This paper presents a systematic literature review (SLR) focused on the implementation of chatbots using Large Language Models (LLMs), aimed at providing insights into the architectures, frameworks, best practices, and evaluation metrics that are shaping the field. By analyzing 39 primary studies, the review addresses six key research questions, exploring common architectures such as client-server and Retrieval-Augmented Generation (RAG), and identifying frequently utilized models, including the GPT family, BERT, and open-source models like LLaMA. The paper evaluates the performance of these models across various domains, emphasizing the impact of fine-tuning, prompt engineering, and embedding techniques on accuracy and domain-specific relevance. Additionally, it highlights the critical evaluation metrics used in LLM-based chatbot systems, including accuracy, user satisfaction, content quality, safety, and efficiency. Ethical considerations, including data governance, bias mitigation, and fairness audits, are also discussed to ensure responsible deployment of LLM chatbots. The review concludes with an exploration of the trade-offs between performance, cost-efficiency, and scalability, providing a comprehensive framework for future research and development of LLM-based chatbot applications.

Fraud detection is a critical challenge in various domains, necessitating accurate and reliable methods to distinguish between legitimate and fraudulent transactions. This work explores the application of copula-based models for anomaly detection in financial forensics. It focuses on their effectiveness in identifying fraudulent activities in a highly imbalanced dataset. Copula models are designed to capture the dependencies between continuous variables, providing a flexible framework for modeling the joint distribution of features. For instance, the variables in a dataset can follow different distributions and the copula is able to model how these variables jointly behave, particularly in extreme cases. In this work, we used a fraud dataset to calculate the copula-based probability of fraud and conditional Gaussian copula. Then, we derive the copula-based Generalized Linear Model (GLM) formula from the conditional copula which is essentially a GLM with probit link and transformed variables when the covariates are continuous. Finally, we compare the performance of these copula-based models with standard methods for predicting a binary variable like GLM with a probit link and logistic regression. Results indicate that copula-based probability and conditional copula formulas offer promising results, particularly in handling complex dependencies, but with a high computational time, while copula-based GLM, when combined with over-sampling, also outperforms traditional methods.

K-Anonymity is a property for the measurement, management, and governance of the data anonymization. Many implementations of k-anonymity have been described in state of the art, but most of them are not practically usable over a large number of attributes in a “Big” dataset, i.e., a dataset drawing from Big Data. To address this significant shortcoming, we introduce and evaluate KGen, an approach to K-anonymity featuring meta-heuristics, specifically, Genetic Algorithms to compute a permutation of the dataset which is both K-anonymized and still usable for further processing, e.g., for private-by-design analytics. KGen promotes such a meta-heuristic approach since it can solve the problem by finding a pseudo-optimal solution in a reasonable time over a considerable load of input. KGen allows the data manager to guarantee a high anonymity level while preserving the usability and preventing loss of information entropy over the data. Differently from other approaches that provide optimal global solutions compatible with smaller datasets, KGen works properly also over Big datasets while still providing a good-enough K-anonymized but still processable dataset. Evaluation results show how our approach can still work efficiently on a real world dataset, provided by Dutch Tax Authority, with 47 attributes (i.e., the columns of the dataset to be anonymized) and over 1.5K+ observations (i.e., the rows of that dataset), as well as on a dataset with 97 attributes and over 3942 observations.

Bias in peer review entails systematic prejudice that prevents accurate and objective assessment of scientific studies. The disparity between referees' opinions on the same paper typically makes it difficult to judge the paper's quality. This article presents a comprehensive study of peer review biases with regard to 2 aspects of referees: the static profiles (factual authority and self‐reported confidence) and the dynamic behavioral context (the temporal ordering of reviews by a single reviewer), exploiting anonymized, real‐world review reports of 2 different international conferences in information systems / computer science. Our work extends conventional bias research by considering multiple biases occurring simultaneously. Our findings show that the referees' static profiles are more dominant in peer review bias when compared to their dynamic behavioral context. Of the static profiles, self‐reported confidence improved both conference fitness and impact‐based bias reductions, while factual authority could only contribute to conference fitness‐based bias reduction. Our results also clearly show that the reliability of referees' judgments varies along their static profiles and is contingent on the temporal interval between 2 consecutive reviews.

Big data poses great challenges for social network analysts in both the data volume and the latent dimensions hidden in the unstructured data. In this paper, we propose a comprehensive knowledge extraction approach for social networks to guide latent dimensions analysis. An improved hypergraph model of social behaviors was then proposed for conveniently conducting multi-faceted analytics in relationships inherent to social media. A real life case study based on Twitter's data was also presented to illustrate the multi-dimensional relations between users based on the categories they co-join and the tweets they co-spread with three orthogonal dimensions of affect analyzed simultaneously, i.e. valence, activation, and intention.

Today's enterprises demand a high degree of compliance of business processes to meet laws and regulations, such as Sarbanes-Oxley and Basel II. Compliance should be enforced during all phases of business process lifecycle, from the phases of analysis and design to deployment, monitoring and evaluation. In this paper, a taxonomy of compliance constraints for business processes is introduced based on the notion of compliance patterns. Patterns facilitate the formal specification of compliance constraints that enable their verification and analysis against business process models. This taxonomy serves as the backbone of the root-cause analysis, which is conducted to reason about and eventually to resolve design-time compliance violations, by providing appropriate guidelines as remedies to alleviate design-time compliance deviations. We have developed and integrated a set of tools to observe and evaluate the applicability of our approach, and experiment with it in case studies.

Service-oriented architectures (SOA) is an emerging approach that addresses the requirements of loosely coupled, standards-based, and protocol- independent distributed computing. Typically business operations running in an SOA comprise a number of invocations of these different components, often in an event-driven or asynchronous fashion that reflects the underlying business process needs. To build an SOA a highly distributable communications and integration backbone is required. This functionality is provided by the Enterprise Service Bus (ESB) that is an integration platform that utilizes Web services standards to support a wide variety of communications patterns over multiple transport protocols and deliver value-added capabilities for SOA applications. This paper reviews technologies and approaches that unify the principles and concepts of SOA with those of event-based programing. The paper also focuses on the ESB and describes a range of functions that are designed to offer a manageable, standards-based SOA backbone that extends middleware functionality throughout by connecting heterogeneous components and systems and offers integration services. Finally, the paper proposes an approach to extend the conventional SOA to cater for essential ESB requirements that include capabilities such as service orchestration, “intelligent” routing, provisioning, integrity and security of message as well as service management. The layers in this extended SOA, in short xSOA, are used to classify research issues and current research activities.

Web services are becoming the prominent paradigm for distributed computing and electronic business. This has raised the opportunity for service providers and application developers to develop value-added services by combining existing Web services. However the current Web service composition solutions, even for the applications developed on the basis of the standard Business Process Execution Language for Web Services (BPEL for short), are rather restricted and inflexible as they lack proper support for generating dynamic compositions and for managing the service composition life cycle. The ReServCom project proposed here aims to remedy this situation by introducing a rule based approach for Web service composition which combines best practices from rule base systems and software engineering to support parameterization, dynamic binding, and flexible service compositions.