This study focuses on virtual services and more particularly on the usage of chat services to provide a formal evidence of the status of one particular chat reference service. It explores the efficiency of the chat service model at Umeå University Library for the period August 2015 to February 2016 and covers a total of 221 virtual chat transactions. It uses content analysis and a process model of chat-based reference to bring comprehension of the content for both inquiries and replies to understand the usage of this service and discern trends and discrepancies. The results show that September and February have the highest amount of questions due to the distribution of the academic year. Furthermore, the requests appeared to be spread evenly over the distinguished categories with a slightly lower number of research related questions which reflect the difficulty to perform a reference interview in the virtual context. The study uncovered that the types of inquiries affect the level of completeness and consequently questions requiring general knowledge of the library are more successfully answered than more specific questions. The referrals are connected to the knowledge area of the librarian answering the chat and remain internal. Those results can be easily improved through skill development programs but librarian evaporation remains a predominant issue that should be addressed. Despite the circumstantial attendance of the chat, the chat service appears to be a valid alternative to the information desk and the library management should improve the chat efficacy by involving more competences.

This graduation report explores the integration of Artificial Intelligence (AI) tools, specifically OpenAI's Generative Pre-trained Transformer (GPT) technology, into web development processes using WordPress (WP) for developing a AI-driven chat service. The focus of the project is on ImagineX AB, a private company that offers the educational service ChatGPT Utbildning aimed at teaching professionals to effectively utilize ChatGPT. The project is motivated by the rapid growth and adoption of AI tools such as ChatGPT, underpinned by the observed increase in user base and its integration into significant platforms, like Microsoft's Bing and Office packages. Despite its promising potential, the application of such AI tools in web development remains underexplored and untested in several aspects. The graduation report presents the implementation of a GPT model-driven chat service on the ChatGPT Utbildning WP website, enabling visitors to interact with the famous AI tool directly. This feature serves a dual purpose – enhancing user engagement and providing an instant demonstration of the utility of ChatGPT. The agile project management methodology in general is divided into four phases: preliminary work, design solutions, develop solution, and delivery – design and development phases are iterative. In this project, there is two design iterations and three development iterations called “cycles”. The project plan is fulfilled with no deviation. Tests and continuous improvements are done throughout the development, with specific and planned in each phase and cycle. The result is two optimized chat bots in respective well-designed chat boxes with full chat functionality driven by OpenAI API and GPT-3.5/GPT-4 models – user tested and then published on ChatGPT Utbildning website. Additionally, insights in agile management solutions in relation to AI tools have been produced. The detailed construction and in-depth discussion contribute to the wide understanding of AI implementation in web development, providing practical insights into the application of ChatGPT in a real-world setting by agile project management. Furthermore, it underscores the transformative potential of AI tools in shaping web solutions and web development, and propelling innovation in the field. The report delves into discussion of technology, ethics, society, and implications on future web development. / Rapporten ämnar redogöra integreringen av artificiell intelligens (AI) instrument, särskilt OpenAI's Generative Pre-trained Transformer (GPT) teknologi, inom ramen för webbutvecklingsprocesser, inklusive agil projektledning, med användning av WordPress (WP), i syfte att utveckla en AIdrivande chatttjänst. Fokus för projektet är på företaget ImagineX AB, en privat aktör som erbjuder en utbildningstjänst benämnd ChatGPT Utbildning med mål att undervisa yrkesverksamma i effektivt bruk av ChatGPT. Motivationen för projektet härstammar från den snabbt växande tillväxten och adoptionen av AI-instrument som ChatGPT, vilket stärks av den observerade tillväxten av användarbasen och dess integrering i betydande plattformar, såsom Microsofts Bing och Office-paket. Trots den lovande potential som dessa AIinstrument innehar, finns det fortfarande delar inom webbutveckling där användningen av sådana verktyg förblir ouppklarade och otillräckligt utforskade. Rapporten visar implementeringen av en GPT-modell-drivande chattjänst på ChatGPT Utbildning WP-webbplatsen, vilket möjliggör direkt interaktion för besökare med det framstående AI-instrumentet. Denna funktion har ett tvåfaldigt ändamål - att förhöja