Det nya verktyget ChatGPT riskerar att kollidera med akademisk integritet och förändra traditionella utbildningsformer då chatboten klarar av att författa trovärdiga uppsatser på kommando. Det är därför av intresse att undersöka acceptans och användande av ChatGPT hos studenter och doktorander, för att förstå teknologins framtid inom akademisk utbildning. Huvudsyftet med denna studie var att, med utgång från UTAUT-modellen, undersöka studenters och doktoranders inställning, beteendeavsikt och användande relaterat till ChatGPT och chatbots inom akademisk utbildning. Enkäten besvarades av totalt 38 studenter (29 kvinnor, 9 män) och 29 doktorander (14 kvinnor, 14 män, 1 föredrog att ej uppge) i ålder mellan 18-45+. Resultatet visade låg användarfrekvens, liten vana och låg beteendeavsikt att använda ChatGPT eller chatbots. Påverkande faktorer för avsikt att använda var främst förväntad nytta av ChatGPT. Påverkande faktorer för amvändarbeteende var främst beteendeavsikt samt erfarenhet. Både farhågor (ex. plagiering, sämre kritisk och kreativ tänkande) och positiva aspekter (ex. inspiration, förbättrat skrivande) av potentiell användning lyftes. Många doktorander ansåg att ChatGPT idag inte uppfyller kraven för studier på högre nivå. Dock förutspådde flertalet att ChatGPT kommer finnas med som en oundviklig del i samhällets digitalisering samt att chatbotar kommer att utvecklas, bli mer användbara och därför ta större plats i akademisk utbildning i framtiden. Det är viktigt att universitetet följer utvecklingen av Chat GPT-användande för att kunna anpassa sätt att lära ut såväl som existerande regelverk gällande fusk. / The new tool ChatGPT risks colliding with academic integrity and changing traditional forms of education because the chatbot can write credible essays on command. Therefore, examining the acceptance and use of ChatGPT among undergraduates and graduate students is of great interest in order to understand the future of technology in academic education. The main purpose of this study was to investigate, based on the UTAUT model, students' and doctoral students' attitude, behavioral intention and use related to ChatGPT and chatbots in academic education.The questionnaire was answered by a total of 38 students (29 women, 9 men) and 29 PhD students (14 women, 14 men, 1 preferred not to state) aged between 18-45+. The results showed low frequency of use, little habit and low behavioral intention to use the technology. Factors influencing intention to use were mainly expected benefits of ChatGPT. Influencing factors for Use Behavior were mainly behavioral intention and experience. Both concerns (eg, plagiarism, poorer critical and creative thinking) and positive aspects (eg, inspiration, improved writing) of potential use were addressed. Many PhD students felt that ChatGPT today does not meet the requirements for higher studies. However, the majority predicted that ChatGPT will become an inevitable part of society's digitization and that chatbots will evolve, become more useful and therefore take a greater place in academic education in the future. It is important that universities are aware of ChatGPT usage in order to adapt ways of learning as well as existing regulations regarding cheating.

In the world of Artificial intelligence, chatbots are a very useful application for the humans to receive answers quickly and solve their problem. However, it has been observed that various departments within a company have diverse use cases or domains, which has contributed to the rise of chatbots. Owing to this, it will be challenging for customers to find the most suitable chatbot for their concern but also to place these chatbots that are geared toward external customers on a single webpage. This thesis has proposed the idea to develop a Concierge bot as a proof of concept and offer the best outcomes in all feasible circumstances as well as the practical potential in order to prevent these problems. In this project, a Concierge bot has been implemented that can access the NLUs of the client bot and route customers to the right client chatbot based on their requests. The Cognigy platform was utilized to develop the client chatbots, including the Concierge bot, and an external Concierge service (Azure Function) was used to send HTTP requests to numerous client bots concurrently. The obtained results in terms of performance with various client bot responses and customer interaction are quite promising. The successful implementation of the proposed idea has also brought up a variety of opportunities and challenges for the subsequent work.

