We study human-chatbot collaborative conversation systems that enable humans to leverage AI chatbot outputs during an online conversation with others. We evaluate response quality in two collaborative systems and compare them with human-only and chatbot-only settings. Both collaborative systems present AI chatbot results as suggestions but encourage the synthesis of human and chatbot responses to different extents. We also examine the influence of chatbot choices, including both retrieval-based and generation-based methods, and the number of suggestions on collaborative systems. Experimental results show that our collaborative systems can significantly improve the efficiency to formulate a response and improve its quality compared with a human-only system while sacrificing the fluency and humanness of the messages. Compared with a chatbot, collaborative systems can provide answers that are more fluent, human-like, and informative. We also found that the retrieval-based chatbots perform better than the generation-based one from all aspects. The optimal number of chatbot suggestions is one, and showing more suggestions has reduced user efficiency. / Master of Science / Artificial Intelligence (AI) systems have become remarkably interactive and accurate with them becoming an integral part of our life. The increasing use of personal assistants like Siri and the application of AI in important real-world tasks such as medical imaging and diagnosis show that AI can perform as good as trained human experts. Organizations today are expanding at a rapid rate and need to service millions of customers concurrently to remain competitive in the market. With the recent success of AI chatbots, the collaboration of Human and AI to augment customer service management is one of the most sought out solutions to this requirement. A service flow where virtual agents and people work together can be a boon to the industry by making the human agents smarter with a bot "whispering" in their ears. We present the design of various collaborative systems we have developed and discuss the improvements in response efficiency and quality due to them in multiple online user experiments. The results of this study can be used to improve conversational chat systems that assist human agents to improve their response time and quality and identify features of the AI agent that are most beneficial for improving the conversation.

No description available.

In today's world, Artificial Intelligence (AI) has seamlessly integrated into ourdaily lives without us even realising it. We witness AI-driven innovations allaround us, subtly enhancing our routines and interactions. Ranging from Siri, Alexa, to Google Assistant, voice assistants have become prime examples of AI technology, assisting us with simple tasks and responding to our inquiries. As these once futuristic ideas have now become an indispensable part of our everyday reality, they also become relevant for the field of GUI. This thesis explores the views of stakeholders, such as designers, alumni, students and teachers, on the inevitable implementation of artificial intelligence(AI) into the graphical user interface (GUI) development. It aims to provide understanding on stakeholders thoughts and needs with the focus on two research questions: RQ1: What are the viewpoints of design stakeholders regarding using Artificial Intelligence tools into GUI development? And RQ2: What characteristics should be considered in including AI in GUI development? To collect data, the thesis will use A/B testing and question sessions. In the A/B testing, participants will watch two videos, one showing how to digitise asketch using an AI tool (Uizard) and the other showing how to do the samething using a traditional GUI design tool (Figma). Afterwards, the participants will answer questions about their experience regarding the two different ways to digitise a sketch. The study highlighted a generally positive outlook among the participating stakeholders. Students and alumni expressed more enthusiasm whereas experienced professionals and teachers were cautious yet open to AI integration. Concerns werevoiced regarding potential drawbacks, including limited control and issues of over-reliance. The findings underscored AI's potential to streamline tasks but also emphasised the need for manual intervention and raised questions about maintaining control and creative freedom. We hope this work serves as a valuable starting point for other researchers interested in exploring this topic.

Graphic design has throughout history been affected by disruptive technologies, every technical advancement within the industry has led to a need for adapting in order to stay relevant. The biggest disruptor within the industry today is without doubt artificial intelligence. AI has already changed the workflow and design processes, and it is evident that AI is here to stay. This emerging technology has the potential to further revolutionise the creative process by providing designers with new tools and techniques to enhance efficiency and improve quality of their outputs. However, many uncertainties and concerns persist regarding how AI will impact the design profession and the space for human creative abilities. This essay aims to contribute to the ongoing discourse surrounding the role of AI in the creative industry through a thematic literature review. The findings of this study disproves the notion that AI poses a threat to creativity and emphasises the perpetual need for human expertise in a design process. This research underscores the value of human creativity and highlights how AI can complement and empower designers rather than replace them.

