Academic

Context: Motivated by the reduction in operating costs, the use of chatbots to automate customer service has been growing. Chatbots have evolved a lot in terms of technologies used as well as in the different application areas. Problem: As it is a recent technology, there is no tool offers to support chatbot test automation with the possibility of testing context information that happens in the dialogue between the chatbot and the human; the existing tools also lack facilities to integrate different data sources that are used during the tests. Objective: Propose and evaluate a new framework for chatbot testing that considers context information and allows the integration test between different data sources. Method: from the analysis of the lack of existing works reported in the literature, a framework for self-testing of chatbots called OggyBug was proposed, which was used by two chatbots development teams that provided feedback on their use. Results: Construction of the framework called OggyBug that allows implementing, manage and report the results of the execution of automatic tests for chatbots, either through an API or through a web interface, with ease of integrating different sources of information within the automation scripts. After collecting the feedback from the teams that used the framework, we can observe the ease in defining scenarios and repeating the execution of the tests. Conclusion: Testing in context information proved to be important to verify or define the information of the conversation session. The configuration of integration tests proved to be complex, due to the need to configure web services in the chatbot's actions.

Context: Artificial Intelligence (AI) applications appear as one of the main demands for the software industry nowadays; within this context, speech recognition and acoustic scene detection and classification achieve near-human performance. However, performing systematic testing on these applications is challenging and very costly if we follow traditional testing methodologies. In this scenario, Metamorphic Testing presents an efficient approach to ensuring the quality of machine learning-based systems. Objective: analyze techniques and applications of metamorphic testing and propose metamorphic relations to perform verification and validation of acoustic scene classifiers. Method: the use of Design Science Research to provide iterative and incremental research development, through which the results achieved in the first cycle of research are presented. Results: in the first design cycle, the use of two metamorphic relations focused on attributes and samples permutation were adopted to verify and validate 6 learning algorithms in an acoustic scene classification system, wherein one of the applied relations, on the random forest algorithm, presented a violation, leading to prediction errors and 2.34% drop in its accuracy in one of the tests performed. In the second design cycle, three new relations based on acoustic variations were proposed to validate the audio attributes, where in all of them the ZCR attribute was more effective to deal with the proposed variations. Conclusion: At the end of the two cycles, our approach has revealed verification flaws and has also proven effective for validation purposes of the systems under test, allowing developers of acoustic scene classification systems to apply them to their learning components, audio extraction processes, and to the test and training dataset.

The growing number of undergraduated thesis produced at the end of undergraduated courses in Brazil are sometimes available only in physical libraries or have limited digital access, making it difficult for researchers and the general population to access this information. This paper presents the development of a system that uses data analysis and information retrieval techniques capable of providing full-text search, as well as the recommendation of works based on their similarity using the Latent Dirichlet Allocation (LDA) technique. The goal of this solution is to offer higher education institutions in Brazil a platform capable of providing digital access to the documents they produced, enabling the dissemination of scientific production. The tool was validated using data from a real educational institution, and the search and recommendation mechanisms proved to be efficient for their purpose.

Alzheimer’s Disease (AD) is an illness that degenerates an individual’s cognitive functions, leaving them unable to take care of themselves. Even without a definitive cure, AD should be treated with remedies and cognitive enhancement. This article presents an application that assists in the cognitive reinforcement of AD patients through games, supports the medical follow-up of patients, and facilitates the daily exchange of information between the caregiver and the doctor.

The numbers of dengue fever cases in Brazil have grown in recent years, with the arrival of other diseases related to the mosquito that transmits dengue fever (Aedes Aegypt), the situation is very alarming. This paper presents the development of Dengue 360, a tool built on the concepts and processes of business intelligence, which can be used to assist the analysis and dissemination of the epidemiological situation in a region. The goal is to provide information through maps, graphs and other visual artifacts that serve as a basis for decision-making by health managers so that they can create more effective prevention and control policies, as well as facilitate access to information about dengue fever in the region in which they live.