[pt] Chatbots são programas de computador que interagem com usuários utilizando linguagem natural. Desde sua origem, a tecnologia avançou significantemente e aplicações baseadas na nuvem de grandes empresas permitiram que desenvolvedores criassem chatbots inteligentes e eficientes. No entanto, não há muitas abordagens de desenvolvimento aos principais módulos de um chatbot que são flexíveis o suficiente para permitir a criação de chatbots diferentes para cada domínio, mantendo um robusto controle de diálogo na aplicação. Existem trabalhos que tentam desenvolver uma abordagem mais flexível, cada um com suas vantagens e desvantagens. Uma das vantagens mais notáveis é o uso de sistemas multiagentes para distribuir e realizar tarefas feitas por chatbots. Nesse contexto, este trabalho propõe um framework geral e flexível baseado em sistemas multiagentes para construir chatbots em um domínio escolhido pelo desenvolvedor, com controle de diálogo na aplicação. Esta solução usa uma adaptação da abordagem de estado da informação, e agentes de software, para gestão do diálogo. Para validar a arquitetura proposta, um cenário de uso com 4 chatbots de prova de conceito são analisados e discutidos. / [en] Chatbots are computer programs that interact with users using natural language. Since its inception, the technology has advanced greatly and cloud-based platforms from big companies allow developers to create intelligent and efficient chatbots. However, there are not many development approaches to the main modules of a chatbot that are flexible enough to allow the creation of different chatbots for each domain, while maintaining a robust dialogue control in the application. There have been some works that try to develop a more flexible approach, each of them with their own advantages and disadvantages. One of the most notable advantages is the use of multi-agent systems to distribute and perform the tasks performed by the chatbot. In this context, this work proposes a general and flexible architecture based on multi-agent systems for building chatbots in any domain chosen by the developer, with dialogue control in the application. This architecture uses an adaptation of the information state approach, also using software agents, to perform dialogue management. To validate the proposed architecture, an user scenario involving the implementation of 4 proof of concept chatbots is analyzed discussed.

Aufgrund eines bedeutenden technologischen Fortschritts im Bereich der künstlichen Intelligenz (KI) sind eine Vielzahl neuer Systeme und Anwendungen entstanden, die eine künstliche Interaktion und Kommunikation mit Nutzern ermöglichen (Gnewuch, Morana, & Maedche, 2017; Maedche, Morana, Schacht, Werth, & Krumeich, 2016). Neben spezifischen Anwendungen in Form von virtuellen Assistenten (VA), wie Apples Siri oder Amazonas Alexa, entwickeln Unternehmen zunehmend Chatbots und Enterprise Bots für die Interaktion mit Kunden. Im Jahr 2016 hat Facebook ihren Messenger für Chatbots geöffnet wodurch mittlerweile über 34.000 Chatbots auf Facebook vorhanden sind. Auch Microsoft hat mit Cortana eine Möglichkeit geschaffen, mit einem Chatbot zu interagieren. Der Messangerdienst Telegram ermöglichte diese künstliche Interkation bereits im Jahr 2015 und Google stellt mit seinem Dienst Dialogflow ein einfaches Angebot zur Erstellung eigener Chatbots für Unternehmen bereit (Stäcker & Stanoevska-Slabeva, 2018). Das Jahr 2017 wird auch als der zweite Frühling der Chatbots bezeichnet (Haberich, 2018). Klar (2018) sagt, dass Chatbots im Kundenservice in allen Branchen eine immer wichtigere Rolle spielen und sogar von Kunden gewünscht werden. Auch wenn Chatbots bereits vielseitig im Kontakt mit Kunden eingesetzt werden, fehlen konkrete wissenschaftliche Studien zu der Akzeptanz von Kunden im Bereich der Bedürfniserhebung. Die Erfüllung von Kundenbedürfnissen ist ein zentrales Element eines Unternehmens, wodurch die Erhebung dieser Kundenbedürfnisse einen hohen Stellenwert einnimmt (Jacob, 2018). Die Erhebung von Kundenbedürfnissen ist mit viel Aufwand verbunden, welches unter anderem ressourcenintensive Studien der Marktforschung oder Analysen bestehender Daten mit sich zieht. Die direkte Bedürfniserhebung durch Kundenberater ist darüber hinaus mit einem hohen Zeit- und Personalaufwand verbunden, da möglichst jeder Kunde unmittelbar betreut werden sollte (Jacob, 2018). Eine Beratung durch einen intelligenten künstlichen Kundenbetreuer, könnte somit eine enorme Kosten- und Zeitaufwandsreduktion hervorrufen und dennoch eine Kundenzufriedenheit und somit Loyalität erzeugen. Ziel dieses Artikels ist es, herauszufinden inwieweit Chatbots in der B2C-Kommunkiation die Bedürfnisse des Kunden an bestimmten Touchpoints erheben können. Dafür wurde eine empirische Studie mit einem explorativen Fragebogen mit 131 Probanden durchgeführt. [... aus der Einleitung]

