Popa, Tudor-Mihai (2025) Investigating the Efficacy of LLMs for Sustainability Identification in Stack Exchange Posts. Bachelor's Thesis, Computing Science.
|
Text
bCS2025PopaTM.pdf Download (712kB) | Preview |
|
![[img]](https://fse.studenttheses.ub.rug.nl/style/images/fileicons/text.png) |
Text
Toestemming.pdf Restricted to Registered users only Download (182kB) |
Abstract
In modern society, more and more code gets written chaotically. Many people want to improve their coding style, so they flock to platforms like Stack Overflow to ask fellow programmers on how to improve their coding and write sustainable code. Software sustainability is a term that became more and more popular in the last decades. Large language models have been recently examined by researchers for tasks other than generation: identification and classification. Knowing this and with large language models on the rise, we aim to leverage these models in order to assess their efficiency in identifying the topic of software sustainability in online forums. Our study aims to first create a pipeline and suggest some prompts to use the existing models for the identification of sustainability. We then opt to assess the performance of the models and different prompts on sustainability identification task and see what is required achieve a satisfactory result.
| Item Type: | Thesis (Bachelor's Thesis) |
|---|---|
| Supervisor name: | Andrikopoulos, V. and Ahmadisakha, S. |
| Degree programme: | Computing Science |
| Thesis type: | Bachelor's Thesis |
| Language: | English |
| Date Deposited: | 02 Jul 2025 12:30 |
| Last Modified: | 02 Jul 2025 12:30 |
| URI: | https://fse.studenttheses.ub.rug.nl/id/eprint/35701 |
Actions (login required)
 |
View Item |