AI-assisted code generation tools
Nygård, Joonas (2024-06-13)
J. Nygård
13.06.2024
© 2024, Joonas Nygård. Tämä Kohde on tekijänoikeuden ja/tai lähioikeuksien suojaama. Voit käyttää Kohdetta käyttöösi sovellettavan tekijänoikeutta ja lähioikeuksia koskevan lainsäädännön sallimilla tavoilla. Muunlaista käyttöä varten tarvitset oikeudenhaltijoiden luvan.
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:oulu-202406144516
https://urn.fi/URN:NBN:fi:oulu-202406144516
Tiivistelmä
The rapid advancement of Artificial Intelligence (AI) has significantly impacted various domains during the recent years. In the field of software engineering, AI-assisted code generation tools have been revolutionizing conventional practices. This thesis delves into the impact of these tools on software engineers' work. The goal was to address a gap in existing literature by capturing the users view on these tools by analysing the user reviews for AI-assisted code generation tools. Data collection and analysis for Socio-Technical Grounded Theory (STGT) method was followed to extract categories from the user reviews.
The findings of this study support the understanding that these tools improve software professionals’ productivity, learning and even satisfaction in work. From quality aspect, the users value the usability and correctness, while unsuitable business models or high price can cause deep resistance in the userbase. From different features, the users valued most the code completion, chat assistant, and documentation features.
This study provides valuable insights into users' perspective on AI-assisted code generation tools, offering new paths for future research. Notably, the research highlights the potential influence of these tools on software professionals' well-being and satisfaction, as well as the emerging discourse surrounding their business and ethical implications.
The findings of this study support the understanding that these tools improve software professionals’ productivity, learning and even satisfaction in work. From quality aspect, the users value the usability and correctness, while unsuitable business models or high price can cause deep resistance in the userbase. From different features, the users valued most the code completion, chat assistant, and documentation features.
This study provides valuable insights into users' perspective on AI-assisted code generation tools, offering new paths for future research. Notably, the research highlights the potential influence of these tools on software professionals' well-being and satisfaction, as well as the emerging discourse surrounding their business and ethical implications.
Kokoelmat
- Avoin saatavuus [37254]