Det blir mer uppenbart att många företag allt oftare väljer att använda sig av chatbotar. Främst gäller detta kundcentrerade sidor inom exempelvis e-handel där chatboten agerar som ett verktyg för att underlätta för kundtjänsten genom att kunna svara på enklare frågor. Majoriteten av människor idag har använt en chatbot och en del uppfattar den som hjälpsam, medan andra tycker att den är i vägen och inte är tillräckligt kompetent för att svara på specifika frågor. Detta gör att användare oftast har fått en uppfattning om chatbotar och hur den bidrar till upplevelsen av sidbesöket som helhet. Användarupplevelse, eller “UX”, avser till hur en användare nyttjar och upplever ett gränssnitt genom att ta hänsyn till mänskliga beteenden och vad användaren vill uppnå med besöket. På så vis skapas positiv användarupplevelse samt gör det användbart. Målet med denna uppsats att undersöka hur användarupplevelsen påverkas av interaktion med chatbotar vid besök av svenska webbplatser. Området för att undersöka användarupplevelsen har varit på en banksida - Nordea, samt två sidor inom området för e-handel inom mode - Nelly och Bubbleroom. Studien har fokuserat på att lyfta fram användarupplevelse i olika vinklar och perspektiv. Den är dels baserad på teorier inom interaktionsdesign så som begreppet UX och användbarhet, och dels centrerad kring generell teori om chatbotar och kundservice. Utifrån teorier och modeller användes olika metoder för att insamla data som grund för resultatet. Dels har en variant av användbarhetstestning använts, kallat “tänka högt-metoden”, och dels har olika intervjuer genomförts för att få en bakgrund kring vad företag har för strategier med sina chatbotar. Metodiken har utgått från studiens olika fokusområden för att kunna diskutera hur väl chatboten spelar roll för användarupplevelsen vid besöket på webbplatsen. Mätvärden har insamlats i form av exempelvis tid, framgång och känslor gentemot uppgifterna som användarna genomförde för att skapa interaktion med sidan och potentiellt med chatboten. Resultaten påvisade att graden av användarupplevelse kan ses som både god och dålig, där både önskade samt oönskade upplevelser kunde uppfattas från användarna. Detta kunde observeras i form av varierande grad av slutföranden av uppgifter, tid och om förväntningarna innan sidbesöket levdes upp till efter interaktionen med sidan och chatboten. / It is becoming increasingly clear that many businesses more often choose to use chatbots. This mainly applies to customer-centric sites in, for example, e-commerce, where the chatbot acts as a tool to facilitate customer service by being able to answer simple questions. Most people today have used a chatbot and some perceive it as helpful, while others think it is in the way and is not competent enough to answer specific questions. This means that users have usually gained an idea of ??chatbots and how it contributes to the experience of the page visit. User experience, or “UX”, refers to how a user uses and experiences an interface by considering human behaviors and what the user wants to achieve with the visit. In this way, a positive user experience is created and made useful. The aim of this essay is to investigate how the user experience is affected by interaction with chatbots when visiting Swedish websites. The area for investigating the user experience has been on a banking site - Nordea, and two sites in the area of ??e-commerce in fashion - Nelly and Bubbleroom. The study has focused on highlighting user experience in different angles and perspectives. It is partly based on theories in interaction design such as the concept of UX and usability, and partly centered around general theory about chatbots and customer service. Based on theories and models, different methods were used to collect data as a foundation for the results. On the one hand, a variant of usability testing has been used, called the "think aloud method", and on the other hand, various interviews have been conducted to get a background on what strategies companies have with their chatbots. The methodology has been based on the study's different focus areas in order to be able to discuss how well the chatbot plays a role in the user experience during the website visit. Measured values ??have been collected in the form of e.g time, success and emotions towards the tasks and scenarios conducted by the users to create interaction with the site and potentially with the chatbot. The results showed that the degree of user experience can be seen as both good and bad, where both desired and unwanted experiences could be perceived from the users. This could be seen by the varying degrees of completion of tasks, time and if the expectations before the page visit were lived up to after the interaction with the page and the chatbot. This study has been conducted in Sweden and thus written in Swedish.

