Evaluating large-language-model chatbots to engage communities in large-scale design projects

Large-scale urban development projects are a significant format of urban expansion and renewal across the globe. As generators of governance innovation and indicators of the future city in each urban context, large-scale development projects have been interpreted within frameworks of ‘variegations’ of wider circulating processes, such as neoliberalisation or financialisation. However, such projects often entail significant state support and investment, are strongly linked to a wide variety of transnational investors and developers and are frequently highly contested in their local environments. Thus, each project comes to fruition in a distinctive regulatory context, often as an exception to the norm, and each emerges through complex interactions over a long period of time amongst an array of actors. We therefore seek to broaden the discussion from an analytical focus on variegated globalised processes to consider three large-scale urban development projects (in Shanghai, Johannesburg and London) as distinctive (transcalar) territorialisations. Using an innovative comparative approach, we outline the grounds for a systematic analytical conversation across mega-urban development projects in very different contexts. Initially, comparability rests on the shared features of large-scale developments – that they are multi-jurisdictional, involve long time scales and bring significant financing challenges. Comparing three development projects, we are able to interrogate, rather than take for granted, how a range of wider processes, circulating practices, transcalar actors and territorial regulatory formations composed specific urban outcomes in each case. Thinking across these diverse cases provides grounds for rebuilding understandings of urban development politics.

Governance processes and image management strategies in large-scale urban development projects are exposed to a range of contextual and internal actor-network-related influences. These relations are complex and, due the long realization time of these projects, cannot be entirely anticipated by management strategies. This research investigates how organizations manage these complexities and uncertainties, what strategies they employ, and how these strategies adapt over time. The research analyzes the empirical case of the Amsterdam Zuidas development through a series of interviews conducted with key stakeholder group representatives and an extensive study of the development visions at different milestones of the development. The study relates these findings to the theoretical framework of Henry Mintzberg on strategy formation and finds that large-scale urban development projects need to employ overlapping strategies and engage in adaptive learning to balance development ambitions with the internal and external influences affecting the strategies.

Improving the climate resilience of urban areas critically depends on the integration of climate adaptation measures, i.e. mainstreaming, into regular construction practices. As research has largely focused on public sector adaptation, the mainstreaming of adaptation into private sector projects remains poorly understood. The aims of this study are twofold. First, we examine what drives private developers and investors to mainstream adaptation into large-scale urban development projects. Second, we explore what policy instruments municipalities can employ to stimulate private sector mainstreaming. Our theoretical lens combines insights from the literature on mainstreaming, sustainable building drivers and policy instruments. These concepts are used to guide our analysis of four urban development projects and an interview study in the Netherlands, a densely populated delta country which is rather vulnerable to the impacts of climate change. Our results show that private developers and investors seldom explicitly include adaptation measures into their development projects. An important impediment is the perceived absence of direct monetary benefits. If adaptation measures are implemented, they are often realized as a side-effect of creating a high-quality living environment or because private actors expect other professional benefits, such as corporate image enhancement or development of know-how. To stimulate private sector mainstreaming, Dutch municipalities already use a mix of policy instruments that might be a source of inspiration for other countries. Yet, especially the way in which enforcement and incentives are applied is not always effective. Key policy insights Despite the private sector’s growing awareness about the need for and importance of climate change adaptation in the Netherlands, adaptation is still seldom explicitly included in large-scale urban development projects. Municipalities should invest in policy instruments that target consumers. Communication, education and incentives can be used to raise consumer awareness and consequently demand for climate-adaptive properties. Municipalities should collaborate with the private sector to develop clear, uniform and feasible adaptation requirements. Municipalities should actively participate in urban development projects, i.e. co-developing with the private sector. This way, private sector drivers and policy instruments can strengthen each other to pave the way for future-proof and climate-resilient urban environments.

The literature on large-scale urban development projects often primarily addresses drastic failures and their underlying causes. Recently, however, success factors have also received increasing attention. From both perspectives, management approaches, participation logics and political strategies are prominent topics in this context. However, the symbolic dimension of large urban development projects is rarely considered. This is somewhat surprising, as symbolic meaning is considered key to urban development in many contexts. We explore this dimension with two cases of urban entrepreneurial development projects, the Novartis Campus in Basel (Switzerland) and the Siemens Campus in Erlangen (Germany). Our empirical study relies on thematic press analyses. We reflect on the postulate that a “fit” between urban symbolism and societal expectations is a crucial determinant of smooth implementation in large-scale urban development projects in company towns. In both case studies, urban integration, architecture and design are of great relevance. These “soft” factors in planning and implementation suggest that the outcomes are not solely dependent on technical professionalism. Instead, the appropriate symbolism within the urban context and the associated project investment emerge as critical factors.

