This study investigated ChatGPT’s Python code generation capabilities with a quasi-experiment and a case study, incorporating quantitative and qualitative methods respectively. The quantitative analysis compared ChatGPT-generated code to human-written solutions in terms of accuracy, quality, and readability, while the qualitative study interviewed participants with varying levels of programming experience about the usability of ChatGPT for code generation. The findings revealed significant differences in quality between AI-generated and human-written solutions but maintained overall similarities in accuracy and readability. The interviewees reported that ChatGPT showed potential for generating simple programs but struggled with complex problems and iterative development, though most participants were optimistic about its future capabilities. Future research could involve larger samples, more programming languages, and increased problem complexities.

Det pågår en stor förändring i arbetsliv och samhälle i samband med lansering av olika generativa AI verktyg som skapar innehåll varierande former. Centralt i debatten är ChatGPT, som har väckt mängder av diskussioner i media angående risker för missbruk, särskilt inom utbildningssektorn. Denna studie syftar till att skapa och bidra till förståelse över ChatGPT och dess användbarhet, samt utmaningar genom att analysera acceptansen hos lärare och studenter i högre utbildning. Detta genom att använda teorier från nya vetenskapliga artiklarna angående ChatGPT i högre utbildning, samt jämföra dem med kvalitativa data i form av perspektiv och åsikter från lärare och studenter, och slutligen analysera dem i ett samband med tidigare utbildningsteknologier. Studiens resultat tyder på att ChatGPT har relativt blandad acceptans och delvis haft fördelaktiga effekter på genomförandet av uppgifter i högre utbildning beroende på kunskapsämne. ChatGPT har redan uppvisat anmärkningsvärda förändringar i arbetsprocessen för både lärare och studenter, däremot förekommer det obesvarade frågor och etiska problematik vilket för närvarande förhindrar dess möjligheter som ett potentiellt revolutionerande utbildningsverktyg i högre utbildning.

This paper presents an exploratory work on using Large Language Models (LLM) in User Experience (UX) design. Previous research shows that UX designers struggle to envision novel designs and to prototype with AI as a design material. We set out to investigate the question of how designers can be sensitized to LLMs, and their implications for the professional role of UX designers. Using autobiographical design, we develop a prototype of a digital workspace (the “PromptBoard”) for designing and prototyping chatbots utilizing ChatGPT. A design sprint workshop with six participants is performed, in an effort to answer the research questions by working with the PromptBoard. Discussions and participant-designed artifacts are analysed using thematic analysis. Findings include that participants are able to express design ideas and successfully create chatbots using the tool but express a conflicting sense of lacking creativity or ownership of the results. Implications to the field of UX design are discussed.

This research paper analyzes the impact of AI-generated text on academic writing, specifically on authorship and voice. OpenAI's ChatGPT, a large language model, is used as a representative case study. The rise of AI in education has sparked debates regarding its advantages and disadvantages. The use of AI in written assessments and its potential impact on traditional notions of authorship, originality, and academic integrity are key concerns. The present study compares an essay written by a student for an English literature course with an equivalent essay generated through ChatGPT. It investigates whether AI can meet the formal requirements of academic writing and the distinctiveness of voice in the generated text, through the lens of assertiveness, self-identification and authorial presence. The present study also highlights the difficulties involved in generating such text. The results show that ChatGPT can produce seemingly appropriate context-based texts, but it requires assistance with factual accuracy and the nuanced characteristics of authorship found in human writing. The AI-generated text lacks the depth, specificity, and accurate source referencing present in human-generated text. The present study concludes that although AI has potential as a tool, its current capabilities, particularly in generating academic text, are limited.

This paper studies how the newly released AI ChatGPT can be used to reduce the time and effort software developers spend on writing unit tests, more specifically if ChatGPT can generate quality unit tests. Another aspect of the study is how the prompting of ChatGPT can be optimized for generating unit tests, by creating a prompt framework. Lastly how the generated unit tests of ChatGPT compare to human written tests was tested. This was done by conducting an experiment where ChatGPT was prompted to generate unit tests for predefined code written in C# or Typescript which was then evaluated and rated. After the generated unit test had been rated, the next steps were determined, and the process was repeated. The results were logged following a diary study. The rating system was constructed with the help of previous research and interviews with software developers working in the industry which defined what a high-quality unit test should include. The interviews also helped in understanding ChatGPT’s perceived capabilities. The experiment showed that ChatGPT can generate unit tests that are of quality, though with certain issues. For example, reusing the same prompt multiple times revealed that the consistency in the responses was lacking. Inconsistencies included different testing approaches (how setup methods were used for example), testing areas and sometimes quality. The inconsistencies were reduced by using the deduced prompt framework, but the issue could be a current limitation of ChatGPT which could be handled with a future release.

