Abstract
In this paper, we evaluate the performance and analyze the explainability of machine learning models boosted by feature selection in predicting COVID-19-positive cases from self-reported information. In essence, this work describes a methodology to identify COVID-19 infections that considers the large amount of information collected by the University of Maryland Global COVID-19 Trends and Impact Survey (UMD-CTIS). More precisely, this methodology performs a feature selection stage based on the recursive feature elimination (RFE) method to reduce the number of input variables without compromising detection accuracy. A tree-based supervised machine learning model is then optimized with the selected features to detect COVID-19-active cases. In contrast to previous approaches that use a limited set of selected symptoms, the proposed approach builds the detection engine considering a broad range of features including self-reported symptoms, local community information, vaccination acceptance, and isolation measures, among others. To implement the methodology, three different supervised classifiers were used: random forests (RF), light gradient boosting (LGB), and extreme gradient boosting (XGB). Based on data collected from the UMD-CTIS, we evaluated the detection performance of the methodology for four countries (Brazil, Canada, Japan, and South Africa) and two periods (2020 and 2021). The proposed approach was assessed in terms of various quality metrics: F1-score, sensitivity, specificity, precision, receiver operating characteristic (ROC), and area under the ROC curve (AUC). This work also shows the normalized daily incidence curves obtained by the proposed approach for the four countries. Finally, we perform an explainability analysis using Shapley values and feature importance to determine the relevance of each feature and the corresponding contribution for each country and each country/year.

Abstract
[No abstract available]

Abstract
Software performance concerns have been attracting research interest at an increasing rate, especially regarding energy performance in non-wired computing devices. In the context of mobile devices, several research works have been devoted to assessing the performance of software and its underlying code. One important contribution of such research efforts is sets of programming guidelines aiming at identifying efficient and inefficient programming practices, and consequently to steer software developers to write performance-friendly code.Despite recent efforts in this direction, it is still almost unfeasible to obtain universal and up-to-date knowledge regarding software and respective source code performance. Namely regarding energy performance, where there has been growing interest in optimizing software energy consumption due to the power restrictions of such devices. There are still many difficulties reported by the community in measuring performance, namely in large-scale validation and replication. The Android ecosystem is a particular example, where the great fragmentation of the platform, the constant evolution of the hardware, the software platform, the development libraries themselves, and the fact that most of the platform tools are integrated into the IDE's GUI, makes it extremely difficult to perform performance studies based on large sets of data/applications. In this paper, we analyze the execution of a diversified corpus of applications of significant magnitude. We analyze the source-code performance of 1322 versions of 215 different Android applications, dynamically executed with over than 27900 tested scenarios, using state-of-the-art black-box testing frameworks with different combinations of GUI inputs. Our empirical analysis allowed to observe that semantic program changes such as adding functionality and repairing bugfixes are the changes more associated with relevant impact on energy performance. Furthermore, we also demonstrate that several coding practices previously identified as energy-greedy do not replicate such behavior in our execution context and can have distinct impacts across several performance indicators: runtime, memory and energy consumption. Some of these practices include some performance issues reported by the Android Lint and Android SDK APIs. We also provide evidence that the evaluated performance indicators have little to no correlation with the performance issues' priority detected by Android Lint. Finally, our results allowed us to demonstrate that there are significant differences in terms of performance between the most used libraries suited for implementing common programming tasks, such as HTTP communication, JSON manipulation, image loading/rendering, among others, providing a set of recommendations to select the most efficient library for each performance indicator. Based on the conclusions drawn and in the extension of the developed work, we also synthesized a set of guidelines that can be used by practitioners to replicate energy studies and build more efficient mobile software.

Abstract
Strategic term re-writing and attribute grammars are two powerful programming techniques widely used in language engineering. The former relies on strategies to apply term re-write rules in defining largescale language transformations, while the latter is suitable to express context-dependent language processing algorithms. These two techniques can be expressed and combined via a powerful navigation abstraction: generic zippers. This results in a concise zipper-based embedding offering the expressiveness of both techniques. In addition, we increase the functionalities of strategic programming, enabling the definition of outwards traversals; i.e. outside the starting position. Such elegant embedding has a severe limitation since it recomputes attribute values. This paper presents a proper and efficient embedding of both techniques. First, attribute values are memoized in the zipper data structure, thus avoiding their re-computation. Moreover, strategic zipper based functions are adapted to access such memoized values. We have hosted our memoized zipper-based embedding of strategic attribute grammars both in the Haskell and Python programming languages. Moreover, we benchmarked the libraries supporting both embedding against the state-of-the-art Haskell-based Strafunski and Scala-based Kiama libraries. The first results show that our Haskell Ztrategic library is very competitive against those two well established libraries.

Abstract
Background: Many programming environments include automated feedback in the form of hints to help novices learn autonomously. Some experimental studies investigated the impact of automated hints in the immediate performance and learning retention in that context. Automated feedback is also becoming a popular research topic in the context of formal specification languages, but so far no experimental studies have been conducted to assess its impact while learning such languages. Objective: We aim to investigate the impact of different types of automated hints while learning a formal specification language, not only in terms of immediate performance and learning retention, but also in the emotional response of the students. Method: We conducted a simple one-factor randomised experiment in 2 sessions involving 85 BSc students majoring in CSE. In the 1st session students were divided in 1 control group and 3 experimental groups, each receiving a different type of hint while learning to specify simple requirements with the Alloy formal specification language. To assess the impact of hints on learning retention, in the 2nd session, 1 week later, students had no hints while formalising requirements. Before and after each session the students answered a standard self-reporting emotional survey to assess their emotional response to the experiment. Results: Of the 3 types of hints considered, only those pointing to the precise location of an error had a positive impact on the immediate performance and none had significant impact in learning retention. Hint availability also causes a significant impact on the emotional response, but no significant emotional impact exists once hints are no longer available (i.e. no deprivation effects were detected). Conclusion: Although none of the evaluated hints had an impact on learning retention, learning a formal specification language with an environment that provides hints with precise error locations seems to contribute to a better overall experience without apparent drawbacks. Further studies are needed to investigate if other kind of feedback, namely hints combined with some sort of self-explanation prompts, can have a positive impact in learning retention. © 2024 Copyright held by the owner/author(s).

Abstract