Large-scale urban development projects have become the main vehicle by which targeted interventions for place- and scale-specific state initiatives unfold, triggering a series of processes that are associated with the rescaling of state space. This study aims to understand the place-specific conditions, pathways and strategies whereby states’ spatial and scalar restructuring takes place in urban development projects (UDPs) within China’s political economic contexts, and in turn how UDPs act as critical lenses for viewing the changing nature of state spatial strategy in China, through a case study of the Lingang New Town in Shanghai. The major findings are: UDPs in China function as tools not just for land value extraction but also for scale-making to cater to the state’s pursuits of place-specific competitiveness in the global economy; the restructuring of the state apparatus and regulatory frameworks is driven by place-specific tensions and crises triggered by earlier rounds of state rescaling; the state chose state-agents rather than market-agents to reinforce its power, and thus the state space expands through development of UDPs; through developing UDPs, China’s spatial strategies have explicitly and officially engaged with the discourse of globalisation while implicitly engaging with geographically variegated practices of neoliberalisation. At the theoretical level, this article facilitates an investigation of how China’s state spatial strategy, characterised by geographically and chronologically variegated engagement with neoliberalism, is actualised through UDPs. It also demonstrates how, despite being a socialist polity, pragmatic market measures and downscaling are taken as transient measures in times of need.

The paper explores the issue of new urban development areas from two specific perspectives: on the one hand, rather than concentrating on housing, we address the question of science and research, in particular university locations and science parks, as a central guiding principle for urban expansion. On the other hand, the paper focuses on the analysis of urban management and governance practices and, more specifically, the disjoining of large projects from their common urban planning context. Emphasis is put on the fact that such undertakings are defined as ‘projects’ and that they are subordinated to a specific management approach. Amid debates concerning large-scale urban development projects and urban governance, we develop the thesis that the risk for projects to unfold as a sort of ‘foreign matter’ in the urban realm increases as the degree to which they are subject to proven planning processes and regulatory practices diminishes. This argument will be empirically illustrated with Belval, the science city in the south of Luxembourg, which is developed ever since 2003 and whose progress is critically assessed here. The general conclusions include planning requirements for dealing with new large-scale development projects.

This book is structured around the view that large-scale Urban Development Projects (UDPs) are the embodiment of processes that operate in and over a variety of scales, from the local to the global. These urban interventions are as it were ‘grains of sand’, albeit of a particularly rough-edged variety, that hold the world’s complex socio-spatial and political-economic configuration in their crystalline structure. They are part of a process of profound restructuring that over the past few decades has transformed the urban landscape in unexpected, perplexing, and often disturbing ways.

Although physical activity can mitigate disease trajectories and improve and sustain mental health, many people have become less physically active during the COVID-19 pandemic. Personal information technology, such as activity trackers and chatbots, can technically converse with people and possibly enhance their autonomous motivation to engage in physical activity. The literature on behavior change techniques (BCTs) and self-determination theory (SDT) contains promising insights that can be leveraged in the design of these technologies; however, it remains unclear how this can be achieved. This study aimed to evaluate the feasibility of a chatbot system that improves the user's autonomous motivation for walking based on BCTs and SDT. First, we aimed to develop and evaluate various versions of a chatbot system based on promising BCTs. Second, we aimed to evaluate whether the use of the system improves the autonomous motivation for walking and the associated factors of need satisfaction. Third, we explored the support for the theoretical mechanism and effectiveness of various BCT implementations. We developed a chatbot system using the mobile apps Telegram (Telegram Messenger Inc) and Google Fit (Google LLC). We implemented 12 versions of this system, which differed in 3 BCTs: goal setting, experimenting, and action planning. We then conducted a feasibility study with 102 participants who used this system over the course of 3 weeks, by conversing with a chatbot and completing questionnaires, capturing their perceived app support, need satisfaction, physical activity levels, and motivation. The use of the chatbot systems was satisfactory, and on average, its users reported increases in autonomous motivation for walking. The dropout rate was low. Although approximately half of the participants indicated that they would have preferred to interact with a human instead of the chatbot, 46.1% (47/102) of the participants stated that the chatbot helped them become more active, and 42.2% (43/102) of the participants decided to continue using the chatbot for an additional week. Furthermore, the majority thought that a more advanced chatbot could be very helpful. The motivation was associated with the satisfaction of the needs of competence and autonomy, and need satisfaction, in turn, was associated with the perceived system support, providing support for SDT underpinnings. However, no substantial differences were found across different BCT implementations. The results provide evidence that chatbot systems are a feasible means to increase autonomous motivation for physical activity. We found support for SDT as a basis for the design, laying a foundation for larger studies to confirm the effectiveness of the selected BCTs within chatbot systems, explore a wider range of BCTs, and help the development of guidelines for the design of interactive technology that helps users achieve long-term health benefits.

One technology that improved humans’ lifestyle is a Chatbot System, an AI-based system that conducts people’s conversations. Chatbots are used in a wide range of applications-assistive technologies, customer service, home automation, education, medical bots, entertainment, etc. Such technology could be beneficial to differently-abled for teaching, assistance, etc. But when it comes to people with a slight speech disorder or autism, available chatbot systems aren’t very effective. This paper investigates the existing speech recognition APIs based on WER and CER and tries to improve results by adding a personalized layer for the user. This chatbot system can be embedded with existing technologies-domestic robots, smart mirrors, home automation, medical applications, etc. It will open these technologies to a wide range of audiences. The proposed Chatbot will use the existing speech recognition API and improve the results based on the above performance measures.

