• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 3
  • Tagged with
  • 3
  • 3
  • 3
  • 3
  • 2
  • 2
  • 2
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
1

Sentiment analysis in social events

Liu, Qiaoshan January 2018 (has links)
Purpose: The purpose of this study is going to visualize the public sentiment on expected and unexpected social events. Exploring the relationship between tweets forwarding and sentiment. Design/methodology/approach: This research related to sentiment analysis of social events applied a lexicon-based method. The social events come from Facebook data breach and Ireland vote on abortion event. The study conducted This study focused on how the public sentiment changes over time and the relationship between sentiment and tweet forwarding. Bing lexicon and NRC lexicon are adopted in the analysis. Result: The result of this study is the dominant sentiment trend is consistent with the trend of the number of tweets over time in the Facebook data breach and Ireland vote on abortion. Besides, the sentiment has affected people forward tweets in this research.
2

Optimizing Lexicon-Based Sentiment Analysis for COVID-19 Twitter : Interactions in Health Contexts

Ramin, Jafari January 2023 (has links)
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.
3

The Influence of Artificial Intelligence on Education: Sentiment Analysis on YouTube Comments : What is people´s sentiment on ChatGPT for educational purposes?

Rodríguez Roldán, Javier January 2024 (has links)
The use of artificial intelligence (AI), especially ChatGPT, has increased exponentially in the past years, and it can be seen how AI-based tools are being used in several fields, including education. The literature on AI on education (AIEd), how it has been used, its potential uses, opportunities and challenges were reviewed as well as the literature on sentiment analysis on social media to evaluate the best approach. Since education might face notorious changes due to this technology, assessing how people feel about this potential change in the paradigm is essential. Sentiment analysis on YouTube comments of videos related to ChatGPT, the most popular AI tool for education across learners and educators, was performed. It was found that 62.1% of thes ample had a positive feeling regarding this technology for educational purposes, whereas 19.4% had a negative sentiment and 18.5% were neutral. To contribute to the literature on sentiment analysis of YouTube comments, the two most used and best-performing algorithms were used for this task: Naive Bayes and Support Vector Machine. The results show that the first algorithm had a 61.30% accuracy, whereas SVM had a 71.79%.

Page generated in 0.0334 seconds