During the COVID-19 pandemic, the surge in social media usage has elevated interestin sentiment analysis, especially for health-related applications. This bachelor thesisexplores the effectiveness of two lexicon-based sentiment analysis techniques, with afocus on enhancing the accuracy of the Valence Aware Dictionary for SentimentReasoning (VADER) algorithm. This bachelor's thesis delves into two lexicon-basedsentiment analysis methods, primarily aiming to enhance the accuracy of the ValenceAware Dictionary for Sentiment Reasoning (VADER) algorithm. By assessing 5000manually labeled COVID-19-related tweets across four dataset versions, we gauge therelative effectiveness of these methods. The focus lies on understanding the rolepreprocessing techniques play in sentiment analysis and refining the VADER algorithm.The insights drawn can inform the design of more effective public health policies andcommunication approaches by capturing more accurately public sentiment expressed intweets. In health contexts like COVID-19, it's vital to gauge public sentiment, whichhelps identify and manage psychological distress, anxiety, and fear. Through thissentiment exploration, healthcare providers can offer comprehensive care and improvesupport systems and mechanisms during global health crises like COVID-19.
| Identifer | oai:union.ndltd.org:UPSALLA1/oai:DiVA.org:lnu-121781 |
| Date | January 2023 |
| Creators | Ramin, Jafari |
| Publisher | Linnéuniversitetet, Institutionen för datavetenskap och medieteknik (DM) |
| Source Sets | DiVA Archive at Upsalla University |
| Language | English |
| Detected Language | English |
| Type | Student thesis, info:eu-repo/semantics/bachelorThesis, text |
| Format | application/pdf |
| Rights | info:eu-repo/semantics/openAccess |
Page generated in 0.0018 seconds