Conversational interfaces (CIs) have been a trending topic in recent years. As of the last decade, CIs have emerged with the aim of simplifying human-machine interactions and found a wide use case in the market. For example, Siri and Google Assistant are some of the most well-known CIs developed by the tech giants Apple and Google. The digital landscape has evolved from web, to mobile apps, to recently CIs. Nowadays, CIs, in particular chatbots and voicebots, are becoming increasingly common. Whether navigating the web or messaging on a phone, it is likely that CIs have been confronted offering the user help.However, CIs have not managed to reach a large-scale use. Furthermore, the reasons regarding the challenges faced by CIs as well as their usability are not greatly explored. In this thesis, we explore the most relevant uses of CIs and the reasons hindering a widespread use of CIs. Our goal is to provide an insight into CIs’ uses and list the reasons regarding the challenges faced by CIs. The research study followed a mixed method approach connecting an explorative qualitative literature study, a survey and an interview. The data was collected by using a systematic mapping approach for it being more suitable for conducting an effective literature review. The survey and the interview were conducted in order to confirm the findings.According to our research, it was found that the most common use cases of CIs were in customer service, sales, travel and bookings, education, healthcare and as voice assistants. The most prominent challenges faced by CIs were poor usability, language processing and understanding, speech recognition and natural language generation and security and privacy. As a conclusion, the future looks promising for CIs, however, they need to be furher researched and developed in order to help them reach a widespread use in the future. / Konversation Gränssnitt (CIs) har varit ett trendande ämne de senaste åren. Sedan det senaste decenniet har CIs kommit fram i syfte att förenkla interaktioner mellan människor och maskiner och har hittat ett brett användningsfall på marknaden. Det digitala landskapet har utvecklats från webb, till mobila appar till nyligen CI. Numera blir CIs, i synnerhet chatbots och voicebots, allt vanligare. Vare sig du navigerar på webben eller meddelanden i en telefon, är det troligt att CIs har konfronterats med att erbjuda användaren hjälp.CIs har dock inte lyckats uppnå storskalig användning. Dessutom är orsakerna till de utmaningar som CIs står inför och deras användbarhet inte utforskas i hög grad. I den här avhandlingen undersöker vi de mest relevanta användningarna av CIs och orsakerna till en utbredd användning av CIs. Vårt mål är att ge en inblick i CI: s användningar och lista orsakerna till de utmaningar som CIs står inför. Forskningsstudien följde en blandad metodstrategi som ansluter en utforskande kvalitativ litteraturstudie, en undersökning och en intervju. Uppgifterna samlades in med hjälp av en systematisk kartläggningsätt för att göra dem mer lämpliga för att genomföra en effektiv litteraturgranskning. Undersökningen och intervjun genomfördes för att bekräfta resultaten.Enligt vår forskning konstaterades att de vanligaste användningsfallen för CIs var kundservice, försäljning, resor och bokningar, utbildning, sjukvård och som röstassistenter. De mest framstående utmaningarna för CIs var dålig användbarhet, språkhantering och förståelse, taligenkänning och naturlig språkgenerering och säkerhet och integritet. Sammanfattningsvis ser framtiden lovande ut för CIs, men de måste undersökas och utvecklas ytterligare för att hjälpa dem att uppnå utbredd användning i framtiden.

