Refine
Document Type
- Bachelor Thesis (2)
Year of publication
- 2019 (2) (remove)
Keywords
- Social Media (2) (remove)
Institute
- Angewandte Computer‐ und Biowissenschaften (2) (remove)
Diese Arbeit hat zum Ziel, auf Basis eines neuronalen Netzes eine Sentimentanalyse für deutsche Facebook-Kommentare durchzuführen und die erzielte Güte der Klassifikation im Vergleich zu anderen Verfahren zu bewerten. Dazu werden als Datengrundlage alle Kommentare (01.12.2018) des Facebook-Auftrittes der Deutschen Bahn und des deutschen Einzelhändlers Lidl verwendet.
Social media platforms play an increasing role in marketing, politics and police affairs, because they can strongly influence opinions. So called “opinion leaders” exert their influence in a given network and shape the opinions of other users. Identifying central nodes in a social graph has been of interest for decades. However, not all centrality measures were developed for social media platforms. They were built for social graphs, which did not include additional metrics (e.g. “likes”, “shares”). Nevertheless, these metrics play a crucial role on modern platforms. Hence, outdated measures need to be adjusted and additional metrics need to be integrated to ensure the best possible results.