användarengagemang och att ge en omedelbar demonstration av ChatGPT:s användbarhet. Den använda smidiga projektledningsmetodiken är typiskt uppdelad i fyra faser: preliminärt arbete, designlösningar, utvecklingslösningar samt leverans - designoch utvecklingsfaser är iterativa vilket omfattar två designiterationer och tre utvecklingsiterationer refererade till som "cykler". Projektplanen har följts utan avvikelser. Testning och kontinuerliga förbättringar har genomförts under hela utvecklingsprocessen, med specifika och planerade insatser i varje fas och cykel. Resultatet manifesteras i två optimerade chattrobotar inom respektive välutformade chattfönster, med fullständig chattfunktionalitet som drivs av OpenAI API samt GPT-3.5/GPT-4 modellerna - vilka har användartestats och därefter publicerats på ChatGPT Utbildning webbplatsen. Ytterligare insikter rörande agil projektledning i relation till AI-frågor erhålls också. Den detaljerade konstruktionen och den djupgående diskussionen bidrar till en omfattande förståelse för AI-implementering inom webbutveckling och ger praktiska insikter om tillämpningen av ChatGPT i en realistisk inställning med smidig projektledning. Vidare framhäver det den transformerande potentialen hos AI-instrument för att utforma webblösningar och webbutveckling, vilket främjar innovation inom området. Rapporten avslutas med diskussioner kring teknik, etik, samhälle och implikationer för framtida webbutveckling.

Creating effective functions in website designs that reduce consumers' anxiety in shopping online is a challenge common to most e-retailers. The present study investigated the roles of online reputation systems and instant chat services in decreasing customer perceived risk and increasing initial trust in unfamiliar e-retailers. Therefore, the reputation system when coupled with live chat service may be an effective external mechanism for providing potential consumers with critical decision making information. The present research focused on examining the respective value of live chat services and reputation systems in reducing potential consumers' perceived risk and simultaneously increasing their initial trust towards an unfamiliar e-retailer. The present research tested an e-retailing trust model based on the consumer decision making process. The model incorporated the following variables: (1) live chat service, and (2) reputation system, and explanatory variables: (1) perceived risk and (2) an initial trust. Customer prediction of purchasing is the response variable. The moderating role of interdependent and independent self-construal on online consumers’ behavior was also examined. Based on the review of literature, the following hypotheses were developed: (H1) Perceived risk associated with an unfamiliar web retailer will vary as a feature of the reputation system feature of a web retailer; where the reputation is positive, perceived risk will decrease. (H2) Perceived risk associated with an unfamiliar web retailer will vary as a feature of the instant chat feature of a web retailer; the mere presence of a live chat feature will decrease perceived risk. (H3) Initial trust associated with an unfamiliar web retailer will vary as a feature of the reputation system feature of a web retailer; where the reputation is viewed as negative, perceived risk will increase. (H4) Initial trust associated with an unfamiliar web retailer will very as a feature of the instant chat feature of a web retailer; the mere absence of a live chat feature will result in an increase in perceived risk. (H5) Purchase Intention will be influenced by the live chat function in the e-retailing website. (H6) Purchase Intention will be influenced by the evaluation system presented in the website. (H7) Purchase Intention will be influenced by the customers' perceived risk. (H8) Purchase intention will be influenced by the customers' initial trust. (H9) There is no interaction effect between the perceived risk and initial trust. (H10) Self-construal will moderate the effects on initial trust and perceived risk. A two by two factorial between-subjects experiment was conducted using a mock retail website design to examine the effect of reputation system and live chat service on customers. The findings demonstrated that the evaluation system significantly influences customers' perceived risk and initial trust, and directly influences customers' purchase intention. Perceived risk and initial trust influence customers' purchase intention independently. For future marketing implications, this research suggests that positive customer reviews, transaction history or other evaluation details in the web presentation is crucial for a starting e-retailer. Although there is no significant direct effect of self-construal on the perceived risk and initial trust, this research demonstrated that female and male have different self-construal and self-construal can be a good mediator to observe its effects on the customers' attitude and behavior. Furthermore, customers' initial trust and perceived risk determine their behavior separately which indicates that customers' initial trust increase doesn’t mean their perceived risk will decrease. / Graduation date: 2012