Prompt engineering is the craft of designing prompts in order to get desired answers from language models such as ChatGPT. This thesis investigates how ChatGPT, specifically GPT-4, can be used to detect plagiarism in simple programming exercises. We used a dataset containing seven different original solutions for programming tasks. Every programming task also contained solutions that were plagiarizing the original as well as solutions that did not plagiarize the original. After testing various different prompts on a subset of the dataset, four different prompts were tested on the majority of the dataset. Three of the prompts produced unreliable results to the point that simply guessing whether or not the task solutions were plagiarized would have frequently been more accurate. The fourth prompt was more accurate although still not accurate enough for it to be recommended to use ChatGPT in order to identify plagiarism. / Promptkonstruktion (prompt engineering) är konsten att skapa instruktioner som ger bästa möjliga svar från språkmodeller (language models) såsom ChatGPT. Denna avhandling undersöker hur ChatGPT kan användas för att upptäcka plagiat i enkla programmeringsuppgifter. Vi använde ett dataset som innehåller sju olika originallösningar på enkla programmeringsuppgifter. Varje programmeringsuppgift har plagierade lösningar som löser samma uppgift och icke-plagierade lösningar som också löser samma uppgift. Efter att ha testat olika instruktioner med ChatGPT på en liten delmängd av datasetet, testades fyra olika instruktioner på majoriteten av datasetet. Tre av instruktionerna gav opålitliga resultat till den grad att det ofta skulle gett ett bättre resultat att gissa om lösningarna var plagierade eller inte. Den fjärde instruktionen gav bättre resultat, men fortfarande inte tillräckligt bra för att rekommendera att använda ChatGPT för att identifiera plagiat.

Text-To-Speech systems are challenged by the presence of homographs, words that have more than one possible pronunciation. Rule-based approaches are often still the preferred solution to this issue in the industry. However, there have been multiple attempts to solve the ‘homograph issue’, by exploring statistical-based, neural-based, and hybrid techniques, mostly for English. Ploujnikov and Ravanelli (2022) proposed a neural-based grapheme-to-phoneme framework, SoundChoice, which comes as an RNN and a transformer version and can be fine-tuned for homograph disambiguation thanks to a weighted homograph loss. This thesis trains and tests this framework on Italian, instead of English, to see how it performs on a different language. Moreover, seeing as the available data containing homographs was insufficient for this task, the thesis experiments using ChatGPT as a data-generating tool. SoundChoice was also investigated for out-of-domain evaluation by testing it on data from a Corpus. The results showed that the RNN model reached a 71% accuracy from a baseline of 59%. A better performance was observed for the transformers model which went from 57% to 74%. Further analysis would be needed to draw more solid conclusions as to the origin of this gap and the models should be trained on Corpus data and tested on ChatGPT data to assess whether ChatGPT-generated data is, indeed, suitable as a replacement for Corpus data.

Studien genomfördes med syfte att undersöka användandet av en AI-chatbott för att underlätta registreringen i en social mediaapplikation som ska kunna användas som en resurspool för doktorander och forskare. Studien undersöker hur vi kan förenkla en user onboarding process med hjälp av ChatGPT, detta för att minska belastningen för nya användare och bidra till en väl formulerad användarprofil. Hur en profil bör utformas kan skilja sig beroende på syfte, en användarprofil kan delas in i två kategorier, personlig profil och professionell profil. Denna studie inriktar sig mot den professionella användarprofilen. För att genomföra studien använde vi oss av intervjuer och enkäter för att samla in data, denna data analyserades sedan och utvärderas tematiskt. Studien har formats utifrån de resultat som samlats in via intervjuer och enkäter, dessa resultat och tillvägagångssätt presenteras i denna rapport. Studien genomförde även en analys av tidigare forskning som berör bland annat textsammanfattning för att kunna genomföra studien utifrån en grund som är vedertagen i dagens forskning. Baserat på den data som samlats in kan studien dra slutsatsen att ChatGPT’s förmåga att sammanfatta texter är mycket god och nyttjandet av denna har goda möjligheter att underlätta en registreringsprocess i en applikation. Genom detta kan vi se att en user onboarding process kan förbättras med hjälp av denna teknik. / This study was conducted with the aim of investigating the use of an AI chatbot to facilitate registration in a social media application that can be used as a resource pool for PhD students and researchers. We are investigating how we can simplify a user onboarding process using ChatGPT, this to reduce the burden on a new user and contribute to such a well-formulated user profile. How a profile should be designed can differ depending on the purpose, a user profile can be divided into two categories, personal profile and professional profile. This study focuses on the professional user profile. To conduct the study we used interviews and questionnaires to collect data, this data is then analyzed and evaluated thematically. The study has been shaped based on the results collected via interviews and surveys, these results and approach are presented in this report. We have also carried out an analysis of previous research that concerns, among other things, text summaries in order to be able to carry out the study based on a basis that is accepted in today's research. Based on the data we collected, we conclude that ChatGPT's ability to summarize texts is very good and the use of ChatGPT enables good potential to facilitate a registration process in an application. Through this we can see that a user onboarding process can be improved with the help of this technology.