Identifying individuals in historical photographs is important for preserving material culture, correcting historical records, and adding economic value. Historians, antiques dealers, and collectors often rely on manual, time-consuming approaches. While Artificial Intelligence (AI) offers potential solutions, it's not widely adopted due to a lack of specialized tools and inherent inaccuracies and biases. In my dissertation, I address this gap by combining the complementary strengths of human intelligence and AI. I introduce Photo Sleuth, a novel person identification pipeline that combines crowdsourced expertise with facial recognition, supporting users in identifying unknown portraits from the American Civil War era (1861--65). Despite successfully identifying numerous unknown photos, users often face the `last-mile problem' --- selecting the correct match(es) from a shortlist of high-confidence facial recognition candidates while avoiding false positives. To assist experts, I developed Second Opinion, an online tool that employs a novel crowdsourcing workflow, inspired by cognitive psychology, effectively filtering out up to 75% of facial recognition's false positives. Yet, as AI models continually evolve, changes in the underlying model can potentially impact user experience in such crowd--expert--AI workflows. I conducted an online study to understand user perceptions of changes in facial recognition models, especially in the context of historical person identification. Our findings showed that while human-AI collaborations were effective in identifying photos, they also introduced false positives. To reduce these misidentifications, I built Photo Steward, an information stewardship architecture that employs a deliberative workflow for validating historical photo identifications. Building on this foundation, I introduced DoubleCheck, a quality assessment framework that combines community stewardship and comprehensive provenance information, for helping users accurately assess photo identification quality. Through my dissertation, I explore the design and deployment of human-AI collaborative tools, emphasizing the creation of sustainable online communities and workflows that foster accurate decision-making in the context of historical photo identification. / Doctor of Philosophy / Identifying historical photos offers significant cultural and economic value; however, the identification process can be complex and challenging due to factors like poor source material and limited research resources. In my dissertation, I address this problem by leveraging the complementary strengths of human intelligence and Artificial Intelligence (AI). I built Photo Sleuth, an online platform, that helps users in identifying unknown portraits from the American Civil War era. This platform employs a novel person identification workflow that combines crowdsourced human expertise and facial recognition. While AI-based facial recognition is effective at quickly scanning thousands of photos, it can sometimes present challenges. Specifically, it provides the human expert with a shortlist of highly similar-looking candidates from which the expert must discern the correct matches; I call this as the `last-mile problem' of person identification. To assist experts in navigating this challenge, I developed Second Opinion, a tool that employs a novel crowdsourcing workflow inspired by cognitive psychology, named seed-gather-analyze. Further, I conducted an online study to understand the influence of changes in the underlying facial recognition models on the downstream person identification tasks. While these tools enabled numerous successful identifications, they also occasionally led to misidentifications. To address this issue, I introduced Photo Steward, an information stewardship architecture that encourages deliberative decision-making while identifying photos. Building upon the principles of information stewardship and provenance, I then developed DoubleCheck, a quality assessment framework that presents pertinent information, aiding users in accurately evaluating the quality of historical photo IDs. Through my dissertation, I explore the design and deployment of human-AI collaborative tools, emphasizing the creation of sustainable online communities and workflows that encourage accurate decision-making in the context of historical photo identification.

The primary objective is to explore the scalability of two-dimensional game maps while preserving certain aesthetical qualities in scaled representations. By either upscaling or downscaling the maps, features of the map inducing these aesthetical qualities may diminish. For instance, there could be alterations in the layout of corridors, rooms, characters, and treasures, as well as variations in the quantity of them. To address this, AI technology has been used as a means of preserving the feature soriginally introduced by the designer to create an alternatively scaled representation. The explorationis made possible by utilizing a game designer tool, Evolutionary Dungeon Designer (EDD), to designmaps - scale them - and generate AI-based solutions through an evolutionary algorithm. Furthermore, evaluations through both a user study and a controlled experiment were performed to analyze thescalability of game maps and the AI-generated representations. The user study showed some divisive results regarding whether the scaled or the AI-generated maps were superior. Often the AI-scaled maps were regarded as dissimilar compared to the original map. However, the AI could to some extent provide the same prevalence of some of the wanted features, but in a different design. This was also evident in the controlled experiment, where the AI managed to contain a specific feature to the same degree, but lacked the capability of making the maps similar. / Det primära målet är att utforska skalbarheten hos tvådimensionella spelkartor samtidigt som vissa estetiska egenskaper bevaras i skalförändrade representationer. Genom antingen att förstora eller förminska kartorna kan vissa egenskaper som bidrar till dessa estetiska egenskaper minska. Till exempel kan det finnas förändringar i layouten av korridorer, rum, karaktärer och skatter, liksom variationer i deras antal. För att lösa detta har AI-teknologi använts för att försöka bevara de egenskaper som ursprungligen infördes av designer, genom att skapa alternativt skalförändrade representationer. Utforskningen möjliggörs genom att använda ett speldesignverktyg, Evolutionary Dungeon Designer (EDD), för att designa kartor - skalförändra dem - och generera AI-baserade lösningar genom en evolutionär algoritm. För att analysera skalbarheten hos spelkartor och de AI-genererade representationerna genomfördes utvärderingar genom både en användarstudie och ett kontrollerat experiment. Användarstudien visade delade resultat gällande om skalförändrade kartorna eller AI-skalförändrade kartorna var mest representativ. Ofta ansågs AI-skalförändrade kartor vara olika den ursprungliga kartan. I de AI-skalade kartorna fanns det dock i viss utsträckning en liknande förekomst av de valda egenskaperna, men i en annan design. Detta var också tydligt i det kontrollerade experimentet, där AI skapade kartor som hade samma grad av en specifik egenskap, men saknade förmågan att göra kartorna lika ursprungskartan.