This thesis is a critique on the ease in which humans tend to anthropomorphize chatbots, assigning human characteristics to entities that fundamentally will never understand the human experience. It will be further exploring these consequences on our society's socio-cultural fabric, representations of the self and identity formation in terms of communication and the essence of humanity.

Chatbots are becoming increasingly common within both private and public sectors as they are implemented for organizations to provide service at any time. Within related research on the topic, the focus lies on the private sector and chatbot users, while the research on how chatbot implementation may affect the employees within the public sector is lacking. The focus of this thesis is therefore to provide more information about chatbot implementation within the public sector. More specifically, to understand how the employees expect and experience that the implementation of chatbots can affect them in their work and ways to communicate information.  In this study, eight semi-structured interviews with a duration of one hour each were conducted, where the interviewees were employees in municipalities and universities who are working with chatbot implementation. The results show that the interviewees expect that there will be a decreased workload and increased time to work on more complex tasks. However, the time that is liberated because of the chatbot needs to be reinvested into its upkeep, and the interviewees experience that new tasks are added to fill that time, indicating that their expectations are unfulfilled.  The results also show that the interviewees expect the chatbot to increase their availability and that it will be a new, less formal way to communicate information. It is experienced that people can contact them any time through the chatbot. They experience that the chatbot uses a simple language to communicate information and that it presents information like it would be presented by a human.

Chatbots are an increasingly popular technique that has seen recent steps in development thanks to artificial intelligence. There is research conducted about chatbots in different areas, but one area that is overlooked is the presentation of data collected by the chatbot. This study aimed to explore what to think about in terms of visualizations when designing an interface in order to present chatbots results to novice users. Conducting a user study with several iterations of design, the research question was: How do you visualize the results of a chatbot survey for novice users to facilitate the understanding of the data? To answer this question, four design iterations with a total of 17 participants were conducted, resulting in a final prototype. The data gathered was then analyzed using thematic analysis. The results failed to help answering the research question, but did give some suggestions on interface visualization, mainly the importance of using visualizations that are carefully selected to improve the understanding of the data presented. Moreover, this study suggests the importance of focusing on the participant’s deeper level of understanding and their conceptual models.

Hoy en día, vivimos en un mundo digitalizado, donde cada vez más las empresas intentan brindar mejores servicios para diferenciarse entre unas y otras. De esta manera, los chatbots permiten atender las consultas de los clientes y brindar un servicio diferente. En esta investigación, se analiza el uso de chatbots en el sector bancario peruano y cómo impacta en la satisfacción del cliente. Además, se observa el efecto que tiene la calidad de servicio, calidad de información y facilidad de uso. Los datos fueron recolectados de 250 encuestados. Los resultados proporcionan una visión a los bancos para poder fortalecer la satisfacción de sus clientes a través de los chatbots. / Nowadays, we live in a digitized world, where more and more companies try to provide better services to differentiate between them. In this way, chatbots allow to answer customer queries and provide a different service. In this research, I analyze the use of chatbots in the Peruvian banking sector and how it impacts customer satisfaction. In addition, the effect of quality of service, quality of information and ease of use is observed. Data was collected from 250 respondents. The results allowed a vision for the banks to be able to strengthen the satisfaction of their clients through chatbots. / Trabajo de investigación