Institutional Repository of Vilnius University
Facebook įrašų komentarų sentimento analizės sistema /
Abstract
dc:descriptionIn this bachelor's thesis, an automatic sentiment analysis system for Facebook post comments has been implemented. The objective of the work is to solve the challenge of efficiently scanning public comments from the complex Facebook platform. Methodology is based on the use of the „Pyppeteer“ Python library in conjunction with the „Chromium“ browser to create a headless operating environment and effectively process the dynamic content of the Facebook platform. For sentiment analysis, the natural language processing tool VADER and the external Komprehend.io sentiment analysis service (API) are implemented, allowing for a comprehensive analysis of social media texts. The developed system efficiently scans and analyzes Facebook comments, presenting the results to users through a web application created using the „Flask“ programming framework. The system demonstrates that, despite Facebook platform blockers and limitations of free sentiment analysis tools, data scraping is feasible even in limited-resource projects through creativity and flexibility. This project reflects the opportunities that modern technologies provide for data collection and analysis, emphasizing the overcoming of technical challenges and deepening the understanding of user emotional trends in Facebook platform posts.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2024
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Šerys, Emilis,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD192063016&prefLang=en_US