustering feature selection approach and the standard feature selection were applied.FindingsRadom forest achieved the highest accuracy of 95.91% higher than similar work compared. Furthermore, using clustering as a feature selection method improved the Sensitivity of the model from 73.83% to 98.79%. Sensitivity (recall) is the most important measure of classifier performance when detecting promoters’ accounts that have spam-like behavior.Research limitations/implicationsThe method applied is novel, more testing is needed in other datasets before generalizing its results.Practical implicationsThe model applied can be used by Saudi authorities to report on the accounts that sell sick-leaves online.Originality/valueThe research is proposing a new way textual clustering can be used in feature selection.

Congregations as Health Connectors – Addressing Health and Social Needs of Neighbors Through Conversations, Not Surveys

Background and Hypothesis: Social determinants of health (SDOH) directly affect health outcomes and indirectly limit access to resources needed to maintain individual health. In an effort to address the negative impacts of SDOH on the urban communities of Indianapolis, four congregations have employed Site Connectors to directly form relationships with neighbors, learn about their health journey, and connect them to resources addressing expressed needs. It is our hypothesis that through research of similar models and discussion with community partners, an optimized model for fostering relationships and assessing the health and social needs of neighbors can be developed for use by the Site Connectors. Project Methods: A search was performed for examples of health and social needs assessments utilized by established care providers, and thirteen were identified. The items within these assessments were then organized into six groups based on SDOH topic (ie. Housing, Transportation, etc.). Additionally, six interviews with community partners performing similar work were conducted utilizing a fixed set of questions. Results: It was determined that the best format for our assessment would not be a survey, as in the example assessments, but rather a visual aid resembling a concept map. This model lends itself more to the nature of relationship-building by guiding Connector-Neighbor conversations rather than dictating them, with three starter questions at the center and six offshoots covering each of the SDOH topics. A post-encounter checklist was also developed for Connectors to retroactively record priority items from their conversations. Potential Impact: It is yet to be determined whether our model will be useful in practice, as the Connectors begin their work in August. However, it is our hope that we have developed a novel format for assessing needs that more holistically addresses the impacts of SDOH through respecting the vulnerability and energy required for relationship-building.

Logistics Work, Ergonomics and Social Sustainability: Empirical Musculoskeletal System Strain Assessment in Retail Intralogistics

Background: A large proportion of logistics jobs still rely on manual labor and therefore place a physical strain on employees. This includes the handling of heavy goods and physiologically unfavorable postures. Such issues pose a risk for employee health and work capability. This article provides a detailed empirical analysis and a decision process structure for the allocation of ergonomic measures in warehousing and intralogistics processes. Methods: The methodological basis is a load assessment of the musculoskeletal system in retail intralogistics. Based on the established measurements systems CUELA and OWAS, the specific loads on employees are assessed for four typical logistics workplace settings. These are combined with standards for efficient decision rules regarding contracting and developing ergonomic improvements. Results: The results suggest an increased risk of long-term low back injury for the selected four standard work situations in warehousing and likely apply to similar work environments in logistics. Using measures, posture descriptions, and international standards, we show how already few threshold values serve as sufficient conditions to decide if ergonomic interventions are required. Conclusions: The specific contribution is characterized by the combination of literature review results, empirical results, and the identification and discussion of specific mitigation measures. These elements are focused on the highly relevant ergonomic situation of logistics workers and present a unique contribution towards the knowledge base in this field due to the multi-perspective approach.