Abstract
The main objectives of this chapter are to provide an overview of chatbot personality dimensions and to analyze the expected impacts on user behavior. To accomplish these objectives, the chapter provides a detailed review of the main contributions in the literature regarding this topic. It highlights the chatbot personality characteristics that are expected to foster user satisfaction, trust, loyalty, and engagement. This information is useful for both practitioners and researchers, particularly related to customer service, as it provides clear guidance on what characteristics to incorporate in chatbots and on what factors need to be further studied in the future.

Abstract
Purpose: Responsible innovation assessment tools (RIATs) are key instruments that can help organizations, associations and individuals measure responsible innovation. Accordingly, this study aims to review the current status of research on responsible innovation and, in particular, of studies that either present the relevance of RIATs or provide empirical evidence of their adoption. Design/methodology/approach: A systematic literature review is conducted to identify and review how RIATs are being addressed in academic research and the applications that are proposed. A systematic process is implemented using the Web of Science and Scopus bibliographic databases, aiming not only to summarize existing studies, but also to include a perspective on gaps and future research. Findings: A total of 119 publications were identified and included in the review process. The study identifies that RIATs have attracted growing interest from the scientific community, with a greater predominance of studies involving qualitative and mixed methods. A well-balanced mix of conceptual and exploratory studies is also registered, with a greater predominance of analysis of RIATs application domains in the past years, with greater incidence in the finance, water, energy, construction, manufacturing and health sectors. Originality/value: This study is pioneering in identifying 16 dimensions and 60 sub-dimensions for measuring responsible innovation. It also suggests the need to include multidimensional perspectives and individuals with interdisciplinary competencies in this process.

Abstract
The lack of interpretability of Deep Learning models hinders their deployment in clinical contexts. Case-based explanations can be used to justify these models' decisions and improve their trustworthiness. However, providing medical cases as explanations may threaten the privacy of patients. We propose a generative adversarial network to disentangle identity and medical features from images. Using this network, we can alter the identity of an image to anonymize it while preserving relevant explanatory features. As a proof of concept, we apply the proposed model to biometric and medical datasets, demonstrating its capacity to anonymize medical images while preserving explanatory evidence and a reasonable level of intelligibility. Finally, we demonstrate that the model is inherently capable of generating counterfactual explanations.

Abstract
The replacement of fossil fuel power plants by variable renewable energy sources is reducing the flexibility of the energy system, which puts at risk its security. Exploiting the flexibility of distributed multi-energy resources through aggregators presents a solution for this problem. In this context, this paper presents a new hierarchical model predictive control framework to assist multi-energy aggregators in the network-secure delivery of multi-energy services traded in electricity, natural gas, green hydrogen, and carbon markets. This work builds upon and complements a previous work from the same authors related to bidding strategies for day-ahead markets - it closes the cycle of aggregators' participation in multi-energy markets, i.e., day-ahead bidding and real-time activation of flexibility services. This new model predictive control framework uses the alternating direction method of multipliers on a rolling horizon to negotiate the network-secure delivery of multi-energy services between aggregators and distribution system operators of electricity, gas, and heat networks. We used the new model predictive control framework to conduct two studies. In the first study, we found that considering multi-energy network constraints at both day-ahead and real-time optimization stages produces the most cost-effective and reliable solution to aggregators, outperforming state-of-the-art approaches in terms of cost and network security. In the second study, we found that the adoption of a green hydrogen policy by multi-energy aggregators can reduce their consumption of natural gas and respective CO2 emissions significantly if carbon and green hydrogen prices are competitive.& COPY; 2023 Elsevier Ltd. All rights reserved.

Abstract
Quality control inspection systems are crucial and a key factor in maintaining and ensuring the integrity of any product. The quality inspection task is a repetitive task, when performed by operators only, it can be slow and susceptible to failures due to the lack of attention and fatigue. This work focuses on the inspection of parts made of high-pressure diecast aluminum for components of the automotive industry. In the present case study, last year, 18240 parts needed to be reinspected, requiring approximately 96 hours, a time that could be spent on other tasks. This article performs a comparison of four deep learning models: Faster R-CNN, RetinaNet, YOLOv7, and YOLOv7-tiny, to find out which one is more suited to perform the quality inspection task of detecting metal filings on casting aluminum parts. As for this use-case the prototype must be highly intolerant to False Negatives, that is, the part being defective and passing undetected, Faster R-CNN was considered the bestperforming model based on a Recall value of 96.00%.

Abstract
Fires in large buildings can have tragic consequences, including the loss of human lives. Despite the advancements in building construction and fire safety technologies, the unpredictable nature of fires, particularly in large buildings, remains an enormous challenge. Acknowledging the paramount importance of prioritising human safety, the academic community has been focusing consistently on enhancing the efficiency of building evacuation. While previous studies have integrated evacuation simulation models, aiding in aspects such as the design of evacuation routes and emergency signalling, modelling human behaviour during a fire emergency remains challenging due to cognitive complexities. Moreover, behavioural differences from country to country add another layer of complexity, hindering the creation of a universal behaviour model. Instead of centring on modelling the occupant behaviour, this paper proposes an innovative approach aimed at enhancing the occupants' behaviour predictability by providing real-time information to the occupants regarding the most suitable evacuation routes. The proposed models use a building's environmental conditions to generate contextual information, aiding in developing solutions to make the occupants' behaviour more predictable by providing them with real-time information on the most appropriate and efficient evacuation routes at each moment, guiding the occupants to safety during a fire emergency. The models were incorporated into a context-aware recommender system for testing purposes. The simulation results indicate that such a system, coupled with hazard and congestion models, positively influences the occupants' behaviour, fostering faster adaptation to the environmental conditions and ultimately enhancing the efficiency of building evacuations.