Background: The incorporation of artificial intelligence (AI), particularly OpenAI's ChatGPT, in higher education, has sparked substantial discourse since its introduction. AI's transformative role in higher education is largely recognized. Despite its potential to revolutionize the pedagogical field, its application raises several concerns. This research seeks to shed light on the dynamics of ChatGPT use in higher education, contributing to the dialogue surrounding AI's educational implications. Purpose: The analysis of the factors influencing ChatGPTs’ adoption, perception, and its effect on learning experience to help the higher education sector deal with challenges and opportunities presented by the chatbot. Method: The study is conducted on a constructivist-interpretivist ground, employing a qualitative, observation-based, exploratory cross-sectional case study. Semi-structured interviews, based on the UTAUT 2 model, are used as the primary data collection method. Thematic analysis was used to analyze the data and create themes, which combined with an abductive approach helped derive broader meaning and implications. Conclusion: Through a trichotomous model, the researchers have identified the primary factors contributing to ChatGPT adoption, its´ role in the post-adoption period, students’ perspectives on the tool and its future integration, as well as what they perceive the role of the educators is in this evolved landscape, and identifying main psychosocial effects the AI tool has on its users. The results highlight the importance of informed decision making, taking a balanced approach to2assimilating ChatGPT into education, paying attention not only to technical benefits but also to impacts on the learner. Suggestions to extend the UTAUT2 model are made. Avenues for further research are opened by the limitations of this study, and by the interplay of the segments in the tri-part model.

Problem formulation: The problem that the thesis research relates to is the limitations of artificially intelligent chatbots as interlocutors. The emotional component of communication plays an essential role in the customer experience, but many users have a negative attitude toward chatbots due to their lack of humanity and empathy. The potential of the new ChatGPT in changing user attitudes toward chatbots is also being explored. However, the limited data available on recent versions of ChatGPT presents an additional challenge for research in this area.  Purpose: Our study aims to study people's emotional responses to human-like chatbots and their impact on user satisfaction. We also explore whether human likeness is a crucial driver of chatbot preference and how the new ChatGPT can change user attitudes toward them in a positive way.  Theoretical framework: The study's theoretical framework considers various aspects of using chatbots based on artificial intelligence (AI) in marketing. In this context, we observe ChatGPT as a revolutionary breakthrough in customer service, capable of improving customer experience and interaction with customer. We emphasise the emotional component of human-chatbot interactions, investigating customer emotions, attitudes, and trust, as well as the chatbot's capacity for empathy and human-like characteristics. Drawing from this theoretical exploration, we formulate four hypotheses to guide our research. Methodology: This quantitative study involves 79 respondents aged 18 years and over. The online survey was conducted using social media for dissemination. The empirical data obtained were coded and analysed using the SPSS program.  Empirical findings: Our study confirms the hypothesis of diverse emotional responses (H4) and a generally neutral emotional response during chatbot interactions (H3). We also find partial support for the presence of negative emotions (H2), but not for consistent positive emotions (H1). The data indicate a range of emotional responses, highlighting the complexity of human reactions to chatbots. Conclusion: Our research provides an overall picture of users' emotional responses to interactions with chatbots. Users show a variety of emotions, mostly neutral, which can change depending on the interaction. We also discovered the potential of the new ChatGPT in changing user attitudes towards chatbots in a more positive or neutral direction. The study also uncovers factors influencing users' emotional responses, such as age, attitudes, and past experiences. The results can be used to develop more effective marketing and business strategies for interacting with chatbots.