Effectiveness of designing a knowledge-based artificial intelligence chatbot system into a nursing training program: A quasi-experimental design

As powerful landmarks to steer local and regional development, strategic projects are often linked with strategic spatial plans. However, the key question remains as to what extent strategic urban projects and plans can be regarded as aligned. By building on previous international comparative research, we identify five main conditions assumed to enable, in combination, the alignment between strategic projects and plans. By adopting a qualitative, multi-method empirical strategy (interviews, site visits, online questionnaire, additional literature) and by performing fuzzy-set Qualitative Comparative Analysis (fs-QCA), we compare 38 European large-scale urban development projects (lsUDPs) and assess which combinations of conditions support concordance of the projects with strategic spatial plans (SSPs). Our analysis shows that there are five pathways, factored out into two main patterns, enabling alignment. Substantial variation in our cases appears to be captured by: (i) considerable involvement of the national state combined with (inter)national private actors and (ii) a considerable involvement of private actors combined with international external events.

This work presents an audio-visual interactive chatbot (AVIN-Chat) system that allows users to have face-to-face conversations with 3D avatars in real-time. Compared to the previous chatbot services, which provide text-only or speech-only communications, the proposed AVIN-Chat can offer audio-visual communications providing users with a superior experience quality. In addition, the proposed AVIN-Chat emotionally speaks and expresses according to the user's emotional state. Thus, it enables users to establish a strong bond with the chatbot system, increasing the user's immersion. Through user subjective tests, it is demonstrated that the proposed system provides users with a higher sense of immersion than previous chatbot systems. The demonstration video is available at https://www.youtube.com/watch?v=Z74uIV9k7_k.

The natural dialog system, Chatbot, plays an important role in business domains by properly answering customer queries. In the pattern matching approach of Chatbot development, the user input is matched with a predefined set of responses. The machine learning approach of Chatbot development uses the principles of natural language processing to learn from conversational content. This study focuses on the performance measurement of pattern-based and machine learning-based Chatbot systems. As per the user point of view, performance measurement parameters are the ability to answer quickly, accurately, and comprehensively; to understand questions clearly; user friendliness; personalization options; ethics followed; and ability to process user feedback. The comprehensiveness of the knowledge base, robustness to handle unexpected input, scalability, and interoperability are some of the parameters considered to evaluate the Chatbot system by expert point of view. In this study, the specially designed Chatbot Usability Questionnaire is used to measure the performance of the implemented Chatbot systems.

The high prevalence of mental health issues and limited access to professional information and support have driven the search for innovative solutions. One promising approach is the development of chatbot systems that provide quick and accessible mental health information. This study evaluates the performance of the Bidirectional Long Short-Term Memory (BiLSTM) algorithm in identifying and classifying user inputs within a mental health chatbot system. BiLSTM is chosen for its ability to process sequential data in both directions, allowing it to capture context more effectively than unidirectional models and better understand user intent. Deep learning methods like BiLSTM have also demonstrated higher accuracy compared to traditional machine learning models. This study focuses solely on BiLSTM to evaluate its performance in this context. The mental health dataset used in this study was sourced from previous research published on the GitHub platform and contains 100 classes of mental health-related questions and statements. This dataset was used to train the BiLSTM model to recognize user intent and generate relevant responses. The model achieved 98% accuracy on the training data. For evaluation on the test set, a confusion matrix was used, yielding an accuracy of 82%. The chatbot is implemented as a web-based application using a Python framework and is designed to provide users with insights and knowledge through text-based interactions. These results highlight the potential of the BiLSTM-based chatbot system to deliver effective and efficient mental health information services

Artificial Intelligence (AI) based Chatbot is a moderately new technology in the world. AI and Natural Language Processing (NLP) empowers a Chatbot to converse like a human being. Chatbots have become popular recently as they diminish human efforts by automating various tasks. AI-based Chatbot learns from the previous discussion and generates an appropriate response or action for the input given by the user. In the proposed research work we designed AI-based Chatbot system using the Sequence to Sequence (Seq2Seq) model. This system uses a Gated Recurrent Unit (GRU) for encoder and decoder. In the proposed model the GRU encoder accepts a query from the user. The GRU encoder uses an attention mechanism to consider only relevant information and convert it into the context vector form. A context vector is another input to the GRU decoder. The GRU decoder generates a response using the Beam search algorithm. The research work uses Cornell Movie Dialogue Corpus to train the proposed interactive Chatbot system. It is observed that the proposed model with the combination of GRU and Beam search gives better accuracy with the minimum loss for testing data. These experimental results are better than existing approaches that use LSTM Seq2Seq models to train Chatbot systems.